mentions - montions.csv

PMCID,Sentence,True?,False?,NER_Tags,Topics
PMC11286849,"Using this technique, we identified 445 proteins with high confidence from trace amounts of highly pure spore preparations, including 52 of the 79 proteins (approximately 70%) previously demonstrated to be localized in spores in the SubtiWiki database and detected through direct protein analysis.",TRUE,FALSE,"(233, 242, 'SubtiWiki', 'subtiwiki')","Molecular interactions, pathways and networks, Gene expression, Model organisms, Endocrinology and metabolism, Phylogenetics"
PMC11286849,The 445 identified proteins were searched against the SubtiWiki and UniProt B.,TRUE,FALSE,"(54, 63, 'SubtiWiki', 'subtiwiki')","Molecular interactions, pathways and networks, Gene expression, Model organisms, Endocrinology and metabolism, Phylogenetics"
PMC11286849,"The identified proteins also included 52 (70%) of the 79 proteins previously annotated as ""sporulation proteins"" in the SubtiWiki database and found in direct protein analysis (marked in yellow in the Supplementary Table S4).",TRUE,FALSE,"(120, 129, 'SubtiWiki', 'subtiwiki')","Molecular interactions, pathways and networks, Gene expression, Model organisms, Endocrinology and metabolism, Phylogenetics"
PMC11286849,The localization of 52 of these 445 proteins in spores is listed in the SubtiWiki database (Supplementary Table S5).,TRUE,FALSE,"(72, 81, 'SubtiWiki', 'subtiwiki')","Molecular interactions, pathways and networks, Gene expression, Model organisms, Endocrinology and metabolism, Phylogenetics"
PMC10832249,MetaPathways v2.5 [37] was used to create the benchmark CAMI environment PGDB (ePGDB) which are PGDBs for microbial communities [38].,TRUE,FALSE,"(0, 12, 'MetaPathways', 'metapathways')","Metagenomics, Microbial ecology, Population genomics"
PMC10832249,MetaPathways utilizes a modified version of PathoLogic for pathway prediction.,TRUE,FALSE,"(0, 12, 'MetaPathways', 'metapathways')","Metagenomics, Microbial ecology, Population genomics"
PMC10832249,PathoLogic was not included in the comparison since MetaPathways uses it to create the ePGDB.,TRUE,FALSE,"(52, 64, 'MetaPathways', 'metapathways')","Metagenomics, Microbial ecology, Population genomics"
PMC10832249,One limitation of the CAMI ePGDB as a benchmark is that it is automatically generated using MetaPathways but the predictions have not been curated so it can be said that the results demonstrate more how similar the other prediction methods are with MetaPathways and PathoLogic than their actual prediction performance.,TRUE,FALSE,"(92, 104, 'MetaPathways', 'metapathways')","Metagenomics, Microbial ecology, Population genomics"
PMC11045623,We used Orbitrap HRMS data of surface water extracts to compare the Automated Target Screening (ATS) workflow with data evaluations performed with the vendor software TraceFinder and the established semi-automated analysis workflow in the MZmine software.,TRUE,FALSE,"(239, 245, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,The ATS approach increased the overall evaluation performance of the peak annotation compared to the established MZmine module without the need for any post-hoc corrections.,TRUE,FALSE,"(113, 119, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"The need for higher throughput data processing in NTS and SS led to the creation of software such as MZmine, which has been used for partially or fully automatic data processing including smoothing, spectra deconvolution, peak detections, and gap filling with sufficient throughput [12, 13].",TRUE,FALSE,"(101, 107, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"In addition to NTS and SS, MZmine can also be used to perform targeted analysis by incorporating user-defined lists of target features and retention times to annotate peaks.",TRUE,FALSE,"(27, 33, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"In this study, we introduce an open-source unsupervised workflow for Automated Target Screening (ATS) of both GC-HRMS and LC-HRMS data and validate its performance against a manual evaluation in TraceFinder (TF) and batch-mode evaluation in MZmine using a real-life data set.",FALSE,FALSE,"(241, 247, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,MZmine (version 2.51) was used for comparing the peak annotation performance of ATS to a sophisticated (semi-)automated analysis workflow.,TRUE,FALSE,"(0, 6, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"MZmine 2.51 was used in this comparison, although a newer version MZmine 3 has been launched during the preparation of the present study.",TRUE,FALSE,"(0, 6, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"As MZmine 3 still uses the same peak detection algorithms, we consider that the results using the older version are comparable [15].",TRUE,FALSE,"(3, 9, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,The details regarding sample extraction and settings of TraceFinder and MZmine can be accessed from Text S1 to Text S3 in Supporting Information S1.,TRUE,FALSE,"(72, 78, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,These “CHECK” cases are similar to the peak status “ESTIMATED” in MZmine.,TRUE,FALSE,"(66, 72, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"Compounds were selected for peak annotation performance comparison if they had at least one annotated response in one of the three evaluation workflows TraceFinder, ATS, or MZmine.",TRUE,FALSE,"(173, 179, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"The peak annotation was compared by calculating the fractions of false positives (FP), false negatives (FN), true positives (TP), and true negatives (TN) of all observations n for MZmine and ATS compared to the manual evaluation in TraceFinder.",TRUE,FALSE,"(180, 186, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,Only features with the “DETECTED” peak status were included in MZmine.,TRUE,FALSE,"(63, 69, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,The highest number of chemicals was identified in TF while ATS and MZmine have a lower number but similar patterns of detected chemicals.,FALSE,FALSE,"(67, 73, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"The comparison of the peak annotation (see Supporting Information S2, Table S2-4) via ATS_raw, ATS_mzML, and MZmine with selected key figures is listed in Table 1.",FALSE,FALSE,"(109, 115, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"For the MZmine analysis of the GC dataset, two sets of retention times were used, (i) a list with retention times as used by ATS with shifts in the range of −1.1 to −0.9 min simulating the case of shifted and not optimized analysis conditions and (ii) the same list of analytes but with exact, shift-corrected retention times as used with TF.",FALSE,FALSE,"(8, 14, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623," Table 1Results of the peak annotation comparison of ATS and MZmineInstrument modeWorkflowTPTNFPFNSensitivitySpecificityAccuracyLC-ESIposATS_raw61110291421300.820.880.86ATS_mzML5161086872230.700.930.84MZmine49710271312570.660.890.80LC-ESInegATS_raw20333483280.880.800.83ATS_mzML17235665580.740.850.81MZmine18431775720.720.810.77GC-EIATS_raw429165691210.780.710.76ATS_mzML382171631680.690.730.71MZmine362091723670.090.540.31MZmine_sc*365163711850.660.700.67*sc shift-corrected, TP true positives, TN true negatives, FP false positives, FN false negatives.",FALSE,FALSE,"(61, 67, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,Results of the peak annotation comparison of ATS and MZmine,FALSE,FALSE,"(53, 59, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"The greatest improvement was observed for the sensitivity, which increased around 1.3-fold if ATS_raw is used compared to MZmine.",FALSE,FALSE,"(122, 128, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"However, this could only be achieved for the shift-corrected dataset for MZmine, where the retention times were adjusted a priori to exactly match the correct times as used in TF.",FALSE,FALSE,"(73, 79, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,ATS increased overall performance and accuracy compared to MZmine (see Table 1).,FALSE,FALSE,"(59, 65, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"While some key numbers like sensitivity and specificity or even accuracy are in a similar range for ATS and MZmine (see Table 1), one has to consider that ATS was using a target feature list which was randomly shifted in the range of −1.1 and −0.9 min while MZmine was only performing well if retention times were exactly as observed for the datasets.",FALSE,FALSE,"(108, 114, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"For MZmine annotation, retention times of the compound list have to be adjusted prior to annotation in another software (e.g., R or MS Excel), and in TF all expected retention times can be adjusted after visual inspection globally in the method or in relation to internal standards serving as retention time reference.",FALSE,FALSE,"(4, 10, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"This was clearly demonstrated for the GC-EI dataset, which performed similarly for the shift-corrected MZmine dataset and the artificially shifted ATS datasets (see Table 1).",FALSE,FALSE,"(103, 109, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"In this case, MZmine lists and assigns both peaks to both compounds in the final feature list, while ATS was able to split the peaks and assign the chemicals correctly (see Supporting Information S1, Figure S1-3A).",FALSE,FALSE,"(14, 20, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,One strategy would be to assign three different features (peaks 1–3) and evaluate them independently in MZmine or manually integrate the three peaks together in TF.,FALSE,FALSE,"(104, 110, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"ATS correctly identified and assigned the respective peak of the EIC, whereas MZmine was only able to do so if the retention times had been accurately shift-corrected and small RT windows in advance.",FALSE,FALSE,"(78, 84, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,"Otherwise, the peak finder of MZmine detects two peaks which have a similar peak pattern but the wrong retention time.",FALSE,FALSE,"(30, 36, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11045623,ATS is able to increase the overall peak annotation accuracy and outperforms sophisticated workflows like MZmine for challenging scenarios like shifted retention times or co-eluting analytes.,FALSE,FALSE,"(106, 112, 'MZmine', 'mzmine')","Proteomics, Metabolomics, Proteomics experiment, Small molecules"
PMC11449484,"coli (strain s_6558), Klebsiella pneumoniae (strain 4300STDY7045912), and Salmonella enterica (strain 350627) were compared with Jalview.",FALSE,FALSE,"(129, 136, 'Jalview', 'Jalview')","Sequence analysis, Data visualisation"
PMC11449484,coli were compared using Jalview.,FALSE,FALSE,"(25, 32, 'Jalview', 'Jalview')","Sequence analysis, Data visualisation"
PMC11449484,"Jalview was used for editing and viewing sequence alignments (Waterhouse et al., 2009).",FALSE,FALSE,"(0, 7, 'Jalview', 'Jalview')","Sequence analysis, Data visualisation"
PMC11373567,"To address the current digital divide amongst LMICs, and between LMICs and HICs, GGN recommended the Leiden Open Variation Database (LOVD) and the ITHANET Portal as platforms for data collection and data sharing.",FALSE,FALSE,"(147, 154, 'ITHANET', 'the_ithanet_portal')","Genetic variation, Genotype and phenotype, Public health and epidemiology, Haematology, Computational biology, Human genetics, Molecular genetics, Population genetics, Genetics, Molecular biology, Biomarkers, Data visualisation, Database management, Rare diseases"
PMC11373567,"By contrast, ITHANET (https://www.ithanet.eu/; accessed on 17 April 2024) is a web portal initially conceived specifically for hemoglobinopathies, which, as of this writing, holds in its databases sequence and functional annotation for 3462 variants in 538 genes.",FALSE,FALSE,"(13, 20, 'ITHANET', 'the_ithanet_portal')","Genetic variation, Genotype and phenotype, Public health and epidemiology, Haematology, Computational biology, Human genetics, Molecular genetics, Population genetics, Genetics, Molecular biology, Biomarkers, Data visualisation, Database management, Rare diseases"
PMC11373567,"More recently, ITHANET launched new databases, namely IthaPhen [71] for genotype-phenotype correlation and IthaCNVs [72] for improved diagnosis of copy number variants in hemoglobinopathies.",FALSE,FALSE,"(15, 22, 'ITHANET', 'the_ithanet_portal')","Genetic variation, Genotype and phenotype, Public health and epidemiology, Haematology, Computational biology, Human genetics, Molecular genetics, Population genetics, Genetics, Molecular biology, Biomarkers, Data visualisation, Database management, Rare diseases"
PMC11373567,"The enormous diversity of causative β-globin mutations and modifier polymorphisms may be illustrated by using quick filters on ITHANET (www.ithanet.eu, accessed 17 April 2024).",FALSE,FALSE,"(127, 134, 'ITHANET', 'the_ithanet_portal')","Genetic variation, Genotype and phenotype, Public health and epidemiology, Haematology, Computational biology, Human genetics, Molecular genetics, Population genetics, Genetics, Molecular biology, Biomarkers, Data visualisation, Database management, Rare diseases"
PMC11373567,"Accordingly, for the quick filter “Haemoglobinopathy/β-thalassaemia” on ITHANET, 491 variants were found that affect the HBB gene and cause β-thalassemia (https://www.ithanet.eu/db/ithagenes?action=list&hem=2), whereas a quick filter for “Functionality/Disease modifying mutations” revealed 886 entries, many of which are associated with changes in β-thalassemia disease severity (https://www.ithanet.eu/db/ithagenes?action=list&func=2).",FALSE,FALSE,"(72, 79, 'ITHANET', 'the_ithanet_portal')","Genetic variation, Genotype and phenotype, Public health and epidemiology, Haematology, Computational biology, Human genetics, Molecular genetics, Population genetics, Genetics, Molecular biology, Biomarkers, Data visualisation, Database management, Rare diseases"
PMC11373567,"These databases are ClinVar, Global Variome shared LOVD, the Globin Gene Server/HbVar, the Malaysian Node of the Human Variome Project Database (MyHVPDb), and ITHANET.",FALSE,FALSE,"(159, 166, 'ITHANET', 'the_ithanet_portal')","Genetic variation, Genotype and phenotype, Public health and epidemiology, Haematology, Computational biology, Human genetics, Molecular genetics, Population genetics, Genetics, Molecular biology, Biomarkers, Data visualisation, Database management, Rare diseases"
PMC11373567,The IthaGenes database (https://www.ithanet.eu/db/ithagenes) [78] provides a graphical user interface with live and advanced search functionality and integrates and links gene and variant entries with other data on the ITHANET Portal and elsewhere.,FALSE,FALSE,"(219, 226, 'ITHANET', 'the_ithanet_portal')","Genetic variation, Genotype and phenotype, Public health and epidemiology, Haematology, Computational biology, Human genetics, Molecular genetics, Population genetics, Genetics, Molecular biology, Biomarkers, Data visualisation, Database management, Rare diseases"
PMC11373567,"ITHANET with IthaGenes is the presently most comprehensive resource for hemoglobinopathies, which, beyond variant information for causative genes, also includes modifiers, detailed information on phenotypic features, detailed epidemiological information, national health policy and management information, and advanced tools for genotype-phenotype prediction for genetic counseling.",FALSE,FALSE,"(0, 7, 'ITHANET', 'the_ithanet_portal')","Genetic variation, Genotype and phenotype, Public health and epidemiology, Haematology, Computational biology, Human genetics, Molecular genetics, Population genetics, Genetics, Molecular biology, Biomarkers, Data visualisation, Database management, Rare diseases"
PMC11373567,The establishment of individual LOVD-based variant databases in GGN member countries and their integration with the ITHANET Portal as a central resource for hemoglobinopathies as part of this effort may be instrumental in initiating essential data-guided disease management in LMICs and in capturing the diversity of hemoglobinopathies as an international resource.,FALSE,FALSE,"(116, 123, 'ITHANET', 'the_ithanet_portal')","Genetic variation, Genotype and phenotype, Public health and epidemiology, Haematology, Computational biology, Human genetics, Molecular genetics, Population genetics, Genetics, Molecular biology, Biomarkers, Data visualisation, Database management, Rare diseases"
PMC11466383,"The Big Skin Health Intervention Fiji Trial (“Big SHIFT”) carried out surveillance for scabies and SSTIs from July 2018 to June 2019 in the Northern Division of Fiji, an area with high prevalence of scabies, prior to a division-wide ivermectin-based mass drug administration (MDA) campaign.",FALSE,TRUE,"(33, 37, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,We extrapolated the total annual number of cases and direct healthcare costs for all divisions in Fiji based upon previous scabies and impetigo prevalence data across all divisions.,FALSE,TRUE,"(98, 102, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"The estimated annual healthcare costs of scabies and related SSTIs in Fiji was US$3.0 million, with cost per capita of $3.3.",FALSE,TRUE,"(70, 74, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,Scabies and related SSTIs lead to a heavy economic burden in Fiji and prevention would reduce these healthcare costs.,FALSE,TRUE,"(61, 65, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"This data is the same as supplement to Hospital admissions for skin and soft tissue infections in a population with endemic scabies: A prospective study in Fiji, 2018–2019 - available at https://figshare.com/articles/dataset/Full_data_set_/13355845 The analysis code for replicating the results is available at https://github.com/EdifofonA/ScabiesSSTI-Costs-Fiji.",FALSE,TRUE,"(156, 160, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"There is a high burden of scabies and related SSTIs at the population level in Fiji, an island country located in the South Pacific Ocean with a census population of 884,887 people in 2017 [6].",FALSE,TRUE,"(79, 83, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"In the Skin Health Intervention Fiji Trial (SHIFT) conducted between 2012–2013, scabies prevalence was measured at 36.4% and impetigo prevalence at 23.4% among residents of three islands of Fiji [7].",FALSE,TRUE,"(32, 36, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"In Fiji, scabies is often initially treated with traditional medicines, and many individuals only seek medical care for prolonged illness or when a secondary skin infection develops [9].",FALSE,TRUE,"(3, 7, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"In 2016, the Fiji Government annual Health Status Report reported that SSTIs caused 4.3% of mortality within the country [10].",FALSE,TRUE,"(13, 17, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"In Fiji, two pilot studies were conducted to provide evidence on MDA [7,11].",FALSE,TRUE,"(3, 7, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,The Skin Health Intervention Fiji Trial (SHIFT) study demonstrated that ivermectin-based MDA was safe and effective in controlling scabies and impetigo in a study population of approximately 2000 people in Fiji [7].,FALSE,TRUE,"(29, 33, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"Big SHIFT was delivered to the whole population of the Northern Division of Fiji, one of four primary administrative units of Fiji (2017 census population, 131,914) [6].",FALSE,TRUE,"(76, 80, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,The Northern division has the highest prevalence of scabies and impetigo among all Fiji divisions–with 1.3 higher odds of scabies and impetigo compared with those in other divisions [8].,FALSE,TRUE,"(83, 87, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,Healthcare in Fiji comprises a government public healthcare system and a smaller private healthcare sector [12].,FALSE,TRUE,"(14, 18, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"In 2019, about US$144 million from the Fiji government’s revenue was allocated to health [13].",FALSE,TRUE,"(39, 43, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"Therefore, we sought to estimate the annual direct healthcare costs of scabies and related SSTIs in Fiji, a middle-income Pacific country with high burden of scabies.",FALSE,TRUE,"(100, 104, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,This study uses prospectively collected data from the Northern Division of Fiji to estimate the costs of healthcare presentations and hospital admissions among patients with scabies and scabies-related SSTIs prior to the delivery of MDA through Big SHIFT.,FALSE,TRUE,"(75, 79, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,Costs are calculated using an ingredients-based approach and then extrapolated to the national level using epidemiological data from Fiji.,FALSE,TRUE,"(133, 137, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"We estimated the mean costs as well as the total annual costs, using extrapolated number of cases in Fiji, to estimate the economic burden at a national level.",FALSE,TRUE,"(101, 105, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,We used this perspective because public provision of most outpatient and inpatient care is free in Fiji and user fees are very low compared with the overall health expenditure in government facilities [12].,FALSE,TRUE,"(99, 103, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"To estimate the quantities of medicines, we supplemented the utilization data collected in the trial with relevant antibiotics and treatment guidelines for scabies and SSTIs in Fiji [16,17].",FALSE,TRUE,"(177, 181, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"We used the average household size in Fiji, 4.2 in 2021 [18], to quantify the number of tubes that would be sufficient to treat the whole family as recommended in the guidelines.",FALSE,TRUE,"(38, 42, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"For those prescribed an injection, we used benzathine penicillin (for impetigo) or cloxacillin (for cellulitis, abscess, or severe SSTI) as recommended by Fiji antibiotics guidelines [16].",FALSE,TRUE,"(155, 159, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"The unit costs per diagnostic test, outpatient visit, admission to PHC facilities, and hospital admission were obtained from a Fiji costing study [20].",FALSE,TRUE,"(127, 131, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"The outpatient visits and admission unit cost estimates from the Fiji costing study includes both recurrent costs (staff time and overheads) and capital costs (building, equipment, beds, furniture, and vehicles).",FALSE,TRUE,"(65, 69, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"The Fiji costing study estimated the costs per bed day for the two hospitals (LTK and CWM), so we used the lower of the values to obtain conservative estimates.",FALSE,TRUE,"(4, 8, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,The cost of surgical procedures was not estimated separately because it was captured in the unit cost of admissions in the Fiji costing study [20].,FALSE,TRUE,"(123, 127, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"Costs obtained in other years and/or different currencies converted to Fijian dollar using the average exchange rate in that year [21], adjusted to 2020 prices using GDP deflator [22], and converted back to US$ using 2020 exchange rates.",FALSE,TRUE,"(71, 75, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"We extrapolated case numbers to all Fiji divisions using the expected annual number of cases in the Northern Division, and the risk ratio (RR) of scabies infestation between the Northern Division and other divisions.",FALSE,TRUE,"(36, 40, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"A study by Romani [8] indicated that scabies and impetigo cases were prevalent in the Northern division compared with other Fiji divisions, with an adjusted odds ratio (OR) of 1.3 for each disease.",FALSE,TRUE,"(124, 128, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"We converted the OR to risk ratio (RR) using the formula in Zhang and Yu [24], and multiplied this RR WITH the risk in the Northern Division to derive the risk for other Fiji divisions.",FALSE,TRUE,"(170, 174, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"To obtain the expected annual cases in other Fiji divisions, we multiplied the annual risk of cases above with the population size for all other Fiji divisions (752,973 based on 2017 census) [6].",FALSE,TRUE,"(45, 49, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"Lastly, we summed up the number of cases for the Northern and the number for other divisions to get the total annual number of cases in all Fiji divisions.",FALSE,TRUE,"(140, 144, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,These extrapolated number of cases in Fiji were multiplied by the mean costs per case to yield the annual costs.,FALSE,TRUE,"(38, 42, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"For ICU, used an average of ICU bed day estimates from two hospitals in the Fiji costing study [20] in the base case, so these two estimates served as our low/high value for sensitivity analysis.",FALSE,TRUE,"(76, 80, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"Ethical approval for Big SHIFT was granted by the Fiji National Health Research Ethics Review Committee (reference: 2018.38.NOR) and the Royal Children’s Hospital Human Research Ethics Committee in Melbourne, Australia (reference: 38020).",FALSE,TRUE,"(50, 54, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"Extrapolating the data from the Northern Division to the rest of Fiji, the estimated annual number of PHC presentations for scabies and related SSTIs was 82,183 (Table 4).",FALSE,TRUE,"(65, 69, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"From a health system perspective, the estimated annual healthcare costs of scabies and related SSTIs in Fiji was US$3.0 million.",FALSE,TRUE,"(104, 108, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,One-way sensitivity analysis indicated that variations in the cost per outpatient visit had the biggest influence on the total cost of scabies and SSTIs in Fiji (Fig 2).,FALSE,TRUE,"(156, 160, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,We used before-intervention data from the Big SHIFT trial in Fiji and extrapolated these costs to the entire country.,FALSE,TRUE,"(61, 65, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,The trial provided rich information on PHC presentations (including visits and admissions) and hospital admissions for scabies and related SSTIs in the Northern Division of Fiji.,FALSE,TRUE,"(173, 177, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"The estimated annual direct healthcare costs of scabies and related SSTIs in Fiji was estimated to be $3.0 million, equivalent to 2.4% of government revenues allocated to health in 2019.",FALSE,TRUE,"(77, 81, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"Scabies and related SSTIs therefore lead to a heavy economic burden in Fiji, raising the potential benefit of prevention programs such as MDA.",FALSE,TRUE,"(71, 75, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"The estimated 23,000 bed days in our study represents 7.1% of admissions for all divisional hospitals in Fiji in 2017 (3.6% of divisional and specialist hospital admissions).",FALSE,TRUE,"(105, 109, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"In countries endemic for scabies like Fiji, patients may not seek treatment of scabies unless it creates a significant disturbance to their quality of life [27].",FALSE,TRUE,"(38, 42, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"This amount is more than double the estimated cost of medicines for treatment of outpatient pneumonia in Fiji [29]; in that study, the average cost of medicines ranged from $1.3 for Nausori PHC to $2.6 for CWMH (in 2020 values).",FALSE,TRUE,"(105, 109, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"While there are few data to guide the attribution of bacterial SSTIs to scabies in highly endemic settings, two lines of evidence suggest that impetigo is highly associated with scabies in Fiji and other Pacific Island countries.",FALSE,TRUE,"(189, 193, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"First, the population attributable risk of impetigo to scabies has ranged from 41 to 93% in studies in Fiji and the Solomon Islands [8,30].",FALSE,TRUE,"(103, 107, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"A strength of our study is that we analyzed PHC data obtained from a trial that was conducted among the entire population of the Northern Division of Fiji, including children and the elderly.",FALSE,TRUE,"(150, 154, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"We only had data to calculate the odds ratio of impetigo in other divisions of Fiji compared to the Northern Division, so we used impetigo as a proxy for all potentially scabies-related SSTIs.",FALSE,TRUE,"(79, 83, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,Our approach also assumes that healthcare utilization patterns in other divisions of Fiji were consistent with those observed in the Northern Division.,FALSE,TRUE,"(85, 89, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11466383,"Our findings are likely to be relevant to other countries in the Pacific, where the burden of scabies and the costs of treatment may be similar to that of Fiji.",FALSE,TRUE,"(155, 159, 'Fiji', 'Fiji')","Cell biology, Imaging"
PMC11385718,The strains (PGRG2 and PGRG5) were initially mapped to the reference genomes using Burrows-Wheeler aligner “mem” algorithm (BWA-mem) v.0.7.17 (5) and converted and sorted into BAM file using SAMtools v.0.1.18 (6).,FALSE,FALSE,"(191, 199, 'SAMtools', 'samtools')","Mapping, Sequence analysis, Sequencing, Rare diseases"
PMC11385718,A gapped consensus sequence was produced using SAMtools v.0.1.18 and BEDTools (7).,FALSE,FALSE,"(47, 55, 'SAMtools', 'samtools')","Mapping, Sequence analysis, Sequencing, Rare diseases"
PMC11385718,The coverage of consensus sequence was determined using SAMtools coverage with an overall coverage of 94.29% (PGRG2) and 95.93% (PGRG5).,FALSE,FALSE,"(56, 64, 'SAMtools', 'samtools')","Mapping, Sequence analysis, Sequencing, Rare diseases"
PMC11385718,"For the variant calling, SAMtools was used to identify the SNPs and InDels from the sorted BAM file of the mapping.",FALSE,FALSE,"(25, 33, 'SAMtools', 'samtools')","Mapping, Sequence analysis, Sequencing, Rare diseases"
PMC10868310,"This work presents vcfpp, a C++ API of HTSlib in a single file, providing an intuitive interface to manipulate VCF/BCF files rapidly and safely, in addition to being portable.",FALSE,FALSE,"(39, 45, 'HTSlib', 'htslib')",Data management
PMC10868310,The C API of HTSlib (Bonfield et al.,FALSE,FALSE,"(13, 19, 'HTSlib', 'htslib')",Data management
PMC10868310,"The motivation behind vcfpp is to offer full functionalities as HTSlib, and provide a simple and safe API in a single header file, which can be easily integrated for programming in C++ as well as other languages that can call C/C++ codes, such as R (https://www.r-project.org/) and Python (https://www.python.org/).",FALSE,FALSE,"(64, 70, 'HTSlib', 'htslib')",Data management
PMC10868310,2009) but were later separated into HTSlib (Bonfield et al.,FALSE,FALSE,"(36, 42, 'HTSlib', 'htslib')",Data management
PMC10868310,"Therefore, it would be more advantageous to use a specialized library, namely HTSlib, to process the VCF rather than a customized parser.",FALSE,FALSE,"(78, 84, 'HTSlib', 'htslib')",Data management
PMC10868310,"HTSlib offers full functionalities to interact with the VCF, including support for BCF, format validation, compression, random access, identification of variant types, and support for URL links as filenames, among others.",FALSE,FALSE,"(0, 6, 'HTSlib', 'htslib')",Data management
PMC10868310,"Furthermore, HTSlib has demonstrated the best performance among many competitors (Bonfield et al.",FALSE,FALSE,"(13, 19, 'HTSlib', 'htslib')",Data management
PMC10868310,"However, HTSlib was written in C language, which can be challenging for beginner programmers to use, especially when it comes to memory management.",FALSE,FALSE,"(9, 15, 'HTSlib', 'htslib')",Data management
PMC10868310,"As a C++ API of HTSlib, vcfpp inherits all functionalities from HTSlib and is implemented in a single header file that can be easily integrated and used safely.",FALSE,FALSE,"(16, 22, 'HTSlib', 'htslib')",Data management
PMC10868310,"Importantly, vcfpp and vcfppR offer users the full functionalities of HTSlib, including support for compressed VCF/BCF, selection of samples, regions, and variant types.",FALSE,FALSE,"(70, 76, 'HTSlib', 'htslib')",Data management
PMC11512631,"Initially, PCLS were fixed in formalin for 3 days at room temperature, then paraffin-embedded and sectioned into 7 μm slices for hematoxylin and eosin (H&E) and Sirius red staining with standard protocols.3233 However, we found that PCLS from cirrhotic livers were fragile and easily degraded during sectioning and Sirius red staining (Supplemental Figure S3A, left panel, http://links.lww.com/HC9/B65).",FALSE,FALSE,"(161, 167, 'Sirius', 'sirius')","Proteomics, Proteomics experiment, Metabolomics"
PMC11512631,"The amount of collagen in Sirius red–stained sections was scored according to the modified Ishak method34 as described in Supplemental Table S1, http://links.lww.com/HC9/B65.",FALSE,FALSE,"(26, 32, 'Sirius', 'sirius')","Proteomics, Proteomics experiment, Metabolomics"
PMC11512631,"CDAHFD-induced cirrhosis32 was confirmed with Sirius red staining (Supplemental Figure S4A, http://links.lww.com/HC9/B65).",FALSE,FALSE,"(46, 52, 'Sirius', 'sirius')","Proteomics, Proteomics experiment, Metabolomics"
PMC11512631,"This short-term exposure of PCLS slices to erlotinib did not significantly reduce the amount of collagen measured with Sirius red staining (Figures 2C, D).",FALSE,FALSE,"(119, 125, 'Sirius', 'sirius')","Proteomics, Proteomics experiment, Metabolomics"
PMC11512631,Amount of collagen (C) measured with Sirius red staining and (D) quantified with collagen proportionate area analysis in PCLS from CDAHFD-induced mouse cirrhosis after 5 μM erlotinib treatment for 72 hours.,FALSE,FALSE,"(37, 43, 'Sirius', 'sirius')","Proteomics, Proteomics experiment, Metabolomics"
PMC11512631,Amount of collagen (G) measured with Sirius red staining and (H) quantified in PCLS from TAA-induced rat cirrhosis after 5 μM erlotinib treatment for 72 hours.,FALSE,FALSE,"(37, 43, 'Sirius', 'sirius')","Proteomics, Proteomics experiment, Metabolomics"
PMC11512631,The images of Sirius red staining for both CDAHFD and TAA models were presented at ×20 magnification.,FALSE,FALSE,"(14, 20, 'Sirius', 'sirius')","Proteomics, Proteomics experiment, Metabolomics"
PMC11512631,"Cirrhosis was induced by TAA38 and confirmed with Sirius staining (Supplemental Figure S5A, http://links.lww.com/HC9/B65).",FALSE,FALSE,"(50, 56, 'Sirius', 'sirius')","Proteomics, Proteomics experiment, Metabolomics"
PMC11512631,"DEN-induced cirrhosis2339404142 was confirmed with Sirius staining (Supplemental Figure S6A, http://links.lww.com/HC9/B65).",FALSE,FALSE,"(51, 57, 'Sirius', 'sirius')","Proteomics, Proteomics experiment, Metabolomics"
PMC11512631,Amount of collagen (B) measured with Sirius red staining and (C) quantified with collagen proportionate area analysis in PCLS after 5 μM erlotinib treatment for 72 hours.,FALSE,FALSE,"(37, 43, 'Sirius', 'sirius')","Proteomics, Proteomics experiment, Metabolomics"
PMC11512631,Amount of collagen (E) measured with Sirius red staining and (F) quantified after daily i.p.,FALSE,FALSE,"(37, 43, 'Sirius', 'sirius')","Proteomics, Proteomics experiment, Metabolomics"
PMC11512631,"CCl4-induced cirrhosis23 was confirmed with Sirius red staining (Supplemental Figure S7A, http://links.lww.com/HC9/B65).",FALSE,FALSE,"(44, 50, 'Sirius', 'sirius')","Proteomics, Proteomics experiment, Metabolomics"
PMC11512631,(E) Amount of collagen measured with Sirius red staining and quantified with collagen proportionate area analysis in PCLS from normal rats.,FALSE,FALSE,"(37, 43, 'Sirius', 'sirius')","Proteomics, Proteomics experiment, Metabolomics"
PMC11512631,Amount of collagen (B) measured with Sirius red staining and (C) quantified in PCLS from human cirrhosis treated with 5 μM erlotinib for 72 hours.,FALSE,FALSE,"(37, 43, 'Sirius', 'sirius')","Proteomics, Proteomics experiment, Metabolomics"
PMC10765786,"Here, we describe cytoviewer, an R/Bioconductor package for interactive visualization and exploration of multi-channel images and segmentation masks.",FALSE,FALSE,"(18, 28, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"The cytoviewer package supports flexible generation of image composites, allows side-by-side visualization of single channels, and facilitates the spatial visualization of single-cell data in the form of segmentation masks.",FALSE,FALSE,"(4, 14, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"As such, cytoviewer improves image and segmentation quality control, the visualization of cell phenotyping results and qualitative validation of hypothesis at any step of data analysis.",FALSE,FALSE,"(9, 19, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,We showcase the functionality and biological application of cytoviewer by analysis of an imaging mass cytometry dataset acquired from cancer samples.,FALSE,FALSE,"(60, 70, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,The cytoviewer package offers a rich set of features for highly multiplexed imaging data visualization in R that seamlessly integrates with the workflow for image and single-cell data analysis.,FALSE,FALSE,"(4, 14, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,It can be installed from Bioconductor via https://www.bioconductor.org/packages/release/bioc/html/cytoviewer.html.,FALSE,FALSE,"(98, 108, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,The development version and further instructions can be found on GitHub at https://github.com/BodenmillerGroup/cytoviewer.,FALSE,FALSE,"(111, 121, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"Here, we present cytoviewer, an R/Bioconductor package for interactive multi-channel image and segmentation mask visualization in R.",FALSE,FALSE,"(17, 27, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,The cytoviewer package builds on the cytomapper R/Bioconductor package [17] and extends its static visualization abilities via an interactive and user-friendly shiny application.,FALSE,FALSE,"(4, 14, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"The cytoviewer package integrates into the Bioconductor framework [19] for single-cell and image analysis leveraging the image handling and analysis strategies from the EBImage Bioconductor package [20] and building on commonly used Bioconductor classes such as SingleCellExperiment, SpatialExperiment [21, 22], and CytoImageList [17].",FALSE,FALSE,"(4, 14, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,We showcase the functionality and biological application of cytoviewer by demonstrating visual exploration of an IMC dataset of cancer patients.,FALSE,FALSE,"(60, 70, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"The R/Bioconductor cytoviewer package leverages the reactive programming framework of the popular R shiny and shinydashboard packages [23], is cross-platform compatible, and launches an interactive web application.",FALSE,FALSE,"(19, 29, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,The graphical user interface (GUI) of the cytoviewer package can be opened directly from R and the function call takes up to five arguments (Fig.,FALSE,FALSE,"(42, 52, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"The full functionality of cytoviewer is leveraged when images, segmentation masks, and a metadata object are provided (Fig.",FALSE,FALSE,"(26, 36, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,1cytoviewer interface and functionality.,FALSE,FALSE,"(1, 11, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,(A) The supported functionality (right) of cytoviewer depends on the data inputs (left).,FALSE,FALSE,"(43, 53, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"(B) The graphical user interface of cytoviewer is divided into a body, header, and sidebar.",FALSE,FALSE,"(36, 46, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"The body of cytoviewer includes the image viewer, which has three tabs: Composite (Image-level), Channels (Image-level), and Mask (Cell-level).",FALSE,FALSE,"(12, 22, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,Scale bar: 150 µm (C) cytoviewer supports different viewing modes.,FALSE,FALSE,"(22, 32, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,cytoviewer interface and functionality.,FALSE,FALSE,"(0, 10, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"The cytoviewer GUI has three main parts: body, sidebar, and header (Fig.",FALSE,FALSE,"(4, 14, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,The body of cytoviewer features the image viewer.,FALSE,FALSE,"(12, 22, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"To demonstrate the functionality and potential biological applications of the cytoviewer package, we explored an example IMC dataset from the Integrated iMMUnoprofiling of large adaptive CANcer patient cohort project (immucan.eu) (Additional file 5: Supplementary Notes—S1.4).",FALSE,FALSE,"(78, 88, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"Here, we showcase the different viewing modes of cytoviewer by analyses of images from a breast cancer patient (Patient2_003) and outline the rich biological information content for each step (Fig.",FALSE,FALSE,"(49, 59, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"The R/Bioconductor cytoviewer package provides a rich set of visualization features including (1) visualization of composite and single-channel images, (2) outlining of cells on images, (3) setting cell outline colors based on cellular metadata (e.g., cell phenotype), (4) coloring segmentation masks based on cellular metadata (e.g., cell area) and (5) easy access and download of generated plots for publication, among others.",FALSE,FALSE,"(19, 29, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"The cytoviewer package operates on standard data containers of the Bioconductor project [19] such as SingleCellExperiment/SpatialExperiment [21, 22] and CytoImageList [17] and can thus be readily implemented into existing R pipelines for image and single-cell analysis.",FALSE,FALSE,"(4, 14, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,The versatile and easy-to-use graphical user interface of cytoviewer further allows accessibility to users with little bioinformatics training and coding experience.,FALSE,FALSE,"(58, 68, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"Here, we demonstrated the use of cytoviewer by exploring IMC data (Additional file 1, 2).",FALSE,FALSE,"(33, 43, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"However, data from other multiplexed imaging technologies including t-CyCIF [6], CODEX [7], or MIBI [8], which produce pixel-level intensities and (optionally) segmentation masks, can be interactively visualized with cytoviewer as long as the input format is appropriate.",FALSE,FALSE,"(217, 227, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,We have integrated cytoviewer into our widely adopted data analysis pipeline for multiplexed imaging data [10] (https://bodenmillergroup.github.io/IMCDataAnalysis/) and envision that the package will meet the needs of the fast-growing community of highly multiplexed imaging users [11].,FALSE,FALSE,"(19, 29, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,"The newly developed R/Bioconductor cytoviewer package, written in the statistical programming language R, allows interactive visualization and exploration of multi-channel images and segmentation masks.",FALSE,FALSE,"(35, 45, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,Project name: cytoviewerProject home page: https://github.com/BodenmillerGroup/cytoviewerOperating system(s): Platform independentProgramming language: ROther requirements: R > = 4.0License: NoneAny restrictions to use by non-academics: None,FALSE,FALSE,"(15, 25, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,Project name: cytoviewer,FALSE,FALSE,"(14, 24, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,Project home page: https://github.com/BodenmillerGroup/cytoviewer,FALSE,FALSE,"(55, 65, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,A video demonstrating the functionality of cytoviewer.Additional file 3: Fig.,FALSE,FALSE,"(43, 53, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,cytoviewer graphical user interface overview.,FALSE,FALSE,"(0, 10, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,The graphical user interface of cytoviewer for the three different viewer modes.,FALSE,FALSE,"(32, 42, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,cytoviewer image filters.,FALSE,FALSE,"(0, 10, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC10765786,A video demonstrating the functionality of cytoviewer.,FALSE,FALSE,"(43, 53, 'cytoviewer', 'cytoviewer')","Cytometry, Imaging, Oncology, Genotype and phenotype, Software engineering"
PMC11202377,Two of the most popular ones are RepeatModeler [9] and REPET [8].,FALSE,FALSE,"(55, 60, 'REPET', 'repet')","Sequence composition, complexity and repeats, DNA, Nucleic acid structure analysis"
PMC11202377,"For each of the species we compared the results of pantera to those of a reference library and those obtained with a denovo method, RepeatModeler for Drosophila melanogaster and Danio rerio and REPET for Oryza sativa.Fig.",FALSE,FALSE,"(194, 199, 'REPET', 'repet')","Sequence composition, complexity and repeats, DNA, Nucleic acid structure analysis"
PMC11202377,"In this case we compared the results of pantera to the uncurated library obtained with REPET [8, 34, 35] downloaded directly from REPETDB [1] composed of 2,479 families.",FALSE,FALSE,"(87, 92, 'REPET', 'repet')","Sequence composition, complexity and repeats, DNA, Nucleic acid structure analysis"
PMC11202377,Pantera found more near-full length (> 90%) members of the reference libraries than RepeatModeler (fruit fly and zebrafish) or REPET (rice) except for LTR elements for rice and zebrafish.,FALSE,FALSE,"(127, 132, 'REPET', 'repet')","Sequence composition, complexity and repeats, DNA, Nucleic acid structure analysis"
PMC11202377,"As an example, of 48 CMC-EnSpm families identified by pantera, only 5 lack the expected TIR elements, compared to 29 families missing the TIR element out of 70 in the REPET results.",FALSE,FALSE,"(167, 172, 'REPET', 'repet')","Sequence composition, complexity and repeats, DNA, Nucleic acid structure analysis"
PMC11202377,"pantera (N = 525), rice6.9.5 (N = 2431), REPET (N = 2471) c Danio rerio.",FALSE,FALSE,"(41, 46, 'REPET', 'repet')","Sequence composition, complexity and repeats, DNA, Nucleic acid structure analysis"
PMC11202377,8) except for the REPET library for rice for which we used a library previously generated.,FALSE,FALSE,"(18, 23, 'REPET', 'repet')","Sequence composition, complexity and repeats, DNA, Nucleic acid structure analysis"
PMC11202377,"Because pantera tends to generate full length consensus sequences more frequently than tools that start from a repeat-first approach, we suggest that it might be used first, then the genome be masked for sequences found by pantera, then a method such as RepeatModeler or REPET be used on the masked genome.",FALSE,FALSE,"(271, 276, 'REPET', 'repet')","Sequence composition, complexity and repeats, DNA, Nucleic acid structure analysis"
PMC11202377,"The authors want to acknowledge the support of Simon Orozco (Institut de Biologia Evolutiva—CSIC UPF) for his feedback on TE library benchmarking methods, Johann Confais (INRAE) for providing the REPET library for Oryza sativa and Jessica Storer (Dfam—University of Connecticut) for her insights on TE curation.",FALSE,FALSE,"(196, 201, 'REPET', 'repet')","Sequence composition, complexity and repeats, DNA, Nucleic acid structure analysis"
PMC10620421,PASTEClassifier19 was used to categorize different types of repetitive sequences.,FALSE,FALSE,"(0, 15, 'PASTEClassifier', 'PASTEClassifier')","Sequence composition, complexity and repeats"
PMC10620421,"(1) BWA v0.7.10-r789: aln, default parameters; (2) LACHESIS: CLUSTER_MIN_RE_SITES = 547; CLUSTER_MAX_LINK_DENSITY = 2; CLUSTER_NONINFORMATIVE_RATIO = 2; ORDER_MIN_N_RES_IN_TRUN = 1094; ORDER_MIN_N_RES_IN_SHREDS = 1076; (3) BUSCO v3.0: --evalue 1e-03 (E-value cutoff for BLAST searches), -sp human; (4) LTR_FINDER: default parameters; (5) RepeatScout: default parameters; (6) PASTEClassifier: default parameters; (7) RepeatMasker: -nolow -no_is -norna -engine wublast; (8) Genscan: default parameters; (9) Augustus v2.4: default parameters; (10) GlimmerHMM v3.0.4: default parameters; (11) GeneID v1.4: default parameters; (12) SNAP: version 2006-07-28, default parameters; (13) GeMoMa v1.3.1: default parameters; (14) Hisat v2.0.4: --max-intronlen 20000, --min-intronlen 20; (15) Stringtie v1.2.3: default parameters; (16) TransDecoder v2.0: default parameters; (17) GeneMark-ST v5.1: default parameters; (18) PASA v2.0.2: -align_tools gmap, -maxIntronLen 20000; (19) EVM v1.1.1: default parameters; (20) BLAST V2.2.31: -evalue 1e-5; (21) tRNAscan-SE: default parameters.",FALSE,FALSE,"(375, 390, 'PASTEClassifier', 'PASTEClassifier')","Sequence composition, complexity and repeats"
PMC10167986,SyntenyViewer is a public web-based tool relying on a relational database available at https://urgi.versailles.inrae.fr/synteny delivering comparative genomics data and associated reservoir of conserved genes between angiosperm species for both fundamental (evolutionary studies) and applied (translational research) applications.,FALSE,FALSE,"(0, 13, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"SyntenyViewer is made available for (i) providing comparative genomics data for seven major botanical families of flowering plants, (ii) delivering a robust catalog of 103 465 conserved genes between 44 species and inferred ancestral genomes, (iii) allowing us to investigate the evolutionary fate of ancestral genes and genomic regions in modern species through duplications, inversions, deletions, fusions, fissions and translocations, (iv) use as a tool to conduct translational research of key trait-related genes from model species to crops and (v) offering to host any comparative genomics data following simplified procedures and formats",FALSE,FALSE,"(0, 13, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,SyntenyViewer is a web resource to perform comparative genomics in plants;,FALSE,FALSE,"(0, 13, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,SyntenyViewer allows access to expertised data and to download novel analyses;,FALSE,FALSE,"(0, 13, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"SyntenyViewer provides methods, scripts, documents and procedures to generate comparative genomics data.",FALSE,FALSE,"(0, 13, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"This article presents SyntenyViewer, a web-based tool hosting expertised synteny relationships between angiosperm genomes through the reconstruction of ancestral genomes (17), and discusses potential uses of the delivered catalog of conserved genes for evolutionary studies as well translational research investigation.",FALSE,FALSE,"(22, 35, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"SyntenyViewer is a tool relying on a relational database (DB), aiming at displaying and making publicly available the previously described comparative genomics data at https://urgi.versailles.inrae.fr/synteny.",FALSE,FALSE,"(0, 13, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,SyntenyViewer data processing and database description.,FALSE,FALSE,"(0, 13, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"(a) Illustration of theSyntenyViewer architecture including the data integration step into a PostgreSQL instance, and the data visualization based on GWT powered by Apache Tomcat and Apache HTTP server.",FALSE,FALSE,"(23, 36, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,(b) Illustration of the SyntenyViewer database model with for each box a table named with its primary key term (referenced below).,FALSE,FALSE,"(24, 37, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"Following this methodology, SyntenyViewer delivers published comparative genomics data (listed in Table 1) obtained for the two major angiosperm families with the grasses within the monocots [ancestral grass karyotype (AGK) with 12 protochromosomes and 16 560 PGs (21, 22)] and the eudicots [ancestral eudicot karyotype (AEK) with 21 chromosomes and 10 286 PGs (23)].",FALSE,FALSE,"(28, 41, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"SyntenyViewer also provides published comparative genomics data for angiosperm lineages of agronomical interest such as Rosaceae [ancestral Rosaceae karyotype (ARK) with nine protochromosomes and 8861 PGs (24, 25)], Brassicaceae [ancestral Brassicaceae karyotype (ABK) with eight protochromosomes and 20 037 PGs (26, 27)], Cucurbitaceae [ancestral Cucurbitaceae karyotype (ACuK) with 22 protochromosomes and 17 969 PGs (28, 29)], legumes [ancestral legume karyotype (ALK) with 16 protochromosomes and 13 181 PGs (30–32)] and Solanaceae [ancestral Solanaceae karyotype (ASK) with 17 protochromosomes and 17 879 PGs (33)].",FALSE,FALSE,"(0, 13, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"For example, see the Terms tab of ‘PlantSyntenyViewer Solanaceae submission file’ where the license is also prompted when a user attempts to download the associated file (Table 1).",FALSE,FALSE,"(40, 53, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"Previous synteny data are integrated into the SyntenyViewer tool relying on a DB with a Java web application for graphical dynamic web content processing, a web server (Apache HTTP and Apache Tomcat) and a PostgreSQL 9.6 instance to store the data (Figure 2).",FALSE,FALSE,"(46, 59, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"A spreadsheet-based data exchange format allows synteny data submission to SyntenyViewer, available at https://urgi.versailles.inrae.fr/Data/Synteny/Data-submission.",FALSE,FALSE,"(75, 88, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"Synteny data is then made publicly available when the format described on our website (https://urgi.versailles.inrae.fr/Data/Synteny/Data-submission), and the aims of SyntenyViewer are met.",FALSE,FALSE,"(167, 180, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,There are two main entry points to visualize SyntenyViewer data (cf Supplementary Video).,FALSE,FALSE,"(45, 58, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"At any stage, the SyntenyViewer’s Uniform Resource Locator is dynamically updated, and it can be bookmarked in the browser for sharing the visualization link, which makes users able to go back to previous work and pursue exploration.",FALSE,FALSE,"(18, 31, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"The delivered SyntenyViewer tool gives public access to validated and reviewed comparative genomics data either between angiosperm species or within major botanical families that can be used as a backbone to investigate evolutionary trends of genes, perform translational research of traits and conduct evolutionary developmental biology (for Evo-Devo) investigation of traits.",FALSE,FALSE,"(14, 27, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"SyntenyViewer allows deep investigation of evolutionary fates of ancestral genes/genomes, through precise identification of the changes involved (gains and losses of genes and associated gene ontologies) and their assignment to specific species or botanical families (Figure 3a).",FALSE,FALSE,"(0, 13, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"SyntenyViewer, a comparative genomics-driven translational research tool.",FALSE,FALSE,"(0, 13, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,(b) ‘SyntenyViewer screen capture’.,FALSE,FALSE,"(5, 18, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"SyntenyViewer tool with the setting parameters (search by gene name and ancestral or modern chromosomes) illustrated at the left and the derived comparative genomics data visualization, as detailed in the text, at the right (here for cereals).",FALSE,FALSE,"(0, 13, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,FZP gene characterization in grasses with orthologs from SyntenyViewer (Panel b) and functional validation in wheat and Brachypodium (in mutants compared to wild type) in deriving similar SS phenotypes (adapted from (47)).,FALSE,FALSE,"(57, 70, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"SyntenyViewer can also be used as a useful tool for translational research on genes driving key agronomical traits, particularly from model species (such as Arabidopsis thaliana) to crops (41).",FALSE,FALSE,"(0, 13, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"From the gene conservation information delivered from SyntenyViewer, further validation needs to be conducted to establish the conservation of the phenotype or trait between the investigated species.",FALSE,FALSE,"(54, 67, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"Beside translational research of genes, SyntenyViewer allows us to conduct ‘Evo-Devo dissection of traits’.",FALSE,FALSE,"(40, 53, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"SyntenyViewer allows us to compare a group of angiosperm species that acquired new phenotypes (or traits in the broad sense) in the course of evolution, compared to a group of species that did not acquire this trait.",FALSE,FALSE,"(0, 13, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"Overall, SyntenyViewer is a web-based tool delivering comparative genomics data either between angiosperm species or within major botanical families (including the Rosaceae, Brassicaceae, Cucurbitaceae, legume and Solanaceae) for evolutionary and translational research purposes.",FALSE,FALSE,"(9, 22, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC10167986,"The ‘Région Auvergne-Rhône-Alpes’ and ‘Fonds Européen de Développement Régional’ (#23000816 project ‘SRESRI-2015’), the Institut Carnot Plant2Pro (project ‘SyntenyViewer’), the Initiative-Science-Innovation-Territoires-Economie (ISITE) CAP2025 (#00002146 SRESRI 2015, Pack Ambition Recherche Project ‘TransBlé’), the Agence Nationale de la Recherche (ANR) projects ‘BREEDWHEAT’ (ANR-10-BTBR-03-06), the Biomass For the Future project (ANR-11-BTBR-0006), the ANR project, for Plant and Animal Genome Evolution (PAGE) (ANR-11-BSV6-0008) and the Plant Bioinformatics Facility (https://doi.org/10.15454/1.5572414581735654E12).",FALSE,FALSE,"(156, 169, 'SyntenyViewer', 'urgi')","Mapping, Plant biology, Structural variation, Paleogenomics, Protein expression, Comparative genomics"
PMC4870745,We developed a simple Web application called Phenotator for the data providers to submit and annotate their phenotypes with an EQ.,FALSE,FALSE,"(45, 55, 'Phenotator', 'phenotator')","Ontology and terminology, Data management"
PMC4870745,The Phenotator is built using services from the NCBO BioPortal [15] to generate simple drop down menus and autocomplete search functionality to guide the users in generating EQs with appropriate terms (Fig.,FALSE,FALSE,"(4, 14, 'Phenotator', 'phenotator')","Ontology and terminology, Data management"
PMC4870745,"Phenotator has a feature to export the collected EQ annotations as an OWL file containing new terms that are logically defined according to the SUBQ pattern,10 which can be expressed in Manchester OWL syntax as “(has_part some (<Quality> and inheres_in some <Entity>))”.",FALSE,FALSE,"(0, 10, 'Phenotator', 'phenotator')","Ontology and terminology, Data management"
PMC4870745,"One hundred twenty-seven phenotype descriptions from the original 11 datasets were entered into Phenotator, together with 41 phenotypes collected from cell migration assays (Z.",FALSE,FALSE,"(96, 106, 'Phenotator', 'phenotator')","Ontology and terminology, Data management"
PMC4870745,The EQs were exported from Phenotator as an OWL file and loaded into the Protege OWL ontology editor.,FALSE,FALSE,"(27, 37, 'Phenotator', 'phenotator')","Ontology and terminology, Data management"
PMC4870745,"To increase the expressivity of the annotation in Phenotator a third column was added to capture additional modifiers to the EQ resulting in annotations emerging like EQE2 (‘actin filament’, ‘localised’, ‘cytosol’).",FALSE,FALSE,"(50, 60, 'Phenotator', 'phenotator')","Ontology and terminology, Data management"
PMC4870745,Pattern-based tooling to rapidly generate new terms are emerging and these could nicely complement existing tooling that are primarily aimed at annotating phenotypes with EQs such as Phenotator and Phenote.,FALSE,FALSE,"(183, 193, 'Phenotator', 'phenotator')","Ontology and terminology, Data management"
PMC4870745,Phenotator and Phenote do little to guide the annotator to make a correct EQ annotation and the translation of these annotations to OWL typically only allows for a basic SUBQ pattern.,FALSE,FALSE,"(0, 10, 'Phenotator', 'phenotator')","Ontology and terminology, Data management"
PMC4870745,The Phenotator and Webulous software was developed by SJ and TB.,FALSE,FALSE,"(4, 14, 'Phenotator', 'phenotator')","Ontology and terminology, Data management"
PMC5753341,"We introduce the marine databases; MarRef, MarDB and MarCat (https://mmp.sfb.uit.no/databases/), which are publicly available resources that promote marine research and innovation.",FALSE,FALSE,"(53, 59, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"The last database, MarCat, represents a gene (protein) catalog of uncultivable (and cultivable) marine genes and proteins derived from marine metagenomics samples.",FALSE,FALSE,"(19, 25, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"Currently, MarCat contains 1227 records with 55 metadata fields.",FALSE,FALSE,"(11, 17, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"Here, we introduced the contextual and sequence MAR databases: MarRef, MarDB and MarCat, with manually curated metadata including attributes for sampling, sequencing, assembly and annotation in addition to the organism and taxonomic information and their corresponding nucleotide and protein sequences.",FALSE,FALSE,"(81, 87, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,Only metagenomic sequences in relation with MarCat has been processed using META-pipe for the first release.,FALSE,FALSE,"(44, 50, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"The MarRef, MarDB and MarCat sequence databases are based on the non-redundant genome and metagenome datasets obtained from ENA (European Nucleotide Archive, http://www.ebi.ac.uk/ena) and NCBI (https://www.ncbi.nlm.nih.gov/).",FALSE,FALSE,"(22, 28, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,MarCat represents a gene (protein) catalog of predicted marine genes derived from marine metagenomic samples.,FALSE,FALSE,"(0, 6, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"The MarRef, MarDB and MarCat contextual databases are built by compiling data from a number of publicly available sequence, taxonomy and literature databases in a semi-automatic fashion.",FALSE,FALSE,"(22, 28, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"The gene (protein) catalog database derived from marine metagenomic samples, MarCat, contains 1227 records, including samples from the Tara Ocean expedition (248 records) and Ocean Sampling Day (150 records).",FALSE,FALSE,"(77, 83, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"While MarRef is thoroughly curated, MarDB and MarCat are only partly curated.",FALSE,FALSE,"(46, 52, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"Records in the marine databases, MarRef, MarDB and MarCat follow the MlxS standard guidelines developed by the Genomic Standard Consortium, in addition to ontologies such as ENVO and GAZ.",FALSE,FALSE,"(51, 57, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"The MarRef, MarDB and MarCat sequence databases are based on the non-redundant genome and metagenome datasets obtained from ENA and NCBI and by manually inspection assigned as belonging to the ‘marine microbial biome’ according to our definition.",FALSE,FALSE,"(22, 28, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,MarCat represents a catalog of uncultivable (and cultivable) full-length genes (proteins) derived from marine metagenomic samples based on the Marine projects in EBI metagenomics (https://www.ebi.ac.uk/metagenomics/).,FALSE,FALSE,"(1, 7, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,Using META-pipe for gene prediction and functional assignment allowed us to generate a consistent catalog across the datasets in MarCat (See https://f1000research.com/articles/6–70/v1 for a more detailed description of functional assignment).,FALSE,FALSE,"(129, 135, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"The index of MarCat (not shown) is less comprehensive, thus have fever filtering options.",FALSE,FALSE,"(13, 19, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"For MarCat, the metagenome databases, the 55 metadata fields have been divided into four categories: isolate info, sampling info, host and pathogenicity info and assembly info, in addition to Summary.",FALSE,FALSE,"(4, 10, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"The BLAST (35) sequence databases provide similarity search against all nucleotide and protein sequences of records included in MarRef, MarDB and MarCat.",FALSE,FALSE,"(146, 152, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"For MarCat, the marine metagenomics gene catalogue, target information can be obtained from other databases such as UniProt, InterPro and Brenda.",FALSE,FALSE,"(4, 10, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"For samples in the MarCat database, all predicted 16 S sequences and assembled contigs in FASTA format can be downloaded.",FALSE,FALSE,"(19, 25, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,"In addition, we aim to include metatranscriptomics data to enhance the quality of the MarCat.",FALSE,FALSE,"(86, 92, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC5753341,For MarCat we intend to include metadata fields for the provenance of analysis according to the recommendation by Hoopen et al.,FALSE,FALSE,"(4, 10, 'MarCat', 'marcat')","Marine biology, Microbiology, Metagenomics, Data mining"
PMC10580933,We trained both models using metagenomic reads simulated from marine microbial genomes in the MarRef database.,FALSE,FALSE,"(94, 100, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"The performance of both models (accuracy, precision, and percent microbe predicted) was compared with the standard taxonomic classification tool Kraken2 using 10 complex metagenomic data sets simulated from MarRef.",FALSE,FALSE,"(207, 213, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"Taxonomic and sequence data from version 1.6 of the MarRef database (24, 25) was used both to simulate metagenomic reads for taxonomic classification and as a source of artificial marine metagenomes for model training, testing, and validation.",FALSE,FALSE,"(52, 58, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"MarRef is a manually curated marine microbial reference database containing fully sequenced genomes (24, 25).",FALSE,FALSE,"(0, 6, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"A total of 1,271 genomes of marine prokaryotic species were retrieved from MarRef to develop the training, testing, and validation data sets.",FALSE,FALSE,"(75, 81, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"For each genome, we extracted the Genome Taxonomy Database (GTDB) (26) genus and species classification from the MarRef database’s metadata file.",FALSE,FALSE,"(113, 119, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"Of the 1,271 MarRef genomes, four records had undefined GTDB taxonomy due to failed quality checks and were dropped from the data set.",FALSE,FALSE,"(13, 19, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"For performance comparison, the default parameters of CAMISIM v1.3 (28) were used to perform 10 separate read simulations from the 1,267 MarRef genomes, with random seeds different from those used in the training and testing sets.",FALSE,FALSE,"(137, 143, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,(1) Full-length genome records and their metadata were downloaded from MarRef v1.6.,FALSE,FALSE,"(71, 77, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"(4) Blind data sets were created using CAMISIM, which randomly generates metagenomic data sets from the MarRef genomes.",FALSE,FALSE,"(104, 110, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,Kraken2 v2.1.2 was used to assign taxonomy to metagenomic reads in the blind data sets using MarRef v1.6 as the reference database.,FALSE,FALSE,"(93, 99, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"Bowtie2 v2.4.5’s bowtie-build command was used to generate a reference database containing all 1,267 MarRef genomes from the training set.",FALSE,FALSE,"(101, 107, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,Our shell script can be found at https://github.com/helloftroy/MarRef_DeepMicrobes.,FALSE,FALSE,"(63, 69, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"We benchmarked the performance of our best-performing species and genus classification models (S-2E, S-3E, G-2E, G-3E; species 2 and 3 epoch, genus 2 and 3 epoch) against Kraken2 using 10 simulated blind metagenomes that contain random proportions of reads from the MarRef genomes.",FALSE,FALSE,"(266, 272, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,Our results suggest that the DeepMicrobes marine (MarRef)-trained model showed lower accuracy than the prior human gut model (0.65 vs 0.96).,FALSE,FALSE,"(50, 56, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,(e) Genomic data comparison between HGR and MarRef genomes.,FALSE,FALSE,"(44, 50, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"Notably, all genomes mispredicted for the genus models have only one representative genome in MarRef for the model to train on; many also have long genome length and high GC content.",FALSE,FALSE,"(94, 100, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"To evaluate whether performance differences between the DeepMicrobes gut and marine models was affected by the input genomes, we compared the HGR and MarRef data sets used for training.",FALSE,FALSE,"(150, 156, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,We noticed average genome size in the MarRef data set was larger than the average genome size in the HGR data set (4.1 vs 2.5 Mbp).,FALSE,FALSE,"(38, 44, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"However, the average number of genomes represented in each genus was lower than the MarRef data set compared to the HGR data set (3.1 vs 20.7) (Fig.",FALSE,FALSE,"(84, 90, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"Lastly, we observed that though the average GC content was similar between both database genomes (0.48), many MarRef genus with <0.5 MCC had high GC content (0.52–0.72).",FALSE,FALSE,"(110, 116, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,ResNet architecture results for all models using sample of MarRef genomes.,FALSE,FALSE,"(59, 65, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC10580933,"Jupyter Notebooks used to create figures and analyze datasetsdata sets, along with shell scripts to run DeepMicrobes, Bowtie2, CAMISIM, and other program code can be found at MarRef_DeepMicrobes.",FALSE,FALSE,"(175, 181, 'MarRef', 'marref')","Marine biology, Microbiology, Genomics, Data mining"
PMC11124354,"A dataset of cold-adapted bacterial genome sequences was generated based on the five databases MarRef v.1.7, MarDB v.1.6, Ocean Microbiomics Database (OMD) v.1.1, BacDive (https://bacdive.dsmz.de/ (accessed on 23 January 2023)), and TEMPURA (http://togodb.org/db/tempura (accessed on 4 April 2023)).",FALSE,FALSE,"(109, 114, 'MarDB', 'mardb')","Marine biology, Microbiology, Genomics, Data mining"
PMC11124354,"Filtering from MarDB, MarRef, and OMD databases was primarily focused on isolation location.",FALSE,FALSE,"(15, 20, 'MarDB', 'mardb')","Marine biology, Microbiology, Genomics, Data mining"
PMC11124354,"All genomes from MarRef and MarDB bacteria classified as mesophilic, thermotolerant, and thermophilic were excluded, as well as those bacteria isolated from homoiotherms and hydrothermal vents.",FALSE,FALSE,"(28, 33, 'MarDB', 'mardb')","Marine biology, Microbiology, Genomics, Data mining"
PMC11124354,"All remaining genomes, including the metagenome-assembled genomes (MAGs) from MarDB and OMD databases, were quality assessed using CheckM (v1.2.2) [41].",FALSE,FALSE,"(78, 83, 'MarDB', 'mardb')","Marine biology, Microbiology, Genomics, Data mining"
PMC11124354,"The genomes of interest from MarRef (N = 86), MarDB (N = 225), OMD (N = 299), BacDive (N = 305), and TEMPURA (N = 25) were downloaded from the respective databases using their provided application programming interfaces (APIs) or download portals.",FALSE,FALSE,"(46, 51, 'MarDB', 'mardb')","Marine biology, Microbiology, Genomics, Data mining"
PMC11124354,"To map antiphage defense systems in cold-adapted bacteria, we generated a dataset of assembled genomes of bacteria that were considered cold-adapted either based on isolation location (MarRef, MarDB, and OMD databases) or experimental temperature growth data (BacDive and TEMPURA databases).",FALSE,FALSE,"(193, 198, 'MarDB', 'mardb')","Marine biology, Microbiology, Genomics, Data mining"
PMC4847265,"Here, we present a different approach, relying on tightly integrated method rather than “Wiki-based” method, to support community annotation and user collaboration in the Integrated Microbial Genomes (IMG) system.",FALSE,FALSE,"(171, 205, 'Integrated Microbial Genomes (IMG)', 'img')","Virology, Microbial ecology, Genomics, Metagenomics, Comparative genomics"
PMC4718670,"Here we present an automated tool, called iMet-Q (intelligent Metabolomic Quantitation), for label-free metabolomics quantitation from high-throughput MS1 data.",FALSE,FALSE,"(42, 48, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"By performing peak detection and peak alignment, iMet-Q provides a summary of quantitation results and reports ion abundance at both replicate level and sample level.",FALSE,FALSE,"(49, 55, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,An in-house standard mixture and a public Arabidopsis metabolome data set were analyzed by iMet-Q.,FALSE,FALSE,"(91, 97, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"From the mixture data set, seven standard metabolites were detected by the four quantitation tools, for which iMet-Q had a smaller quantitation error of 12% in both profile and centroid data sets.",FALSE,FALSE,"(110, 116, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"With the isotope ratios calculated by iMet-Q, 49% (89 out of 183) metabolite candidates were filtered out.",FALSE,FALSE,"(38, 44, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"From the public Arabidopsis data set reported with two internal standards and 167 elucidated metabolites, iMet-Q detected all of the peaks corresponding to the internal standards and 167 metabolites.",FALSE,FALSE,"(106, 112, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,iMet-Q provides user-friendly interfaces and is publicly available for download at http://ms.iis.sinica.edu.tw/comics/Software_iMet-Q.html.,FALSE,FALSE,"(0, 6, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"To rectify the above concerns, we develop a quantitation tool, called iMet-Q (intelligent Metabolomic Quantitation), written in C# programming language, which provides highly accurate quantitation and user-friendly graphical interfaces.",FALSE,FALSE,"(70, 76, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"For peak detection, iMet-Q requires one input parameter, i.e., mzWidth (defined as the width of a peak in m/z dimension), and calculates the full width at half maximum (FWHM) of a peak to dynamically determine its chromatographic width so that the peak boundary can be automatically determined (i.e., without requiring parameter input).",FALSE,FALSE,"(20, 26, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Once the charge state is determined, iMet-Q calculates its isotope ratio (i.e., the ratio of the second isotope abundance to the monoisotope abundance) to facilitate metabolite identification.",FALSE,FALSE,"(37, 43, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Since metabolites usually have smaller retention time drifts across LC-MS technical replicates, iMet-Q first aligns peaks across different LC-MS replicates of a sample and then across different samples.",FALSE,FALSE,"(96, 102, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"We used two metabolite data sets, an in-house standard mixture and a public Arabidopsis metabolome data set [28], to evaluate the performance of iMet-Q and compare it with three public quantitation tools, including XCMS, MetAlign, and MZmine2.",FALSE,FALSE,"(145, 151, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"As a result, iMet-Q had small quantitation error of 12% in both profile and centroid data sets.",FALSE,FALSE,"(13, 19, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"For the public Arabidopsis metabolome data set reported with two internal standards and 167 elucidated metabolites, iMet-Q detected the internal standards from all replicates and samples.",FALSE,FALSE,"(116, 122, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"In addition, all of the 167 metabolites were also detected by iMet-Q, whereas 103 (62%), 145 (87%), and 129 (77%) elucidated metabolites were detected by XCMS, MetAlign, and MZmine 2, respectively.",FALSE,FALSE,"(62, 68, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Comparing with the three quantitation tools, iMet-Q had relatively small abundance variations (≤0.19) when quantifying the internal standards, and had higher abundance correlation (≥0.92) when quantifying the 167 metabolites across replicates.",FALSE,FALSE,"(45, 51, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,The source code of iMet-Q is freely available on SourceForge (http://sourceforge.net/projects/imet-q/?source=navbar) under the license of GPL2.,FALSE,FALSE,"(19, 25, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"iMet-Q automatically skipped centroiding step when processing the centroid data set and used the following parameter setting: mzWidth = 0.02, mzTol = 0.02, and rtTol = 0.2 for both data sets.",FALSE,FALSE,"(0, 6, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Public Arabidopsis data set was processed by iMet-Q with mzWidth, mzTol, and rtTol of 0.03, 0.03, and 0.16 min, respectively.",FALSE,FALSE,"(45, 51, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"In order to process data from various mass spectrometers, iMet-Q accepts input files in netCDF, mzXML, and mzML formats, which can be conveniently converted from raw data by existing converters.",FALSE,FALSE,"(58, 64, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"The workflow of iMet-Q contains two main tasks, peak detection and peak alignment, as depicted in Fig 1.",FALSE,FALSE,"(16, 22, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"To compare compounds across different samples, iMet-Q aligns the detected peaks in the peak lists according to their m/z and retention time.",FALSE,FALSE,"(47, 53, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"If the input files have already been centroided, iMet-Q automatically skips this step.",FALSE,FALSE,"(49, 55, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Instead of determining a fixed baseline for each spectrum, iMet-Q equally divides a scan into s segments (s = 10 by default) with an overlap of 20% to avoid borderline issues and defines the average intensity in a segment as its noise level.",FALSE,FALSE,"(59, 65, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"After processing signals in each scan, iMet-Q uses a two-stage algorithm to construct the extracted ion chromatogram (EIC) of a compound.",FALSE,FALSE,"(39, 45, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"In signal clustering, starting from the most intensive signal, say sij, among all scans in S, iMet-Q clusters signals in S with sij if the m/z differences between the signals and sij are within the given tolerance d, i.e., mzWidth in iMet-Q.",FALSE,FALSE,"(94, 100, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"In the step of EIC boundary determination, iMet-Q automatically calculates FWHM and then dynamically determines the boundaries using FWHM.",FALSE,FALSE,"(43, 49, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"In order to determine the charge state and isotope ratio, iMet-Q first constructs an isotope envelope for a peak.",FALSE,FALSE,"(58, 64, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Then, to validate the correctness of the isotope envelope, iMet-Q calculates the peak shape similarity between the monoisotope peak and the second isotope peak by using the dot product as shown below: Similarity=∑i=1nxiyi∑i=1nxi2∑i=1nyi2(1) where n is the number of scans that both the monoisotope peak and the second isotope peak co-occur, and xi and yi are their respective signal intensities in the ith scan.",FALSE,FALSE,"(59, 65, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"By performing the above peak detection procedures, iMet-Q generates a peak list with charge state and isotope ratio information for each input replicate file.",FALSE,FALSE,"(51, 57, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"For an input data set with multiple samples (each probably with multiple technical replicates), iMet-Q performs the same algorithm for pair-wise alignment within a sample (i.e., aligning replicates) and then across samples.",FALSE,FALSE,"(96, 102, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,iMet-Q first selects the peak list that contains the largest number of detected peaks as the reference list and aligns other peak lists to it.,FALSE,FALSE,"(0, 6, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"For a pair of reference list and aligning peak list, iMet-Q uses peaks detected in both lists with their m/z and retention time differences within user-defined tolerances (i.e., mzTol and rtTol in iMet-Q) as landmarks [34].",FALSE,FALSE,"(53, 59, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Given the retention time of landmarks in the reference list and in the aligning peak list as vectors A and B, respectively, iMet-Q uses LOESS regression [26, 27] to generate a mapping between A and B with span of 20% and weight of 1 since LOESS regression combines multiple linear least square regression models which fit localized subsets of the data.",FALSE,FALSE,"(124, 130, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,iMet-Q then aligns the peaks in both peak lists that satisfy user-defined m/z tolerance and retention time tolerance based on adjusted retention time.,FALSE,FALSE,"(0, 6, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"In addition to viewing quantitation results in the main interface, iMet-Q reports the medians of m/z, retention time and abundance of the peaks in all replicates of all samples.",FALSE,FALSE,"(67, 73, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"For the charge state of an aligned peak, iMet-Q displays the charge state that is detected in most replicates.",FALSE,FALSE,"(41, 47, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"For the isotope ratio, iMet-Q collects the isotope ratios corresponding to the displayed charge state and reports the median as the isotope ratio.",FALSE,FALSE,"(23, 29, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"We evaluated the performance of iMet-Q in metabolite quantitation by comparing the accuracy of detecting metabolites and the abundance consistency, calculated by Pearson product-moment correlation coefficient (PPMCC), of detected metabolites among replicates with XCMS, MetAlign, and MZmine 2 using samples ranging from a small standard data set (seven standard metabolites) to a complex biological data set (public Arabidopsis data set).",FALSE,FALSE,"(32, 38, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,We also demonstrated the ability of iMet-Q on charge state determination and isotope ratio calculation.,FALSE,FALSE,"(36, 42, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"To demonstrate the ability of iMet-Q, we used a standard metabolite mixture in which seven standard metabolites with different sample concentration in two samples were included for evaluation.",FALSE,FALSE,"(30, 36, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Both profile and centroid data sets generated from the raw data were processed by iMet-Q, XCMS, MetAlign, and MZmine 2, respectively.",FALSE,FALSE,"(82, 88, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"As shown in Table 1, iMet-Q, XCMS, and MZmine 2 had the average quantitation error of 12%, 12% and 13% on the profile data set, and 12%, 32% and 14% on the centroid data set.",FALSE,FALSE,"(21, 27, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"The results showed that iMet-Q achieved the smallest quantitation errors and also had the same average quantitation error of 12% in both profile and centroid data set, suggesting the robustness of iMet-Q on processing input files in both data type.",FALSE,FALSE,"(24, 30, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"In addition to accurate quantitation, iMet-Q determined the charge state and isotope ratio of detected peaks.",FALSE,FALSE,"(38, 44, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"In order to evaluate the charge state determined by iMet-Q, we used CAMERA to annotate charge states and isotope peaks of the standard metabolites.",FALSE,FALSE,"(52, 58, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,Charge states and isotope peaks of the seven standard metabolites in both profile and centroid data sets annotated by iMet-Q were overall identical with CAMERA’s annotation.,FALSE,FALSE,"(118, 124, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Using iMet-Q’s calculated isotope ratios (the isotope ratio tolerance is ±0.02) to filter out unnecessary metabolite candidates, we reduced 49% (89 out of 183) metabolite candidates (S6 Table).",FALSE,FALSE,"(6, 12, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,The public Arabidopsis data of 36 distinct samples collected from eight different plant classes (classified by Matsuda et al.) was used to demonstrate iMet-Q’s performance on quantifying complex biological samples.,FALSE,FALSE,"(151, 157, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Table 2 shows the reproducibility and normalized abundances of two internal standards detected by the four quantitation tools, where iMet-Q, XCMS, and MetAlign detected all the internal standards from each replicate, achieving 100% reproducibility, slightly better than MZmine 2.",FALSE,FALSE,"(133, 139, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Furthermore, iMet-Q reported normalized abundances of 1±0.19 and 1±0.18 for the two standard metabolites, comparable to the best 1±0.18 reported by XCMS and MZmine 2 for Lidocaine and the best 1±0.17 reported by XCMS for Camphor-10-sulfonic acid.",FALSE,FALSE,"(13, 19, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"As a result, iMet-Q detected all of the elucidated metabolites, whereas XCMS, MetAlign, and MZmine 2 detected 103 (62%), 145 (87%), and 129 (77%) of the elucidated metabolites, respectively.",FALSE,FALSE,"(13, 19, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"As a result, iMet-Q achieved an average replicate abundance correlation of 0.92, whereas XCMS, MetAlign, and MZmine 2 achieved average abundance correlations of 0.87, 0.78, and 0.81, respectively (as shown in Fig 3).",FALSE,FALSE,"(13, 19, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,The result revealed that iMet-Q not only achieved high accuracy on detecting the 167 elucidated metabolites but also provided very consistent quantitation result.,FALSE,FALSE,"(25, 31, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"The numbers of detected peaks in the combined quantitation results of iMet-Q, XCMS, MetAlign, and MZmine 2 were 13079, 7487, 37364, and 19394, respectively.",FALSE,FALSE,"(70, 76, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"The average abundance correlations of the eight plant classes using the combined quantitation results of iMet-Q, XCMS, MetAlign, and MZmine 2 were 0.71, 0.75, 0.65, and 0.59, respectively.",FALSE,FALSE,"(105, 111, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Note that all the replicates of flower class, the best clustered plant class (blue color in Fig 4), were clustered using iMet-Q’s combined quantitation result, and the average abundance correlation of the flower class was 0.88.",FALSE,FALSE,"(121, 127, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"This evaluation implies that, although the numbers of peaks detected by MetAlign and MZmine 2 were much larger than those detected by iMet-Q and XCMS, peaks detected by iMet-Q and XCMS might be more essential for distinguishing plant classes.",FALSE,FALSE,"(134, 140, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,We thus used the 19 confirmed metabolites to demonstrate the ability of iMet-Q.,FALSE,FALSE,"(72, 78, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"By calculating the abundance correlations between 19 metabolites and their in-source fragments, iMet-Q reported an abundance correlation of 0.94, whereas XCMS, MetAlign, and MZmine 2 reported abundance correlations of 0.61, 0.76, and 0.66, respectively (as shown in Fig 5).",FALSE,FALSE,"(96, 102, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,This result revealed that the abundances of the 19 metabolites and their in-source fragments were accurately detected and calculated by iMet-Q.,FALSE,FALSE,"(136, 142, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Furthermore, isotope ratios of 89.47% (17 out of 19) metabolites were accurately calculated by iMet-Q, with differences within 0.05 to the theoretical ratio (S12 Table).",FALSE,FALSE,"(95, 101, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"We particularly implemented iMet-Q as a project-oriented quantitation platform, allowing users to conveniently quantify, manage and compare a large number of data sets or quantitation results in Microsoft Windows series platform (including Windows 7, 8, and Windows Server 2008, 2012).",FALSE,FALSE,"(28, 34, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"To be specific, iMet-Q applies a tree structure to organize quantitation results, where each node represents a project and sub-nodes of a project represent the quantitation results (as shown in Fig 6).",FALSE,FALSE,"(16, 22, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,iMet-Q provides three wizards to guide users easily executing the program as follows.,FALSE,FALSE,"(0, 6, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Since multiple technical replicates may be conducted on a sample, iMet-Q pops up a table to guide users to group technical replicates by the sample.",FALSE,FALSE,"(66, 72, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"During quantitation, iMet-Q sequentially detects peaks from each replicate and then aligns those detected peaks across replicates/samples.",FALSE,FALSE,"(21, 27, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"To compare abundances across samples, iMet-Q hierarchically displays a quantitation result in the main interface, where the quantitation result is summarized in a summary table.",FALSE,FALSE,"(38, 44, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"In order to efficiently select peaks of interest in the summary table, iMet-Q provides a search function using the range of m/z, retention time, charge state, or isotope ratio to narrow down the peaks listed in the summary table.",FALSE,FALSE,"(71, 77, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Therefore, in this paper, we introduced an intelligent quantitation tool, iMet-Q, which is capable of dynamically determining the peak widths in liquid chromatogram dimension without input parameter, and automatically performing isotope pattern assembly.",FALSE,FALSE,"(74, 80, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"In our evaluation, iMet-Q has the quantitation performance better than XCMS, MetAlign, and MZmine 2 on standard and large-scale metabolome data sets.",FALSE,FALSE,"(19, 25, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Besides, iMet-Q provides both the charge states and isotope ratios of detected peaks.",FALSE,FALSE,"(9, 15, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"Although our evaluation demonstrates that the metabolite isotope ratios calculated by iMet-Q are close to the theoretical values, it is important to note that isotope ratio can be affected by noise interference, saturation effects and different experimental conditions [36, 37].",FALSE,FALSE,"(86, 92, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,"In addition to providing accurate quantitation, charge state, and isotope ratios, iMet-Q is equipped with friendly user interfaces so that quantifying metabolites become an easy task.",FALSE,FALSE,"(82, 88, 'iMet-Q', 'imet-q')",Metabolomics
PMC4718670,The software program is now publicly available for download at http://ms.iis.sinica.edu.tw/comics/Software_iMet-Q.html.,FALSE,FALSE,"(107, 113, 'iMet-Q', 'imet-q')",Metabolomics
PMC8205298,We provide an R script for post-processing MSI data in the imzML community format (https://bitbucket.org/lababi/msi.r) and implemented the TrIQ in our open-source imaging software RmsiGUI (https://bitbucket.org/lababi/rmsigui/).,FALSE,FALSE,"(180, 187, 'RmsiGUI', 'rmsigui')","Proteomics experiment, Metabolomics, Imaging, Small molecules"
PMC8205298,"Default values for \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym}  \usepackage{amsfonts}  \usepackage{amssymb}  \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}k\end{document}k and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym}  \usepackage{amsfonts}  \usepackage{amssymb}  \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}q\end{document}q in RmsiGUI are 100 and 98%, respectively.",FALSE,FALSE,"(530, 537, 'RmsiGUI', 'rmsigui')","Proteomics experiment, Metabolomics, Imaging, Small molecules"
PMC8205298,"Recently, we published an R-based platform for MSI data processing with a graphical user interface, RmsiGUI, which provides modules for the control of an open hardware imaging robot (Open LabBot), the processing of raw data, and the analysis of MSI data (Rosas-Román et al., 2020).",FALSE,FALSE,"(100, 107, 'RmsiGUI', 'rmsigui')","Proteomics experiment, Metabolomics, Imaging, Small molecules"
PMC8205298,We integrated the TrIQ algorithm into RmsiGUI and provide the R code snippets for facilitating its adoption into other programs.,FALSE,FALSE,"(38, 45, 'RmsiGUI', 'rmsigui')","Proteomics experiment, Metabolomics, Imaging, Small molecules"
PMC8205298,Figure 1 shows the graphical user interface of RmsiGUI with the TrIQ option selector.,FALSE,FALSE,"(47, 54, 'RmsiGUI', 'rmsigui')","Proteomics experiment, Metabolomics, Imaging, Small molecules"
PMC8205298,RmsiGUI is freely available from https://bitbucket.org/lababi/rmsigui/.,FALSE,FALSE,"(0, 7, 'RmsiGUI', 'rmsigui')","Proteomics experiment, Metabolomics, Imaging, Small molecules"
PMC8205298,"We released TrIQ R scripts and the R package RmsiGUI under the terms of the GNU General Public License, GPL V3 (http://gplv3.fsf.org/).",FALSE,FALSE,"(45, 52, 'RmsiGUI', 'rmsigui')","Proteomics experiment, Metabolomics, Imaging, Small molecules"
PMC8205298,The software RmsiGUI is freely available from https://bitbucket.org/lababi/rmsigui/.,FALSE,FALSE,"(13, 20, 'RmsiGUI', 'rmsigui')","Proteomics experiment, Metabolomics, Imaging, Small molecules"
PMC11305627,"A dual-chamber leadless pacemaker system has been designed for atrioventricular synchronous pacing using wireless, beat-to-beat, implant-to-implant (i2i) communication between distinct atrial and ventricular leadless pacemakers.",FALSE,FALSE,"(149, 152, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,Atrium-to-ventricle and ventricle-to-atrium i2i communication success rates were also assessed.,FALSE,FALSE,"(44, 47, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"Post hoc summary statistics describing the relationships between atrioventricular synchrony and i2i success, posture/activity, implantation indication, atrioventricular event, and heart rate were calculated.",FALSE,FALSE,"(96, 99, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"In the evaluable population (n=384 of 464 enrolled [83%]; 61% male; age, 70 years; weight, 82 kg; 60% ejection fraction; 95% of beats evaluable), the mean atrioventricular synchrony of 98% of beats observed across all postures using the standard 300-millisecond limit was greater than both atrial-to-ventricular i2i (94%) and ventricular-to-atrial i2i (94%; P<0.001), exceeding both i2i values in 95% of patients.",FALSE,FALSE,"(312, 315, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"In addition, the relationship between atrioventricular synchrony and the implant-to-implant (i2i) communication needed to maintain it was evaluated.",FALSE,FALSE,"(93, 96, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"The dual-chamber LP consists of an atrial LP (ALP) and a ventricular LP (VLP; Figure 1A) that communicate bidirectionally and on a beat-to-beat basis to continually deliver atrioventricular synchronous pacing with a novel i2i communication modality.8 Transmissions are sent from ALP to VLP (A-to-V) and from VLP to ALP (V-to-A) immediately before each paced event and after each sensed event to avoid interference with noncommunication (ie, pacing) operations.",FALSE,FALSE,"(222, 225, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,Examples of i2i communication are shown in Figure 1B.,FALSE,FALSE,"(12, 15, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"It is important to note that the i2i signal characteristics can be tuned to enhance transmission success using the i2i setting level, which incorporates the transmitting signal pulse amplitude, transmitting signal pulse duration, and receiving sensing threshold (range, 1–7; nominal, 4).",FALSE,FALSE,"(33, 36, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"B, Example of implant-to-implant, or i2i, communication messages for As-Vp and Ap-Vs event sequences.",FALSE,FALSE,"(37, 40, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"During successful bidirectional i2i communication, the system can function in DDD(R) mode.",FALSE,FALSE,"(32, 35, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"Persistent i2i communication interruption, however, could disrupt this harmony and result in delayed ventricular pacing or withheld atrial pacing.",FALSE,FALSE,"(11, 14, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"The system mitigates such asynchrony by monitoring the receipt of each transmission and automatically transitioning to 1 of 3 “safeguard modes.” If A-to-V i2i communication fails, the system effectively functions in DDI mode.",FALSE,FALSE,"(155, 158, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"In contrast, if V-to-A i2i communication fails, the system effectively functions in VDD mode.",FALSE,FALSE,"(23, 26, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"If i2i communication fails in both directions simultaneously, the system effectively functions in VDI mode.8 Collectively, these 3 safeguard modes guarantee ventricular pacing at the programmed rate during i2i interruption while providing atrial tracking and pacing whenever possible, despite changes in intrinsic rhythm or atrioventricular conduction.",FALSE,FALSE,"(3, 6, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"The atrioventricular synchrony that ultimately results from i2i, however, can be definitively assessed only by manually verifying atrial and ventricular activation timing through external electrocardiographic adjudication.",FALSE,FALSE,"(60, 63, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"Although such a manual assessment may not readily be feasible in a clinical implantation setting, the A-to-V and V-to-A i2i success rates (ie, i2i throughput, percent of transmissions sent that were successfully received) are device-based diagnostics that can be interrogated by the programmer.",FALSE,FALSE,"(120, 123, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"These i2i success rates can serve as feedback metrics, upstream from atrioventricular synchrony, to guide implantation site selection and provide LP communication monitoring.9",FALSE,FALSE,"(6, 9, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"LP diagnostics were cleared immediately before each posture period with the programmer (Merlin Patient Care System, Abbott), and LPs were interrogated after each posture period to determine interim i2i success rates.",FALSE,FALSE,"(198, 201, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"In addition to the acute posture/activity recordings collected in clinic at 3 months, out-of-clinic durations of all distinct instances of i2i communication interruption from 1 to 3 months were collected from device interrogations at 3 months.",FALSE,FALSE,"(139, 142, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"The model was fit with 3-month atrioventricular synchrony as the outcome and the following linear predictors with no associations: i2i success (A-to-V and V-to-A), posture/activity, pacing indication, mean heart rate, RA implantation site, RV implantation site, and atrioventricular event (percent Ap and percent Vp).",FALSE,FALSE,"(131, 134, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"To evaluate the relationship between i2i communication success and the resulting atrioventricular synchrony, each metric was calculated as the mean across all completed postures for each patient.",FALSE,FALSE,"(37, 40, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"Over the analyzed patient population (N=384), the resulting mean success rates for atrioventricular synchrony, A-to-V i2i, and V-to-A i2i were 98.1% (95% CI, 96.7–99.4) of beats, 93.6% (95% CI, 91.2–96.1) of transmissions, and 94.1% (95% CI, 91.7–96.4) of transmissions, respectively, as shown in Figure 2A.",FALSE,FALSE,"(118, 121, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"These i2i rates were achieved with mean programmed A-to-V and V-to-A i2i setting levels of 4.8±1.4 and 5.2±1.3 of 7, respectively.",FALSE,FALSE,"(6, 9, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"V-to-A i2i was statistically greater than A-to-V i2i (P<0.005), and it is important to note that atrioventricular synchrony was greater than both V-to-A i2i and A-to-V i2i (P<0.001 for both).",FALSE,FALSE,"(7, 10, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,Relationship between atrioventricular (AV) synchrony and i2i transmission success.,FALSE,FALSE,"(57, 60, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"A, atrioventricular synchrony, Atrial-to-ventricular (A-to-V) implant-to-implant (i2i) success, and ventricular-to-atrial (V-to-A) i2i success, calculated from the mean percent of beats across all postures for each patient.",FALSE,FALSE,"(82, 85, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"B, Color-coded atrioventricular synchrony vs A-to-V i2i and V-to-A i2i.",FALSE,FALSE,"(52, 55, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"The impact of i2i communication interruption on atrioventricular synchrony can be visualized in Figure 2B, which shows that most outlier patients with atrioventricular synchrony of 70% to 90% (orange) or <70% (red) were associated with A-to-V or V-to-A i2i success rates <80%.",FALSE,FALSE,"(14, 17, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,The ability of the device-based i2i values to ultimately serve as the lower bound of the resulting atrioventricular synchrony was revealed using the difference between atrioventricular synchrony and the lower of the V-to-A and A-to-V i2i values.,FALSE,FALSE,"(32, 35, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"Atrioventricular synchrony was 7.1 (95% CI, 4.6–9.7) mean absolute percentage points greater than the lower of the 2 i2i success rates for each patient.",FALSE,FALSE,"(117, 120, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"Overall, atrioventricular synchrony exceeded both i2i values in 94.5% of patients (363/384) and was no lower than 5% below the lower i2i value in 99.0% of patients (380/384).",FALSE,FALSE,"(50, 53, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,The durations of distinct instances of i2i interruption were quantified for the out-of-clinic period before the 3-month atrioventricular synchrony assessment.,FALSE,FALSE,"(39, 42, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"From 1 to 3 months after implantation across all patients, 86.6% (95% CI, 82.5–90.7) of all instances of A-to-V i2i interruption and 96.8% (95% CI, 95.0–98.7) of all instances of V-to-A i2i interruption were <6 seconds in duration; moreover, 98.9% (95% CI, 97.7–100.0) and 98.9% (95% CI, 97.8–100.0) of all instances of A-to-V and V-to-A interruption, respectively, were <30 seconds in duration.",FALSE,FALSE,"(112, 115, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"Specifically, posture/activity, A-to-V i2i success, V-to-A i2i success, percent Ap, and percent Vp demonstrated a significant impact on atrioventricular synchrony (P<0.001), but pacing indication, heart rate, and implantation site did not.",FALSE,FALSE,"(39, 42, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"This first dual-chamber LP system maintains atrioventricular synchrony through a novel beat-to-beat, i2i communication channel.",FALSE,FALSE,"(101, 104, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"If 100% of such i2i transmissions are successful, atrioventricular synchrony would be observed in 100% of beats.",FALSE,FALSE,"(16, 19, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"During bouts of i2i communication interruption, novel safeguard algorithms provide dynamic shifts in pacing mode to minimize any resulting asynchrony.",FALSE,FALSE,"(16, 19, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"An important finding was that ≈99% of i2i interruption instances resolved within 30 seconds, when the system returns to DDD behavior before changes in atrial rate or PR interval are likely given an opportunity to disrupt atrioventricular synchrony.",FALSE,FALSE,"(38, 41, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"As a consequence of the safeguards, the fleeting nature of most i2i interruptions, and potential for intrinsic ventricular activation, atrioventricular synchrony should always meet or exceed i2i success in either direction, absent any confounding sensing or capture issues.",FALSE,FALSE,"(64, 67, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"Across a broad spectrum of patient implantation indications, postures, activities, heart rates, implantation sites, and atrioventricular event combinations in this patient population, A-to-V and V-to-A i2i transmissions were successful in 93.6% and 94.1% of beats, respectively, yet atrioventricular synchrony was achieved in 98.1% of beats.",FALSE,FALSE,"(202, 205, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"Moreover, atrioventricular synchrony exceeded both i2i success rates in 94.5% of patients and was no lower than 5% below both i2i values in 99.0% of patients.",FALSE,FALSE,"(51, 54, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"Note that the apparent patient anomalies in which the mean atrioventricular synchrony did not exceed mean i2i success rates (eg, 3 orange points in the upper-right corner of Figure 2B) were associated with atrioventricular synchrony values just under the 90% cutoff (ie, 88.8%, 87.0%, and 83.3%).",FALSE,FALSE,"(106, 109, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"Although atrioventricular synchrony can be definitively verified only by manual electrocardiographic adjudication, i2i success rates are device-based diagnostics that can be readily interrogated by the programmer and serve as a lower bound for atrioventricular synchrony estimation.",FALSE,FALSE,"(115, 118, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"Therefore, implantation site selection and subsequent device monitoring can be facilitated by using i2i success as a conservative surrogate for atrioventricular synchrony.",FALSE,FALSE,"(100, 103, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"Two previous preclinical ovine studies of this system’s i2i communication reported long-term A-to-V and V-to-A i2i transmission success rates exceeding 99%8 and atrioventricular synchrony exceeding 99% across a variety of postures/activities, similar to this clinical study.9 The slightly higher i2i success rates observed in those 2 preclinical studies may be attributed to differences in ovine compared with human intra-LP distances and orientations, which are anatomically constrained and may affect i2i signal reception.",FALSE,FALSE,"(56, 59, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"Successful i2i communication, which is verified intraprocedurally during implantation, could theoretically be hindered by the ambulatory postures, activities, and cardiovascular conduction scenarios associated with daily living.",FALSE,FALSE,"(11, 14, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"However, these anatomical LP locations may not fully capture the factors that can affect i2i communication and atrioventricular synchrony (eg, relative distance and orientation of the LPs) due to patient-to-patient differences in cardiac anatomy.",FALSE,FALSE,"(89, 92, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,It is important to note that the i2i setting level can be manually adjusted beyond the automatic recommendations to achieve a patient-specific balance of i2i success and battery longevity.,FALSE,FALSE,"(33, 36, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"During atrial pacing, greater atrioventricular synchrony could result from the VLP maintaining both the V-A and V-V delays, despite transient A-to-V i2i interruption.",FALSE,FALSE,"(149, 152, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"In contrast, greater atrioventricular synchrony during ventricular sensing may be explained by its lack of dependence on A-to-V i2i communication to initiate the atrioventricular delay for timely ventricular activity when intact atrioventricular conduction was present.",FALSE,FALSE,"(128, 131, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,This additional and more accurate quantification of true atrioventricular synchrony further illustrated the functionality of beat-to-beat i2i communication for true dual-chamber leadless pacing.,FALSE,FALSE,"(138, 141, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"However, the reasons for exclusion (eg, withdrawn consent, LP fixation, improper device programming, ECG signals with persistent noise or low amplitudes) were independent of i2i communication and thus not expected to bias the reported communication success or downstream atrioventricular synchrony.",FALSE,FALSE,"(174, 177, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"In addition, such out-of-clinic settings may also include environmental electrical noise that could potentially interfere with i2i communication.",FALSE,FALSE,"(127, 130, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,"An evaluation of atrioventricular synchrony during ambulatory 24-hour Holter periods without programming restrictions or prescribed postures/activities should be the subject of future analyses, as should longer-term i2i communication performance.",FALSE,FALSE,"(216, 219, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,Device-based i2i communication success diagnostics were within 5% of the assessed atrioventricular synchrony in 99% of patients and thus may serve as a lower-bound surrogate to an otherwise cumbersome manual atrioventricular synchrony measurement.,FALSE,FALSE,"(13, 16, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC11305627,Nonstandard Abbreviations and AcronymsA-to-Vatrial to ventricular deviceALPatrial leadless pacemakeri2iimplant-to-implantLPleadless pacemakerRAright atrialRVright ventricleV-to-Aventricular to atrial deviceVLPventricular leadless pacemaker,FALSE,FALSE,"(101, 104, 'i2i', 'ion-to-image')","Proteomics experiment, Imaging, Analytical chemistry"
PMC10146746,"Alignment of the spectra was performed after the preprocessing step with MSIWarp, a Python package provided with C++ implementation.",FALSE,FALSE,"(73, 80, 'MSIWarp', 'msiwarp')","Proteomics experiment, Imaging, Structure analysis"
PMC10146746,MSIWarp is a flexible tool compatible with multiple instrument types to perform mass alignment of mass spectrometry imaging spectra [22].,FALSE,FALSE,"(0, 7, 'MSIWarp', 'msiwarp')","Proteomics experiment, Imaging, Structure analysis"
PMC10146746,"MSIWarp alignment significantly improved the performance of the CNN model, especially for the two machines that showed lower performances without alignment.",FALSE,FALSE,"(0, 7, 'MSIWarp', 'msiwarp')","Proteomics experiment, Imaging, Structure analysis"
PMC10146746,"Keeping the alignment with MSIWarp, we compared the results obtained on the three culture media per machine (Table 2).",FALSE,FALSE,"(27, 34, 'MSIWarp', 'msiwarp')","Proteomics experiment, Imaging, Structure analysis"
PMC10146746,"Keeping the alignment with MSIWarp, we compared the performances obtained after 24 h and 48 h of growth on two machines (MYCO-PSL and SAINT-ANTOINE).",FALSE,FALSE,"(27, 34, 'MSIWarp', 'msiwarp')","Proteomics experiment, Imaging, Structure analysis"
PMC10146746,Impact of the machine and of the alignment with MSIWarp.,FALSE,FALSE,"(48, 55, 'MSIWarp', 'msiwarp')","Proteomics experiment, Imaging, Structure analysis"
PMC5608769,We have developed massPix—an R package for analysing and interpreting data from MSI of lipids in tissue.,FALSE,FALSE,"(18, 25, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769," massPix produces single ion images, performs multivariate statistics and provides putative lipid annotations based on accurate mass matching against generated lipid libraries.",FALSE,FALSE,"(1, 8, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769," massPix is an open-source tool for the analysis and statistical interpretation of MSI data, and is particularly useful for lipidomics applications.",FALSE,FALSE,"(1, 8, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,"Here, we have developed massPix, an R-based package which processes MSI data, plots single ion distributions and performs multivariate statistics [principal components analysis (PCA) and clustering].",FALSE,FALSE,"(24, 31, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,massPix supports data in imzML format (Race et al.,FALSE,FALSE,"(1, 8, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,"Whilst massPix has been developed for high resolution matrix assisted laser desorption ionisation (MALDI) data acquired with Thermo Scientific instrumentation, the software is vendor agnostic and can be applied to any data in imzML format independent of mass spectrometry platform.",FALSE,FALSE,"(7, 14, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,"massPix is compatible with Windows, Mac and Linux operating systems, and requires at least sufficient RAM to load the entire experimental dataset into memory (for instance to process 3 GB image file, ~3.2 GB memory is used).",FALSE,FALSE,"(0, 7, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,"massPix is run from the R scripting interface, however a detailed knowledge of R is not required to install and use the software.",FALSE,FALSE,"(0, 7, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,"massPix outputs high quality images, a data frame of the final normalised and annotated image which can be further manipulated in R, and csv files for spectra corresponding to cluster centers, PCA loadings, and lipid annotations.",FALSE,FALSE,"(0, 7, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,"The massPix R package, all R scripts, library files and the imzML Converter are available on GitHub (https://github.com/hallz/massPix).",FALSE,FALSE,"(4, 11, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,MALDI–MSI is currently more widely used within the field and these datasets have been used to developed massPix.,FALSE,FALSE,"(104, 111, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,The overall data processing workflow followed by massPix is shown (b),FALSE,FALSE,"(49, 56, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,The overall data processing workflow followed by massPix is shown (b),FALSE,FALSE,"(49, 56, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,massPix has the further capability to perform difference matching on deisotoped features to search for mass differences associated with measurement-introduced alternation (e.g.,FALSE,FALSE,"(1, 8, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,massPix uses an unsupervised approach to classify pixels of high spectral similarity using PCA (Fig.,FALSE,FALSE,"(0, 7, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,The use of massPix software can thus aid interpretation of region-specific molecular changes.,FALSE,FALSE,"(11, 18, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,"Single ion distributions produced by massPix for [PC(36:1)+K]+, [PC(38:6)+K]+ , [PC(40:6)+K]+, in a sub-section of cerebellum (b).",FALSE,FALSE,"(37, 44, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,"Availability and implementation: The source code, R package, documentation and test data are freely available to download from https://github.com/hallz/massPix.",FALSE,FALSE,"(152, 159, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC5608769,massPix is distributed under the GNU General Public Licence (version 3).,FALSE,FALSE,"(0, 7, 'massPix', 'masspix')","Proteomics experiment, Statistics and probability, Imaging, Metabolomics"
PMC7953914,The International Wheat Information System (WheatIS) Expert Working Group (EWG) was initiated in 2012 under the Wheat Initiative with a broad range of contributing organizations.,FALSE,FALSE,"(44, 51, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"The mission of the WheatIS EWG was to create an informational infrastructure, establish data standards, and build a single portal that allows search, retrieval, and display of globally distributed wheat data sets that are indexed in standard data formats at servers around the world.",FALSE,FALSE,"(19, 26, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"The web portal at WheatIS.org was released publicly in 2015, and by 2020, it expanded to 8 geographically-distributed nodes and around 20 organizations under its umbrella.",FALSE,FALSE,"(18, 25, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"Realizing the importance of findability and accessibility of wheat data sets distributed around the world, the Wheat Information System (WheatIS) Expert Working Group was established in 2012 to develop data standards for the wheat community and enable data query and access to globally-distributed data sets in standardized formats.",FALSE,FALSE,"(137, 144, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"Three years after the inception of the WheatIS EWG, the WheatIS portal was made publicly available in 2015 through wheatis.org.",FALSE,FALSE,"(39, 46, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"Currently, the web portal is maintained at the University of Western Australia, Australia, and the portal WheatIS servers are located at the “Plant Bioinformatics Facility” hosted by URGI France.",FALSE,FALSE,"(106, 113, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"Only after 7 years, WheatIS “nodes,” i.e., servers that contain indexed and formatted data sets, proliferated and are currently distributed in 3 continents in 5 countries, demonstrating the buy-in from the wheat research communities ( Alaux et al., 2018; Blake et al., 2019; Scheben et al., 2019; Wilkinson et al., 2016b; Yuan et al., 2017).",FALSE,FALSE,"(20, 27, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,Goals of WheatIS Expert Working Group.,FALSE,FALSE,"(10, 17, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"The Wheat Initiative tasked the WheatIS EWG’s to provide the international wheat research community with easy access to wheat genetics, phenotype with environmental information, genomic data and bioinformatics tools, and to support and promote the diverse wheat databases internationally.",FALSE,FALSE,"(32, 39, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"To help, the Wheat Data Interoperability Working Group (WDI-WG) was created as one of the Research Data Alliance working groups, under the umbrella of the WheatIS Expert Working Group.",FALSE,FALSE,"(155, 162, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"Some members belong to the WheatIS EWG, other have a more fundamental or transversal interest.",FALSE,FALSE,"(27, 34, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"To this date, no salary is provided to WheatIS EWG members or the members of their research groups to create or contribute to wheatis.org.",FALSE,FALSE,"(39, 46, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"This meager funding from the Wheat Initiative means that many people that are involved in the WheatIS EWG activities, such as curating data, building indexed data sets, configuring and maintaining servers, are doing these tasks on a volunteer basis in addition to their regular daily tasks.",FALSE,FALSE,"(94, 101, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"Fortunately, both computational and experimental research groups that are part of the WheatIS community recognize the primary importance of data availability, access, and sharing through wheatis.org, and because it is beneficial to the larger scientific community, they consider their service a crucial part of their scientific responsibility.",FALSE,FALSE,"(86, 93, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"The most significant accomplishment of the WheatIS EWG is the creation of a central hub, called WheatIS that provides a publicly available single-entry point.",FALSE,FALSE,"(43, 50, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"The WheatIS core server have access to resources at the globally-distributed nodes and enables data query and extraction through the web portal, unifying data discovery for the wheat research community.",FALSE,FALSE,"(4, 11, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"Specifically, the WheatIS portal was created to: 1) provide access to a data file repository storing files with their associated metadata; 2) allow queries to find data available in the WheatIS core and its nodes using keywords through a google-like search engine; 3) Data standards recommendations ( Dzale Yeumo et al., 2017); and 4) catalog several dedicated integrative databases that manage data types such as genomic, genetic, phenotypic, and functional genomic.",FALSE,FALSE,"(18, 25, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,Current WheatIS searchable nodes.,FALSE,FALSE,"(9, 16, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"The following are the current organizations that manage a WheatIS server node: 1) the International Maize and Wheat Improvement Center CIMMYT (Mexico), 2) the European Bioinformatics Institute (EMBL-EBI) (UK), 3) the GrainGenes database (USA), 4) the Gramene database (USA), 5) the Triticeae Toolbox database (USA), 6) Transplant-IPGPAS (Poland), 7) l’Unité de Recherche Génomique Info (URGI) (France), and 8) wheatgenome.info at the University of Western Australia (Australia).",FALSE,FALSE,"(58, 65, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,Rules of how to become a part of the WheatIS community.,FALSE,FALSE,"(38, 45, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"The WheatIS community is always expanding, adding new data sets and nodes from groups that never contributed data to wheatis.org.",FALSE,FALSE,"(4, 11, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"WheatIS contributing members provides know-how and support to those who would like to create and maintain their own WheatIS nodes at their locations or contribute data to WheatIS, a simple request to wheatis-contact@wheatis.org will provide help and support.",FALSE,FALSE,"(0, 7, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"Our primary goal for the WheatIS Expert Working Group is to create a single portal that can query indexed data sets distributed worldwide, extract information, and provide access to these data sets to the wheat research community.",FALSE,FALSE,"(25, 32, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,The size and types of data sets accessible at WheatIS are growing daily with more nodes being added.,FALSE,FALSE,"(46, 53, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"In all apparent measures, WheatIS is successful in building up a highly collaborative community of wheat research groups and creating a valuable product that is useful in connecting heterogenous data sets.",FALSE,FALSE,"(26, 33, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"In the case of WheatIS, the remarkable need to search, reach, and extract wheat data sets that are generated across the globe was a given among wheat scientists, and still energizes the community as more data sets are being generated with continually cheapening experimental technologies and computational power.",FALSE,FALSE,"(15, 22, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"In the case of WheatIS EWG, the formation of the Wheat Initiative by G20 ministers of agriculture instantly created such a supra-national umbrella organization.",FALSE,FALSE,"(15, 22, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"It is also important to mention that some members of the WheatIS EWG are also members of the maize, Brassica and rice communities and their contributions played a significant role in WheatIS’s success and in turn their experience in the WheatIS initiative are making an impact in their communities.",FALSE,FALSE,"(57, 64, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"It needed technical expertise to build and maintain a strong computational infrastructure and create data formats to make data sets readable; scientific expertise to understand different types of wheat data sets (including genetic, genomic, phenotypic, and metabolic); outreach capability to help build relationships to add new nodes with new data sets; and leaders who not only motivate and manage personnel, but also work with the Wheat Initiative and the broader wheat community to promote and support WheatIS.",FALSE,FALSE,"(505, 512, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"For WheatIS, or for any scientific community for that matter, the critical question is the type of the expertise needed and how much time the experts can devote to a fledgling community.",FALSE,FALSE,"(4, 11, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"When the WheatIS EWG was formed to create a single portal to make wheat data sets findable, accessible, and shareable ( Wilkinson et al., 2016a), the initial focus was primarily on the data sets.",FALSE,FALSE,"(9, 16, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"However, sharing data sets also lead to strengthening wheat communities as well, which happened for WheatIS working under the Wheat Initiative.",FALSE,FALSE,"(100, 107, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"Through WheatIS and through sharing data sets, WheatIS has evolved into a fledgling nexus for the other EWGs, a few in the beginning, and more later, to contribute to a single portal where any data points generated would be made accessible.",FALSE,FALSE,"(8, 15, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"Through this communication network, WheatIS is helping the Wheat Initiative to become a more cohesive group and facilitates future collaborations.",FALSE,FALSE,"(36, 43, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"Although the current graphical user interface for WheatIS is functional, it needs improvement in several areas.",FALSE,FALSE,"(50, 57, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"In the new interface, which we colloquially name WheatIS 2.0, we plan not only to work with the cosmetic issues, but also functional issues such as providing a more advanced and easy-to-use search capabilities.",FALSE,FALSE,"(49, 56, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,The WheatIS 2.0 will be shaped in these and other specific areas that were identified through personal discussions in the EWG meetings and the feedback we received from actual users.,FALSE,FALSE,"(4, 11, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,We first thank the “Wheat Information System Expert Working Group” (WheatIS EWG) members for their valuable input to build this infrastructure.,FALSE,FALSE,"(68, 75, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"We thank the Wheat Initiative led by Hélène Lucas, Peter Langridge and Frank Ordon that created a remarkable umbrella organization for WheatIS to thrive.",FALSE,FALSE,"(135, 142, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,I wonder if they are planning to provide some data analytics or AI type of data prediction in WheatIS in the future.,FALSE,FALSE,"(95, 102, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"The manuscript described the process and successful experiences of forming an international research community, namely the international Wheat Information System (WheatIS) Expert working group.",FALSE,FALSE,"(163, 170, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"At the lowest level of quality check, when a new dataset is indexed at one of the nodes, the WheatIS system automatically checks its formatting, and if the dataset is not formatted correctly, it is not displayed through the web interface, and flagged for further quality check.",FALSE,FALSE,"(93, 100, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914," Although correct formatting and accurate display of the datasets are important, the most important criterion for indexing a dataset at WheatIS is primarily its scientific value for the WheatIS users.",FALSE,FALSE,"(136, 143, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,The process of selecting and indexing datasets at the WheatIS nodes is crucial; every dataset available through the WheatIS framework needs to be high-quality.,FALSE,FALSE,"(54, 61, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"Therefore, all indexed datasets at WheatIS are required to be either peer-reviewed, manually curated by professional curators, or both.",FALSE,FALSE,"(35, 42, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,Most datasets at WheatIS are the products of peer-reviewed scientific research with associated peer-reviewed publications.,FALSE,FALSE,"(17, 24, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC7953914,"In addition to our ongoing volunteer efforts, we continuously look for new funding resources for WheatIS.",FALSE,FALSE,"(97, 104, 'WheatIS', 'WheatIS')","Plant biology, Ecology, Biological databases, Bioinformatics, Agricultural science"
PMC11223827,The PSIPRED Workbench is available at http://bioinf.cs.ucl.ac.uk/psipred.,FALSE,FALSE,"(4, 11, 'PSIPRED', 'psipred')","Structure prediction, Protein folds and structural domains, Protein secondary structure, Protein folding, stability and design, Protein structure analysis"
PMC11223827,The PSIPRED Workbench is part of a worldwide ecosystem of Bioscience data repositories and web services.,FALSE,FALSE,"(4, 11, 'PSIPRED', 'psipred')","Structure prediction, Protein folds and structural domains, Protein secondary structure, Protein folding, stability and design, Protein structure analysis"
PMC11223827,We have been developing the PSIPRED Workbench for nearly 25 years.,FALSE,FALSE,"(28, 35, 'PSIPRED', 'psipred')","Structure prediction, Protein folds and structural domains, Protein secondary structure, Protein folding, stability and design, Protein structure analysis"
PMC11223827,"Since 2019, we have published a number of new methods in the UCL Bioinformatics Group and have made some of these available online via the PSIPRED Workbench.",FALSE,FALSE,"(139, 146, 'PSIPRED', 'psipred')","Structure prediction, Protein folds and structural domains, Protein secondary structure, Protein folding, stability and design, Protein structure analysis"
PMC11223827,"Similarly to PSIPRED, S4PRED prediction results comprise a confidence score, a cartoon representation, 3-state prediction assignment, and the original amino acid sequence.",FALSE,FALSE,"(13, 20, 'PSIPRED', 'psipred')","Structure prediction, Protein folds and structural domains, Protein secondary structure, Protein folding, stability and design, Protein structure analysis"
PMC11223827,"This is a significant improvement over our cutting edge PSIPRED method, which achieves a Q3 accuracy of 70.6% when tested on single sequences without any provided homology information.",FALSE,FALSE,"(56, 63, 'PSIPRED', 'psipred')","Structure prediction, Protein folds and structural domains, Protein secondary structure, Protein folding, stability and design, Protein structure analysis"
PMC11223827,The PSIPRED Workbench offers a number of analysis methods.,FALSE,FALSE,"(4, 11, 'PSIPRED', 'psipred')","Structure prediction, Protein folds and structural domains, Protein secondary structure, Protein folding, stability and design, Protein structure analysis"
PMC11223827,Methods available via the PSIPRED workbench,FALSE,FALSE,"(26, 33, 'PSIPRED', 'psipred')","Structure prediction, Protein folds and structural domains, Protein secondary structure, Protein folding, stability and design, Protein structure analysis"
PMC11223827,"Figure 4 shows the trends in usage of the PSIPRED web server since 2018, when our faster and more user-friendly web site was first launched.",FALSE,FALSE,"(42, 49, 'PSIPRED', 'psipred')","Structure prediction, Protein folds and structural domains, Protein secondary structure, Protein folding, stability and design, Protein structure analysis"
PMC11223827,Total number of predictive analysis tasks run by the PSIPRED Workbench in the years 2019 to 2023.,FALSE,FALSE,"(53, 60, 'PSIPRED', 'psipred')","Structure prediction, Protein folds and structural domains, Protein secondary structure, Protein folding, stability and design, Protein structure analysis"
PMC11223827,The PSIPRED workbench remains a popular and well-used bioinformatics resource for researchers across the globe.,FALSE,FALSE,"(4, 11, 'PSIPRED', 'psipred')","Structure prediction, Protein folds and structural domains, Protein secondary structure, Protein folding, stability and design, Protein structure analysis"
PMC11223827,Funding for the PSIPRED Workbench is provided by the UK’s Biotechnology and Biological Sciences Research Council under BBSRC [BB/T019379/1].,FALSE,FALSE,"(16, 23, 'PSIPRED', 'psipred')","Structure prediction, Protein folds and structural domains, Protein secondary structure, Protein folding, stability and design, Protein structure analysis"
PMC11508656,"Thus, APE could be applied in the future as an accelerator of endothelial cell proliferation after, e.g., stent placement or atherosclerosis.",FALSE,TRUE,"(6, 9, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"In a first preliminary pilot study, it was shown that the supplementation of human umbilical vein endothelial cells (HUVECs) with an aqueous extract of AP (APE) did not harm the cells but dose-dependently enhanced the development of an endothelial cell monolayer in vitro four days after seeding [17].",FALSE,TRUE,"(156, 159, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,These data led us to hypothesise that APE can influence the proliferation of HUVECs and the formation of thrombi.,FALSE,TRUE,"(38, 41, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"HUVECs were seeded in well plates in a cell culture medium supplemented with APE at three different concentrations (50, 100, and 200 µg/mL) [17].",FALSE,TRUE,"(77, 80, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,The HUVECs were evaluated at least 12 h after APE and cell culture medium supplementation to avoid a misinterpretation of the morphological state of the endothelial cells [21].,FALSE,TRUE,"(46, 49, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"The effect of APE on the proliferation of HUVECs was assessed in real-time by the xCELLigence system E-plate 16 (ACEA Biosciences, Inc., San Diego, CA, USA) for 85 h at 10 min intervals.",FALSE,TRUE,"(14, 17, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"The effect of APE in increasing concentrations (0 µg/mL, 50 µg/mL, 100 µg/mL, and 200 µg/mL) on the CI was measured.",FALSE,TRUE,"(14, 17, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,The endothelial cells reacted very differently to the addition of APE depending on the concentration of the extract.,FALSE,TRUE,"(66, 69, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Compared to the control cells (46,720.0 ± 6473.9), there was a significant increase in endothelial cells 85 h after the addition of APE at 50 µg/mL (62,428.3 ± 4035.8) and at 100 µg/mL (70,931.1 ± 4850.2).",FALSE,TRUE,"(132, 135, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,Figure 2 clearly shows that the addition of 100 µg/mL APE resulted in a significant increase in the HUVEC density already after 48 h (25%) and even more so after 85 h (52%) of culturing compared to that in the control cells.,FALSE,TRUE,"(54, 57, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"As an example, the course of monolayer growth for the addition of 100 µg/mL APE is shown in Figure 4.",FALSE,TRUE,"(76, 79, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"While the addition of APE at a concentration of 50 µg/mL caused no change in monolayer growth compared to that in the control cells (p = 0.60), the cell index was significantly increased by 22% 85 h after the addition of 100 µg/mL of APE compared to that in the control cells (p = 0.0054).",FALSE,TRUE,"(22, 25, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Two days after cell seeding and continuous cultivation in culture medium with APE, no significant differences in viability between untreated and APE-treated HUVECs could be detected (Figure 5).",FALSE,TRUE,"(78, 81, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Eighty-five hours after cell seeding, a higher number of viable HUVECs cultured with APE-100 and APE-200 was detected compared to that in the control cells.",FALSE,TRUE,"(85, 88, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,There were also significantly more viable HUVECs after the addition of APE-200 than after the addition of AP 50.,FALSE,TRUE,"(71, 74, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"To analyse the influence of the possible damage of APE on HUVECs, the integrity of the outer endothelial cell membrane was examined.",FALSE,TRUE,"(51, 54, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Therefore, two days after cell seeding, no cell damage caused by the addition of the APE was detected.",FALSE,TRUE,"(85, 88, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Interestingly, the lowest LDH release also occurred in HUVECs treated with APE-100.",FALSE,TRUE,"(75, 78, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Four days after cell seeding, LDH release was significantly lower in cell cultures treated with APE-50 and APE-100 compared to that in the untreated control.",FALSE,TRUE,"(96, 99, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,Cells cultured with APE-200 showed no differences compared to the control cells.,FALSE,TRUE,"(20, 23, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,It can therefore be concluded that the cultivation of cells with APE does not have a negative effect on the integrity of the cell membrane and does not induce cell damage in the concentration range investigated.,FALSE,TRUE,"(65, 68, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,The absorbance values obtained for the APE-treated cells were then normalised to this value.,FALSE,TRUE,"(39, 42, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Forty-eight hours after cell seeding, the metabolic activity of all the APE-treated HUVECs was significantly higher than 100% and thus above that of the untreated control cells.",FALSE,TRUE,"(72, 75, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,A significantly increased metabolic activity was observed in cells cultured with 100 µg/mL APE compared to 50 and 200 µg/mL APE (Figure 8).,FALSE,TRUE,"(91, 94, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Eighty-five hours after cell seeding, the metabolic activity of all the APE-treated cells was still above 100% and thus significantly higher than that of the untreated control.",FALSE,TRUE,"(72, 75, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,The highest metabolic activity was again observed in HUVECs cultured with APE-100 (Figure 8).,FALSE,TRUE,"(74, 77, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Forty-eight hours after cell seeding, a significantly increased prostacyclin release was observed in APE-200-treated HUVECs compared to untreated and APE-50- and APE-100-treated cells (Figure 9).",FALSE,TRUE,"(101, 104, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,The significantly highest release was observed in APE-50-treated HUVECs compared to control and APE-100-treated cells.,FALSE,TRUE,"(50, 53, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,HUVECs cultured with APE-100 showed the significantly lowest prostacyclin release compared to APE-50- and APE-200-treated cells (Figure 9).,FALSE,TRUE,"(21, 24, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"To investigate the influence of cultivating HUVECs with APE on a possible inflammatory activation of the cells, the release of the pro-inflammatory interleukin-6 (IL-6) was analysed.",FALSE,TRUE,"(56, 59, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Forty-eight hours after seeding, the significantly highest IL-6 release was found for HUVECs treated with APE-200 compared to those of the untreated and APE-100-treated cells.",FALSE,TRUE,"(106, 109, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,The lowest release was found in APE-100-treated HUVECs (Figure 10).,FALSE,TRUE,"(32, 35, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,The lowest IL-6 release occurred in untreated control cells compared to those in APE-50- and APE-200-treated cells.,FALSE,TRUE,"(81, 84, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,The highest release was observed in APE-200-treated HUVECs compared to that in APE-100-treated and untreated cells.,FALSE,TRUE,"(36, 39, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Compared to APE-200- and APE-50-treated cells, the release of IL-6 by APE-100-treated cells was significantly reduced (Figure 10).",FALSE,TRUE,"(12, 15, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"It can therefore be concluded that the release of IL-6 was significantly increased by culturing the cells in APE-50 and APE-200, whereas culturing the cells in APE-100 was comparable to the release of IL-6 from untreated HUVECs.",FALSE,TRUE,"(109, 112, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,Figure 11 shows adherent HUVECs after supplementation of the culture medium with 100 µg/mL APE.,FALSE,TRUE,"(91, 94, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Forty-eight or eighty-five hours after cell seeding, all HUVECs (with or without APE) showed uniform vinculin expression.",FALSE,TRUE,"(81, 84, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Thus, the formation of cell–cell and cell–substrate contacts was unaffected by the addition of APE.",FALSE,TRUE,"(95, 98, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,The study revealed that APE at a concentration of 100 µg/mL resulted in a significant increase in adherent HUVECs compared to untreated control cells after 48 h and especially 85 h days of cultivation.,FALSE,TRUE,"(24, 27, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,Figure 2 clearly shows that the addition of 100 µg/mL APE led to a significant increase in the density of HUVECs already after 48 h (+25%) and even more significantly after 85 h (+52%) of culturing.,FALSE,TRUE,"(54, 57, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"However, the exact molecular mechanism by which APE achieves the increased HUVEC density remains unclear.",FALSE,TRUE,"(48, 51, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,One possible reason could be the supplementation of cells with iron from APE.,FALSE,TRUE,"(73, 76, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"There are studies analysing the iron content in APE [38,39,40].",FALSE,TRUE,"(48, 51, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"After supplementation of the culture medium with APE, significantly more viable HUVECs adhered compared to control cells (see Figure 2, nearly no death cells were visible), the damage to the outer cell membrane was prevented and less LDH was detected in the culture medium compared to the untreated control, while at the same time the metabolic activity was increased, hinting at an increased proliferation of the HUVECs.",FALSE,TRUE,"(49, 52, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"The activation or perturbation of the endothelial cells, as previously described as a reaction to altered conditions in the culture milieu [41,42,43,44,45], also occurred here in the first two days after the addition of APE at concentrations of 50 and 200 µg/mL, but was completely prevented at a concentration of 100 µg/mL.",FALSE,TRUE,"(220, 223, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,The pattern of the IL-6 release of HUVECs with APE cultivation was very similar to that of prostacyclin.,FALSE,TRUE,"(47, 50, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Here also, no increase in IL-6 concentration compared to that in control cells occurred for the APE concentration of 100 µg/mL (see Figure 10).",FALSE,TRUE,"(96, 99, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Interestingly, no TXA2 was detected in the cell culture supernatant of HUVECs cultured with APE.",FALSE,TRUE,"(92, 95, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,These release responses consistently indicated that there was no inflammatory response of the endothelial cells after adding 100 µg/mL APE to the culture medium.,FALSE,TRUE,"(135, 138, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Thus, in the present study, the reduced synthesis of, e.g., prostacyclin and IL-6 (after 100 µg/mL APE in comparison to 50 or 200 µ/mL APE) could be associated with increased proliferation and thus stronger growth of the endothelial cell monolayer.",FALSE,TRUE,"(99, 102, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,The anti-inflammatory effect of APE may also contribute to the improvement of endothelial proliferation.,FALSE,TRUE,"(32, 35, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"APE has been shown to reduce both TnFα and TGFβ [53,54].",FALSE,TRUE,"(0, 3, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,showed that APE significantly reduced apoptosis [55].,FALSE,TRUE,"(12, 15, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"In addition, an APE-induced increase in endothelial nitric oxide synthase (eNOS) expression has been repeatedly reported [59,60,61,62].",FALSE,TRUE,"(16, 19, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Two or four days after cell seeding, HUVECs (with or without APE) showed uniform vinculin expression, so that the formation of cell–cell and cell–substrate contacts appeared to be unaffected by the addition of APE.",FALSE,TRUE,"(61, 64, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"To date, in vivo toxicological studies of APE have not revealed any toxic effects on kidney, liver, the reproductive system, or body physiology during or after the administration of acute or chronic doses [68,69,70,71,72].",FALSE,TRUE,"(42, 45, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,The highest proliferation was achieved after the addition of 100 µg/mL APE.,FALSE,TRUE,"(71, 74, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Since neither cell–cell (VE-cadherin) nor cell–substrate (vinculin) binding was affected by APE, it is reasonable to assume that the increase in endothelial density was due to the proliferation of HUVECs.",FALSE,TRUE,"(92, 95, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,Representative examples of the HUVEC monolayers of the control culture (without APE) and the culture wit APE in the concentration of 100 µg/mL (85 h after seeding).,FALSE,TRUE,"(80, 83, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Continuous detection of the HUVEC monolayer for the addition of 100 µg/mL APE to the culture medium using the xCelligence system, n = 8 each.",FALSE,TRUE,"(74, 77, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,APE 50: HUVECs in culture medium with 50 µg/mL AP extract.,FALSE,TRUE,"(0, 3, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,APE-100: HUVECs in culture medium with 100 µg/mL AP extract.,FALSE,TRUE,"(0, 3, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,APE-200: HUVECs in culture medium with 200 µg/mL APE.,FALSE,TRUE,"(0, 3, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"(A) Phase contrast image; (B) dead HUVECs stained with PI in red, (C) FDA-stained HUVEC monolayer showing viable cells in green; (D) HUVEC monolayer supplemented with 50 µg/mL APE; (E) HUVEC monolayer supplemented with 100 µg/mL APE; (F) HUVEC monolayer supplemented with 200 µg/mL APE.",FALSE,TRUE,"(176, 179, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,APE-50: HUVECs in culture medium with 50 µg/mL APE.,FALSE,TRUE,"(0, 3, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,AP-100: HUVECs in culture medium with 100 µg/mL APE extract.,FALSE,TRUE,"(48, 51, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,AP200: HUVECs in culture medium with 200 µg/mL APE extract.,FALSE,TRUE,"(47, 50, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,APE-100: HUVECs in culture medium with 100 µg/mL APE.,FALSE,TRUE,"(0, 3, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,Prostacyclin (PGl2)—secretion of HUVECs two and four days after seeding (untreated control: HUVECs in culture medium; 50 µg/mL APE: HUVECs in culture medium with 50 µg/mL APE; 100 µg/mL APE: HUVECs in culture medium with 100 µg/mL APE; 200 µg/mL APE200: HUVECs in culture medium with 200 µg/mL APE.,FALSE,TRUE,"(127, 130, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Representative image of paraformaldehyde-fixated HUVECs in culture medium supplemented with 100 µg/mL APE 85 h after seeding (HUVECs were fluorescently stained threefold, the actin cytoskeleton in green, von Willebrand factor in red, and genomic DNA in blue; scale bar: 50 µm).",FALSE,TRUE,"(102, 105, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC11508656,"Representative immunofluorescence images of paraformaldehyde-fixated HUVECs in culture medium, HUVECs with 50 µg/mL APE, HUVECs with 100 µg/mL APE, and HUVECs with 200 µg/mL APE 85 h after seeding (40× primary magnification).",FALSE,TRUE,"(116, 119, 'APE', 'ape')","Workflows, Ontology and terminology, Bioinformatics"
PMC9929198,"In Phase III the data was engineered using Agilent’s proprietary software and open source software: OpenChrom 1.4 [2], Julia 1.7 [3] and Linux (Ubuntu 21.04) [4].Data formatRaw, Analysed, FilteredParameters for data collectionGCMS standard operating procedures were adhered to for sample analysis, including temperature, run times, carrier gas and internal standards.",FALSE,FALSE,"(100, 109, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,These files are required to be readable by OpenChrom in order that the analytical output can be accessed independently of the GCMS instrument.,FALSE,FALSE,"(43, 52, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,OpenChrom was used to produce a range of files for each sample which were saved into the sample folder.,FALSE,FALSE,"(0, 9, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,The method for producing these files using OpenChrom are described in the experimental design.,FALSE,FALSE,"(43, 52, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,The retention times are recorded in intervals on an average of 600 milliseconds that is exported from OpenChrom.3.“Chromatogram-MS_”.,FALSE,FALSE,"(102, 111, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,The other columns present are automatically produced by OpenChrom and are not relevant for sample identification.6.“Report_”.,FALSE,FALSE,"(56, 65, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,The retention times are recorded in intervals on an average of 600 milliseconds that is exported from OpenChrom.,FALSE,FALSE,"(102, 111, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,The other columns present are automatically produced by OpenChrom and are not relevant for sample identification.,FALSE,FALSE,"(56, 65, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,"In phase III, OpenChrom [7] was used to process the Agilent proprietary data into open source formats.",FALSE,FALSE,"(14, 23, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,OpenChrom is an open source program developed to view and analyse chromatographic as well as other types of data.,FALSE,FALSE,"(0, 9, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,"Specifically OpenChrom can open GCMS data acquired from most proprietary vendors and runs on macOS, Windows and Linux [2].",FALSE,FALSE,"(13, 22, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,"DrugSamples_Drug-MDMA_Pathway-AlHg_Batch-75C.D.2.OpenChrom can read the sample data folder generated by ChemStation without any modification.3.OpenChrom detect peaks using the sample data and the AMDIS database, which must be installed.",FALSE,FALSE,"(49, 58, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,"OpenChrom detects peaks as follows:(i)right-click on the chromatogram,(ii)move the mouse pointer over “Peak Detector” and(iii)click “AMDIS (extern)” from the menu.This produces a number of windows.",FALSE,FALSE,"(0, 9, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,"The peaks are stored in memory and an inverted triangle is displayed on top of the detected peaks.4.Peak areas were obtained in OpenChrom following the steps:(i)right-click on the chromatogram,(ii)hover over “Peak Integrator”,(iii)select “Peak Integrator Trapezoid”; a window with title “Edit Processor Options” appears,(iv)keep the default button highlighted “Use System Options”, and(v)select “Finish” at the bottom right corner of the window.5.The calculated retention times and areas were recorded in a comma separated value (CSV) file following the naming convention in Fig.",FALSE,FALSE,"(128, 137, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,"with prefix “Peaks_”,(vi)click “Finish” at the bottom right of the pop-up window.6.OpenChrom created a report that contains the sample information and the peak areas.",FALSE,FALSE,"(83, 92, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,"The report was saved in the file with prefix “Report_” in text format (with extension “*.txt”); the report is obtained following the steps,(i)right-click on the chromatogram,(ii)select “Chromatogram Reports”,(iii)select “OpenChrom Report (*.txt)”,(iv)save the report by following the same process as in item 5, and by replacing prefix “Peaks_” with “Report_”.7.To record the TIS as a CSV file,(i)right-click on the chromatogram,(ii)move the cursor over “Chromatogram Export”,(iii)click on “CSV Chromatogram (*.csv)”(iv)and follow the same process as in item 5, replacing the prefix with “Chromatogram-MS_”.8.At this point the sample file names are of the form DrugSamples_Drug-MDMA_Pathway-AlHg_Batch-75C.D, where the last block after the “_” represents the batch number of the drug production.",FALSE,FALSE,"(221, 230, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,OpenChrom can read the sample data folder generated by ChemStation without any modification.,FALSE,FALSE,"(0, 9, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,"OpenChrom detect peaks using the sample data and the AMDIS database, which must be installed.",FALSE,FALSE,"(0, 9, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,"OpenChrom detects peaks as follows:(i)right-click on the chromatogram,(ii)move the mouse pointer over “Peak Detector” and(iii)click “AMDIS (extern)” from the menu.",FALSE,FALSE,"(0, 9, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,"Peak areas were obtained in OpenChrom following the steps:(i)right-click on the chromatogram,(ii)hover over “Peak Integrator”,(iii)select “Peak Integrator Trapezoid”; a window with title “Edit Processor Options” appears,(iv)keep the default button highlighted “Use System Options”, and(v)select “Finish” at the bottom right corner of the window.",FALSE,FALSE,"(28, 37, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,OpenChrom created a report that contains the sample information and the peak areas.,FALSE,FALSE,"(0, 9, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,"The report was saved in the file with prefix “Report_” in text format (with extension “*.txt”); the report is obtained following the steps,(i)right-click on the chromatogram,(ii)select “Chromatogram Reports”,(iii)select “OpenChrom Report (*.txt)”,(iv)save the report by following the same process as in item 5, and by replacing prefix “Peaks_” with “Report_”.",FALSE,FALSE,"(221, 230, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC9929198,"select “OpenChrom Report (*.txt)”,",FALSE,FALSE,"(8, 17, 'OpenChrom', 'openchrom')","Proteomics experiment, Proteomics, Metabolomics, Data visualisation"
PMC11480384,"In the current study, the raw data for metabolomics can be obtained in Metabolights, with the ID MTBLS10002 (MetaboLights MTBLS)31.",FALSE,FALSE,"(109, 121, 'MetaboLights', 'metabolights')",Metabolomics
PMC11188463,"The Human Splicing Finder, SpliceAI, and varSEAK database were used to predict the effect of mutations on splicing function.",FALSE,FALSE,"(4, 25, 'Human Splicing Finder', 'human_splicing_finder')","Gene transcripts, RNA splicing, Genetic variation, Data governance, Rare diseases, Medical informatics"
PMC11188463,Human Splicing Finder Version 2.4.1 suggested that the c.5633A>T of DYSF mutation caused alteration of auxiliary sequences and significant alteration of the ESE/ESS motif ratio.,FALSE,FALSE,"(0, 21, 'Human Splicing Finder', 'human_splicing_finder')","Gene transcripts, RNA splicing, Genetic variation, Data governance, Rare diseases, Medical informatics"
PMC11188463,"Different complementary online software tools were employed for splicing prediction: Human Splicing Finder (HSF) Version 2.4.1 (http://www.umd.be/HSF/), SpliceAI (https://spliceailookup.broadinstitute.org/), and varSEAK (https://varseak.bio/).",FALSE,FALSE,"(85, 106, 'Human Splicing Finder', 'human_splicing_finder')","Gene transcripts, RNA splicing, Genetic variation, Data governance, Rare diseases, Medical informatics"
PMC10696839,The prediction procedure for mass values was written in part of the GPMsDB-tk (GPMsDB-dbtk) scripts developed in this study.,FALSE,FALSE,"(79, 90, 'GPMsDB-dbtk', 'gpmsdb-dbtk')","Database management, Microbiology, Proteomics"
PMC10696839,"Matching of protein mass peaks was performed using GPMsDB-tk (v1.0.1, including GPMsDB-dbtk v1.0.1 for building custom databases for user-provided genomes), developed as part of this study.",FALSE,FALSE,"(80, 91, 'GPMsDB-dbtk', 'gpmsdb-dbtk')","Database management, Microbiology, Proteomics"
PMC10696839,The source code and documentation are available at https://github.com/ysekig/GPMsDB-tk [59] and https://github.com/ysekig/GPMsDB-dbtk [60].,FALSE,FALSE,"(122, 133, 'GPMsDB-dbtk', 'gpmsdb-dbtk')","Database management, Microbiology, Proteomics"
PMC10696839,"For identification purposes, a toolkit (GPMsDB-tk) was developed in this study based on these observations with the current GPMsDB.",FALSE,FALSE,"(40, 49, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,The best-matched genome entries were identified using GPMsDB-tk.,FALSE,FALSE,"(54, 63, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,This confirmed that microbial identification by GPMsDB-tk is robust to differences in cultivation conditions.,FALSE,FALSE,"(48, 57, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,"In the cultivation of anaerobes from the same sample, > 100 colonies were selected and anaerobically subcultured in 96-well plates, and then the resultant cells were used for identification with GPMsDB-tk.",FALSE,FALSE,"(195, 204, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,"Overall, 76 isolates (72%), including those matched with MAGs, were correctly identified at the species level; i.e., in these cases, MALDI-TOF MS identification with GPMsDB-tk gave the same GTDB taxonomy string down to the species level with those of 16S rRNA gene sequencing.",FALSE,FALSE,"(166, 175, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,4Identification of the 103 isolates obtained from mouse fecal samples based on MALDI-TOF MS profiles with GPMsDB-tk.,FALSE,FALSE,"(106, 115, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,Identification of the 103 isolates obtained from mouse fecal samples based on MALDI-TOF MS profiles with GPMsDB-tk.,FALSE,FALSE,"(105, 114, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,"Our toolkit (GPMsDB-tk) and database (GPMsDB) thus substantially expand its utility for not only clinical discipline but also the screening of microbes in other microbial fields, including a search for uncultured lineages of descent in the domains Bacteria and Archaea.",FALSE,FALSE,"(13, 22, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,"We found that MALDI-TOF MS measurements with GPMsDB-tk successfully identified the isolates in most of the determinations (96 correct calls out of 103 isolates at the genus to strain [MAG] levels, 93%), as validated by full-length 16S rRNA gene sequencing (Additional file 7: Table S6).",FALSE,FALSE,"(45, 54, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,The prediction procedure for mass values was written in part of the GPMsDB-tk (GPMsDB-dbtk) scripts developed in this study.,FALSE,FALSE,"(68, 77, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,"Matching of protein mass peaks was performed using GPMsDB-tk (v1.0.1, including GPMsDB-dbtk v1.0.1 for building custom databases for user-provided genomes), developed as part of this study.",FALSE,FALSE,"(51, 60, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,GPMsDB-tk is a software toolkit for assigning taxonomic identification to user-provided MALDI-TOF mass spectrometry profiles.,FALSE,FALSE,"(0, 9, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,Details of the functionality available in the GPMsDB-tk are shown in Additional file 1: Fig.,FALSE,FALSE,"(46, 55, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,GPMsDB-tk is a Python package that can be run on a regular laptop using ~ 5 Gb of RAM for a single thread.,FALSE,FALSE,"(0, 9, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,"Unless specified, for taxonomic identification based on MALDI-TOF MS measurements, self-mass calibration in the GPMsDB-tk (option -aa) and -m option (-m 0) were used with the option “reps” (reference data with representative genome entries at the species level), “all” (reference data with all genome entries), or “custom” (reference data with all genome entries plus user-provided custom genome data) with the option “peak_bwf” with schoring theme III (“–score_type weighted”).",FALSE,FALSE,"(112, 121, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,GPMsDB-tk provides not only score values for hit genomes but also probability value for each score.,FALSE,FALSE,"(0, 9, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,Schematic of the GPMsDB-tk.,FALSE,FALSE,"(17, 26, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,GPMsDB-tk results for identification of 81 bacterial and archaeal reference strains.Additional file 5: Table S4.,FALSE,FALSE,"(0, 9, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,GPMsDB-tk results for identification of 13 acidobacterial strains.Additional file 6: Table S5.,FALSE,FALSE,"(0, 9, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,GPMsDB-tk results for identification of 81 bacterial and archaeal reference strains.,FALSE,FALSE,"(0, 9, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,GPMsDB-tk results for identification of 13 acidobacterial strains.,FALSE,FALSE,"(0, 9, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,"GPMsDB-tk, which consists of Python scripts and documentation, is licensed under the GNU General Public License (Version 3).",FALSE,FALSE,"(0, 9, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC10696839,The source code and documentation are available at https://github.com/ysekig/GPMsDB-tk [59] and https://github.com/ysekig/GPMsDB-dbtk [60].,FALSE,FALSE,"(77, 86, 'GPMsDB-tk', 'gpmsdb-tk')","Taxonomy, Proteomics, Microbiology"
PMC11351099,"MacSyFinder with the TXSScan models is used to identify genes and gene clusters encoding for diverse secretion systems (24, 56).",FALSE,FALSE,"(0, 11, 'MacSyFinder', 'macsyfinder')",Functional genomics
PMC11351099,"For example, DefenseFinder, MacSyFinder, and GapMind took around one and a half minutes or less to run for each test genome.",FALSE,FALSE,"(28, 39, 'MacSyFinder', 'macsyfinder')",Functional genomics
PMC10320092,"In this scenario, we present KVFinder-web, an open-source web-based application of parKVFinder software for cavity detection and characterization of biomolecular structures.",FALSE,FALSE,"(29, 37, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,The KVFinder-web has two independent components: a RESTful web service and a web graphical portal.,FALSE,FALSE,"(4, 12, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Our web service, KVFinder-web service, handles client requests, manages accepted jobs, and performs cavity detection and characterization on accepted jobs.",FALSE,FALSE,"(17, 25, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Our graphical web portal, KVFinder-web portal, provides a simple and straightforward page for cavity analysis, which customizes detection parameters, submits jobs to the web service component, and displays cavities and characterizations.",FALSE,FALSE,"(26, 34, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"We provide a publicly available KVFinder-web at https://kvfinder-web.cnpem.br, running in a cloud environment as docker containers.",FALSE,FALSE,"(32, 40, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Further, this deployment type allows KVFinder-web components to be configured locally and customized according to user demand.",FALSE,FALSE,"(37, 45, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Hence, users may run jobs on a locally configured service or our public KVFinder-web.",FALSE,FALSE,"(72, 80, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,Graphical AbstractKVFinder-web: A web-based application for cavity detection and characterization of any type of biomolecular structure.,FALSE,FALSE,"(19, 27, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,KVFinder-web: A web-based application for cavity detection and characterization of any type of biomolecular structure.,FALSE,FALSE,"(0, 8, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Recently, we have developed parKVFinder (13), a robust method for detecting and characterizing binding sites in biomolecules, using a geometric grid-and-sphere method and thread-level parallelization.",FALSE,FALSE,"(31, 39, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Compared to other software for cavity detection, parKVFinder has an intuitive set of parameters and has been extensively benchmarked in the literature for detection and computational capabilities, delivering accurate and robust performance with any type of protein cavity (1,2,4,13).",FALSE,FALSE,"(52, 60, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"parKVFinder stands out by combining geometric and physicochemical characterizations of binding sites, effectively aiding users to identify functionally relevant cavities and to study the molecular recognition process.",FALSE,FALSE,"(3, 11, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Aside from parKVFinder's advances in performance and usability, the installation and configuration procedures of our software, as well as other standalone cavity detection software, still pose a major barrier to users who lack the technical knowledge ideally required to perform them.",FALSE,FALSE,"(14, 22, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"In this scenario, we introduce KVFinder-web, an open-source web-based application of the parKVFinder software, consisting of a RESTful web service for cavity detection and characterization and a graphical web portal.",FALSE,FALSE,"(31, 39, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,Our web application aims to democratize and expand even further the parKVFinder user base in the structural biology community.,FALSE,FALSE,"(71, 79, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"These users will be able to perform cavity detection on third-party computing platforms, such as institutional servers or cloud infrastructures, using parKVFinder as a service (SaaS).",FALSE,FALSE,"(154, 162, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"KVFinder-web is a powerful web-based tool designed to detect cavities in a wide range of biomolecular structures, including but not limited to proteins and nucleic acids.",FALSE,FALSE,"(0, 8, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,The interactive web interface (KVFinder-web portal) provides users an easy-to-use platform to execute the parKVFinder software and analyze the results through any web browser.,FALSE,FALSE,"(31, 39, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Meanwhile, the web service (KVFinder-web service) itself executes parKVFinder (13) with its geometric grid-and-sphere-based method, as detailed in (2,4,13).",FALSE,FALSE,"(28, 36, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"To further enhance user experience, we also provide alternative client-side applications, including a Python HTTP client and a graphical PyMOL plugin (PyMOL KVFinder-web Tools).",FALSE,FALSE,"(157, 165, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"To ensure more comprehensive characterization, KVFinder-web has been integrated with additional features, such as depth calculation and Eisenberg & Weiss hydropathy characterization, which are implemented in pyKVFinder (4).",FALSE,FALSE,"(47, 55, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,These features are now part of the latest version of parKVFinder (v1.2.0) and enable users to obtain more robust and detailed results.,FALSE,FALSE,"(56, 64, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"The KVFinder-web portal (Figure 1; https://github.com/LBC-LNBio/KVFinder-web-portal), developed using the Shiny R package (14) (https://shiny.rstudio.com), provides a simple and straightforward website for cavity analysis and visualization, requiring only a biomolecule in Protein Data Bank (PDB) format or PDB ID.",FALSE,FALSE,"(4, 12, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,KVFinder-web portal.,FALSE,FALSE,"(0, 8, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,(A) Screenshot of the KVFinder-web portal main page showing the main tabs and the sections of target biomolecule input and choice of KVFinder-web run mode.,FALSE,FALSE,"(22, 30, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"After uploading the PDB, the KVFinder-web portal checks the PDB and informs non-standard residues detected [3].",FALSE,FALSE,"(29, 37, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"The ‘Run Cavity Analysis’ tab features the major functionalities of KVFinder-web, in which users can load a target biomolecule, customize the cavity detection parameters (‘Probe In’, ‘Probe Out’, ‘Removal Distance’, and ‘Volume Cutoff’), and download and visualize results.",FALSE,FALSE,"(68, 76, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"To execute KVFinder-web (Figure 1B), users must first choose a biomolecule and then select an appropriate run mode.",FALSE,FALSE,"(11, 19, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,KVFinder-web allows users to submit any kind of target biomolecule for cavity analysis (Figure 1B).,FALSE,FALSE,"(0, 8, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"After completing these two steps, users submit the job to the KVFinder-web service by clicking the ‘Submit the job’ button.",FALSE,FALSE,"(62, 70, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,The KVFinder-web portal provides an easy and interactive way to download and visualize cavity detection results.,FALSE,FALSE,"(4, 12, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,Results and visualization in KVFinder-web portal.,FALSE,FALSE,"(29, 37, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,(A) Screenshot of the results section of the KVFinder-web portal.,FALSE,FALSE,"(45, 53, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,The KVFinder-web service (https://github.com/LBC-LNBio/KVFinder-web-service) is a RESTful service with a Web-Queue-Worker architecture.,FALSE,FALSE,"(4, 12, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,The received data must contain the molecular structures and parKVFinder detection parameters.,FALSE,FALSE,"(63, 71, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,The ‘Worker’ module communicates with the ‘Queue’ module and requests the next job to be processed by the parKVFinder software.,FALSE,FALSE,"(109, 117, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Each KVFinder-web service module is packaged in a Docker container (21), making it available to run in local or cloud computing environments.",FALSE,FALSE,"(5, 13, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Besides our publicly available KVFinder-web service, a local web service can also be configured on third-party platforms, such as institutional servers or cloud services, using parKVFinder as a service (SaaS).",FALSE,FALSE,"(31, 39, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"The KVFinder-web service has some limitations compared to a standalone version of parKVFinder, which are designed to prevent very demanding jobs from exhausting the web service.",FALSE,FALSE,"(4, 12, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Therefore, some parKVFinder parameters are constrained or even predefined.",FALSE,FALSE,"(19, 27, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"The KVFinder-web application components (KVFinder-web service and KVFinder-web portal) will be continuously improved and updated to meet the needs of the scientific community, including new characterizations and performance enhancements.",FALSE,FALSE,"(4, 12, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"In addition to the primary interaction mode of KVFinder-web, we also provide additional client-side applications, such as PyMOL KVFinder-web and an example of a Python HTTP client, which broaden the range of possibilities for user interaction.",FALSE,FALSE,"(47, 55, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"For users familiarized with PyMOL (16), PyMOL KVFinder-web Tools (Supplementary Figure S1; https://github.com/LBC-LNBio/PyMOL-KVFinder-web-Tools), developed in Python3 and Qt, integrates the KVFinder-web service with the molecular visualization software.",FALSE,FALSE,"(46, 54, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,This user-friendly graphical user interface (GUI) enables customization of detection parameters for a target biomolecular structure and submits jobs to a configured KVFinder-web service (Supplementary Figure S1A).,FALSE,FALSE,"(165, 173, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"As in parKVFinder PyMOL plugin (13), the search space can also be adjusted to a custom box (box adjustment mode) and/or a radius within a target ligand or molecule (ligand adjustment mode), instead of detecting and characterizing cavities throughout the biomolecular surface (whole structure mode).",FALSE,FALSE,"(9, 17, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"After successful submission, accepted jobs are routinely and asynchronously requested to the KVFinder-web service.",FALSE,FALSE,"(93, 101, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"This graphical plugin operates in a similar way to KVFinder-web portal, the characterizations are shown in lists (Supplementary Figure S1B) and the cavities customized by their properties in PyMOL viewer (Supplementary Figure S1C and D).",FALSE,FALSE,"(51, 59, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Nevertheless, submitted jobs in the KVFinder-web portal can be loaded in PyMOL KVFinder-web Tools and vice versa.",FALSE,FALSE,"(36, 44, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,The KVFinder-web portal and PyMOL KVFinder-web Tools may not fully fulfill the needs of advanced users.,FALSE,FALSE,"(4, 12, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,This client operates using standard parKVFinder input syntax and provides tools to interact with a configured KVFinder-web service.,FALSE,FALSE,"(39, 47, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"The KVFinder-web service is publicly available at https://kvfinder-web.cnpem.br, which is free and open to all users without login requirement.",FALSE,FALSE,"(4, 12, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"As an illustrative example of KVFinder-web (Figure 3), we detected and characterized the catalytic site of the Human Immunodeficiency Virus type 1 (HIV-1) protease bound to cyclic urea carbonyl oxygen (22), using KVFinder-web portal.",FALSE,FALSE,"(30, 38, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Besides cavity detection and shape definition, KVFinder-web also provides the volume, area, depth and hydropathy of the detected cavities (Figure 2; cavity KAG).",FALSE,FALSE,"(47, 55, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"The cavity detection implemented in the KVFinder-web application has been extensively benchmarked against other well-known cavity detection methods in the literature (2,4,13), presenting robust detection and computational performance.",FALSE,FALSE,"(40, 48, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"In addition, we evaluated KVFinder-web computational performance with a protein structure dataset from (13), varying two major parameters related to cavity detection: ‘Probe Out’ and ‘Removal Distance’ (Figure 4).",FALSE,FALSE,"(26, 34, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Thus, greater ‘Probe Out’ sizes tend to reduce the degree of accessibility of the molecular surface created and ultimately, increase the elapsed time to perform calculations in KVFinder-web service (Figure 4A).",FALSE,FALSE,"(177, 185, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,Effects of detection parameters on KVFinder-web service performance.,FALSE,FALSE,"(35, 43, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"KVFinder-web provides simple access to a rapid and accurate method of cavity detection and characterization in any type of biomolecular structure, regardless of the molecule's nature.",FALSE,FALSE,"(0, 8, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"The KVFinder-web portal provides a simple, easy and straightforward pipeline on any web browser with interactive visualization capabilities powered by NGLVieweR and DataTable.",FALSE,FALSE,"(4, 12, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,The graphical PyMOL plugin replicates the main features of parKVFinder PyMOL plugin with few limitations to avoid exhausting KVFinder-web service computational resources and to ensure a smooth and efficient operation for all users.,FALSE,FALSE,"(62, 70, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"Together with the KVFinder-web service, the KVFinder-web portal and PyMOL KVFinder-web Tools aim to democratize parKVFinder software and remove barriers for users who do not have the technical knowledge to install and configure a cavity detection software, who have restricted computational resources, or who just want to perform a simple and quick analysis.",FALSE,FALSE,"(18, 26, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,The publicly available KVFinder-web service is accessible at https://kvfinder-web.cnpem.br.,FALSE,FALSE,"(23, 31, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"The corresponding open-source code of the KVFinder-web service, KVFinder-web portal, and PyMOL KVFinder-web Tools are available at https://github.com/LBC-LNBio/KVFinder-web-service (https://doi.org/10.5281/zenodo.7825790), https://github.com/LBC-LNBio/KVFinder-web-portal (https://doi.org/10.5281/zenodo.7825788), and https://github.com/LBC-LNBio/PyMOL-KVFinder-web-Tools (https://doi.org/10.5281/zenodo.7825798), respectively.",FALSE,FALSE,"(42, 50, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,The complete documentation of the modules of the KVFinder-web application is available at https://lbc-lnbio.github.io/KVFinder-web/.,FALSE,FALSE,"(49, 57, 'KVFinder', 'kvfinder')","Structural biology, Computational chemistry, Structure analysis, Protein structure analysis"
PMC10320092,"In this scenario, we present KVFinder-web, an open-source web-based application of parKVFinder software for cavity detection and characterization of biomolecular structures.",FALSE,FALSE,"(29, 41, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,The KVFinder-web has two independent components: a RESTful web service and a web graphical portal.,FALSE,FALSE,"(4, 16, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"Our web service, KVFinder-web service, handles client requests, manages accepted jobs, and performs cavity detection and characterization on accepted jobs.",FALSE,FALSE,"(17, 29, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"Our graphical web portal, KVFinder-web portal, provides a simple and straightforward page for cavity analysis, which customizes detection parameters, submits jobs to the web service component, and displays cavities and characterizations.",FALSE,FALSE,"(26, 38, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"We provide a publicly available KVFinder-web at https://kvfinder-web.cnpem.br, running in a cloud environment as docker containers.",FALSE,FALSE,"(32, 44, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"Further, this deployment type allows KVFinder-web components to be configured locally and customized according to user demand.",FALSE,FALSE,"(37, 49, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"Hence, users may run jobs on a locally configured service or our public KVFinder-web.",FALSE,FALSE,"(72, 84, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,Graphical AbstractKVFinder-web: A web-based application for cavity detection and characterization of any type of biomolecular structure.,FALSE,FALSE,"(19, 31, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,KVFinder-web: A web-based application for cavity detection and characterization of any type of biomolecular structure.,FALSE,FALSE,"(0, 12, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"In this scenario, we introduce KVFinder-web, an open-source web-based application of the parKVFinder software, consisting of a RESTful web service for cavity detection and characterization and a graphical web portal.",FALSE,FALSE,"(31, 43, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"KVFinder-web is a powerful web-based tool designed to detect cavities in a wide range of biomolecular structures, including but not limited to proteins and nucleic acids.",FALSE,FALSE,"(0, 12, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,The interactive web interface (KVFinder-web portal) provides users an easy-to-use platform to execute the parKVFinder software and analyze the results through any web browser.,FALSE,FALSE,"(31, 43, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"Meanwhile, the web service (KVFinder-web service) itself executes parKVFinder (13) with its geometric grid-and-sphere-based method, as detailed in (2,4,13).",FALSE,FALSE,"(28, 40, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"To further enhance user experience, we also provide alternative client-side applications, including a Python HTTP client and a graphical PyMOL plugin (PyMOL KVFinder-web Tools).",FALSE,FALSE,"(157, 169, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"To ensure more comprehensive characterization, KVFinder-web has been integrated with additional features, such as depth calculation and Eisenberg & Weiss hydropathy characterization, which are implemented in pyKVFinder (4).",FALSE,FALSE,"(47, 59, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"The KVFinder-web portal (Figure 1; https://github.com/LBC-LNBio/KVFinder-web-portal), developed using the Shiny R package (14) (https://shiny.rstudio.com), provides a simple and straightforward website for cavity analysis and visualization, requiring only a biomolecule in Protein Data Bank (PDB) format or PDB ID.",FALSE,FALSE,"(4, 16, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,KVFinder-web portal.,FALSE,FALSE,"(0, 12, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,(A) Screenshot of the KVFinder-web portal main page showing the main tabs and the sections of target biomolecule input and choice of KVFinder-web run mode.,FALSE,FALSE,"(22, 34, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"After uploading the PDB, the KVFinder-web portal checks the PDB and informs non-standard residues detected [3].",FALSE,FALSE,"(29, 41, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"The ‘Run Cavity Analysis’ tab features the major functionalities of KVFinder-web, in which users can load a target biomolecule, customize the cavity detection parameters (‘Probe In’, ‘Probe Out’, ‘Removal Distance’, and ‘Volume Cutoff’), and download and visualize results.",FALSE,FALSE,"(68, 80, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"To execute KVFinder-web (Figure 1B), users must first choose a biomolecule and then select an appropriate run mode.",FALSE,FALSE,"(11, 23, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,KVFinder-web allows users to submit any kind of target biomolecule for cavity analysis (Figure 1B).,FALSE,FALSE,"(0, 12, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"After completing these two steps, users submit the job to the KVFinder-web service by clicking the ‘Submit the job’ button.",FALSE,FALSE,"(62, 74, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,The KVFinder-web portal provides an easy and interactive way to download and visualize cavity detection results.,FALSE,FALSE,"(4, 16, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,Results and visualization in KVFinder-web portal.,FALSE,FALSE,"(29, 41, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,(A) Screenshot of the results section of the KVFinder-web portal.,FALSE,FALSE,"(45, 57, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,The KVFinder-web service (https://github.com/LBC-LNBio/KVFinder-web-service) is a RESTful service with a Web-Queue-Worker architecture.,FALSE,FALSE,"(4, 16, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"Each KVFinder-web service module is packaged in a Docker container (21), making it available to run in local or cloud computing environments.",FALSE,FALSE,"(5, 17, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"Besides our publicly available KVFinder-web service, a local web service can also be configured on third-party platforms, such as institutional servers or cloud services, using parKVFinder as a service (SaaS).",FALSE,FALSE,"(31, 43, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"The KVFinder-web service has some limitations compared to a standalone version of parKVFinder, which are designed to prevent very demanding jobs from exhausting the web service.",FALSE,FALSE,"(4, 16, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"The KVFinder-web application components (KVFinder-web service and KVFinder-web portal) will be continuously improved and updated to meet the needs of the scientific community, including new characterizations and performance enhancements.",FALSE,FALSE,"(4, 16, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"In addition to the primary interaction mode of KVFinder-web, we also provide additional client-side applications, such as PyMOL KVFinder-web and an example of a Python HTTP client, which broaden the range of possibilities for user interaction.",FALSE,FALSE,"(47, 59, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"For users familiarized with PyMOL (16), PyMOL KVFinder-web Tools (Supplementary Figure S1; https://github.com/LBC-LNBio/PyMOL-KVFinder-web-Tools), developed in Python3 and Qt, integrates the KVFinder-web service with the molecular visualization software.",FALSE,FALSE,"(46, 58, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,This user-friendly graphical user interface (GUI) enables customization of detection parameters for a target biomolecular structure and submits jobs to a configured KVFinder-web service (Supplementary Figure S1A).,FALSE,FALSE,"(165, 177, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"After successful submission, accepted jobs are routinely and asynchronously requested to the KVFinder-web service.",FALSE,FALSE,"(93, 105, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"This graphical plugin operates in a similar way to KVFinder-web portal, the characterizations are shown in lists (Supplementary Figure S1B) and the cavities customized by their properties in PyMOL viewer (Supplementary Figure S1C and D).",FALSE,FALSE,"(51, 63, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"Nevertheless, submitted jobs in the KVFinder-web portal can be loaded in PyMOL KVFinder-web Tools and vice versa.",FALSE,FALSE,"(36, 48, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,The KVFinder-web portal and PyMOL KVFinder-web Tools may not fully fulfill the needs of advanced users.,FALSE,FALSE,"(4, 16, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,This client operates using standard parKVFinder input syntax and provides tools to interact with a configured KVFinder-web service.,FALSE,FALSE,"(110, 122, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"The KVFinder-web service is publicly available at https://kvfinder-web.cnpem.br, which is free and open to all users without login requirement.",FALSE,FALSE,"(4, 16, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"As an illustrative example of KVFinder-web (Figure 3), we detected and characterized the catalytic site of the Human Immunodeficiency Virus type 1 (HIV-1) protease bound to cyclic urea carbonyl oxygen (22), using KVFinder-web portal.",FALSE,FALSE,"(30, 42, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"Besides cavity detection and shape definition, KVFinder-web also provides the volume, area, depth and hydropathy of the detected cavities (Figure 2; cavity KAG).",FALSE,FALSE,"(47, 59, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"The cavity detection implemented in the KVFinder-web application has been extensively benchmarked against other well-known cavity detection methods in the literature (2,4,13), presenting robust detection and computational performance.",FALSE,FALSE,"(40, 52, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"In addition, we evaluated KVFinder-web computational performance with a protein structure dataset from (13), varying two major parameters related to cavity detection: ‘Probe Out’ and ‘Removal Distance’ (Figure 4).",FALSE,FALSE,"(26, 38, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"Thus, greater ‘Probe Out’ sizes tend to reduce the degree of accessibility of the molecular surface created and ultimately, increase the elapsed time to perform calculations in KVFinder-web service (Figure 4A).",FALSE,FALSE,"(177, 189, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,Effects of detection parameters on KVFinder-web service performance.,FALSE,FALSE,"(35, 47, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"KVFinder-web provides simple access to a rapid and accurate method of cavity detection and characterization in any type of biomolecular structure, regardless of the molecule's nature.",FALSE,FALSE,"(0, 12, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"The KVFinder-web portal provides a simple, easy and straightforward pipeline on any web browser with interactive visualization capabilities powered by NGLVieweR and DataTable.",FALSE,FALSE,"(4, 16, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,The graphical PyMOL plugin replicates the main features of parKVFinder PyMOL plugin with few limitations to avoid exhausting KVFinder-web service computational resources and to ensure a smooth and efficient operation for all users.,FALSE,FALSE,"(125, 137, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"Together with the KVFinder-web service, the KVFinder-web portal and PyMOL KVFinder-web Tools aim to democratize parKVFinder software and remove barriers for users who do not have the technical knowledge to install and configure a cavity detection software, who have restricted computational resources, or who just want to perform a simple and quick analysis.",FALSE,FALSE,"(18, 30, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,The publicly available KVFinder-web service is accessible at https://kvfinder-web.cnpem.br.,FALSE,FALSE,"(23, 35, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,"The corresponding open-source code of the KVFinder-web service, KVFinder-web portal, and PyMOL KVFinder-web Tools are available at https://github.com/LBC-LNBio/KVFinder-web-service (https://doi.org/10.5281/zenodo.7825790), https://github.com/LBC-LNBio/KVFinder-web-portal (https://doi.org/10.5281/zenodo.7825788), and https://github.com/LBC-LNBio/PyMOL-KVFinder-web-Tools (https://doi.org/10.5281/zenodo.7825798), respectively.",FALSE,FALSE,"(42, 54, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC10320092,The complete documentation of the modules of the KVFinder-web application is available at https://lbc-lnbio.github.io/KVFinder-web/.,FALSE,FALSE,"(49, 61, 'KVFinder-web', 'kvfinder-web')","Structural biology, Computational biology, Protein structural motifs and surfaces"
PMC8685811,"To fulfill this need, we developed pyKVFinder, a Python package to detect and characterize cavities in biomolecular structures for data science and automated pipelines.",FALSE,FALSE,"(35, 45, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"pyKVFinder efficiently detects cavities in biomolecular structures and computes their volume, area, depth and hydropathy, storing these cavity properties in NumPy arrays.",FALSE,FALSE,"(0, 10, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Benefited from Python ecosystem interoperability and data structures, pyKVFinder can be integrated with third-party scientific packages and libraries for mathematical calculations, machine learning and 3D visualization in automated workflows.",FALSE,FALSE,"(70, 80, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"As proof of pyKVFinder’s capabilities, we successfully identified and compared ADRP substrate-binding site of SARS-CoV-2 and a set of homologous proteins with pyKVFinder, showing its integrability with data science packages such as matplotlib, NGL Viewer, SciPy and Jupyter notebook.",FALSE,FALSE,"(12, 22, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,pyKVFinder facilitates biostructural data analysis with scripting routines in the Python ecosystem and can be building blocks for data science and drug design applications.,FALSE,FALSE,"(0, 10, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"In this scenario, we developed pyKVFinder, an open-source python package for cavity detection and characterization abstracted into multidimensional arrays.",FALSE,FALSE,"(31, 41, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"pyKVFinder adopts the original geometrical grid-and-sphere-based detection method as implemented in KVFinder [7], which has been improved in the latest parallel version, parKVFinder [8].",FALSE,FALSE,"(0, 10, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"To fulfill this need, pyKVFinder is wrapped into Python and, using Python’s well-established data structure (e.",FALSE,FALSE,"(22, 32, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"pyKVFinder can be integrated with third-party scientific packages and libraries for mathematical calculations, statistical analysis, and tridimensional visualization.",FALSE,FALSE,"(0, 10, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Moreover, users can explore the functionality of pyKVFinder step-by-step using interactive interfaces, such as IPython/Jupyter notebooks.",FALSE,FALSE,"(49, 59, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"As mentioned above, one of pyKVFinder’s main contributions in data science workflows is to translate the detected cavities from tridimensional coordinates of cavity points to NumPy arrays, a data structure that allows for a wide diversity of scientific computation and efficient storage and access to N-dimensional arrays (ndarrays), also called tensors [19].",FALSE,FALSE,"(27, 37, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Besides conventional cavity properties such as volume and area, which are stored as Python dictionaries, pyKVFinder computes cavity depth and hydropathy.",FALSE,FALSE,"(105, 115, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Thus, pyKVFinder provides a versatile way to detect and characterize biomolecular cavities and integrate this information into data science or automated workflows.",FALSE,FALSE,"(6, 16, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Python-C parallel KVFinder (pyKVFinder) applies a Simplified Wrapper and Interface Generator (SWIG; http://www.swig.org/) to extend grid operations written in C to Python, a high-level programming language.",FALSE,FALSE,"(28, 38, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,pyKVFinder can be easily installed with the pip package management system.,FALSE,FALSE,"(0, 10, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"In pyKVFinder, the target biomolecule is inserted into a regular 3D grid, which is stored as an ndarray, considering the van der Waals radii of the atoms.",FALSE,FALSE,"(3, 13, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"To detect cavities, pyKVFinder uses a dual-probe algorithm that scans the biomolecular structure, as described in [7, 8].",FALSE,FALSE,"(20, 30, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"On each detected cavity, pyKVFinder may perform spatial, depth, hydropathy and constitutional characterizations.",FALSE,FALSE,"(25, 35, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,pyKVFinder can be imported as a package in the Python environment and users can decide to run the full cavity detection and characterization workflow through the run_workflow function or run pyKVFinder functions in a stepwise fashion.,FALSE,FALSE,"(0, 10, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"At the latter, users can integrate pyKVFinder functions into third-party Python packages and benefit from interactive IPython/Jupyter notebooks.",FALSE,FALSE,"(35, 45, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"By running pyKVFinder in Python environment, users can visualize the detected cavities through the Python NGL Viewer widget [21].",FALSE,FALSE,"(11, 21, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,1Diagram of cavity detection and characterization workflow using pyKVFinder package.,FALSE,FALSE,"(65, 75, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,The flowchart illustrates function calls and their dependencies for performing cavity detection and characterization with pyKVFinder package,FALSE,FALSE,"(122, 132, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,Diagram of cavity detection and characterization workflow using pyKVFinder package.,FALSE,FALSE,"(64, 74, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,2Representative view of detected cavities in the pyKVFinder data structure.,FALSE,FALSE,"(49, 59, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Based on a 3D grid (left figure), pyKVFinder detects cavities in biomolecules and returns an ndarray with dimensions (m, n, o) (right figure).",FALSE,FALSE,"(34, 44, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,Representative view of detected cavities in the pyKVFinder data structure.,FALSE,FALSE,"(48, 58, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"With the ndarray of detected cavities, pyKVFinder package may perform four characterization procedures, i.e., spatial, constitutional, depth and hydropathy characterizations.",FALSE,FALSE,"(39, 49, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,a Three different characterizations of the apo ADRP substrate-binding cavity of SARS-CoV-2 (PDB ID: 6WEN) using pyKVFinder.,FALSE,FALSE,"(112, 122, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,c Hydropathy profile of the same compared cavities collected from pyKVFinder ndarrays.,FALSE,FALSE,"(66, 76, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"The cavity detection and characterization objects, from detect, spatial, constitutional, calculate_frequencies, depth, hydropathy functions, can be stored into a pyKVFinderResults class that accumulates them in its attributes.",FALSE,FALSE,"(162, 172, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"In this scenario, the export, write and plot_frequencies methods have their counterparts in the export, write_results and plot_frequencies functions of pyKVFinder package, respectively.",FALSE,FALSE,"(152, 162, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Additionally, the read_cavity function reads a cavity file (.pdb extension), written by pyKVFinder, parKVFinder or KVFinder, and a target PDB or XYZ file (.pdb or.xyz extension), and returns an ndarray with each element corresponding to the cavity space (> 1), biomolecule space (0), or bulk or empty space (− 1), similar to the output of the detect function.",FALSE,FALSE,"(88, 98, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"To demonstrate the use of pyKVFinder and how it benefits from the Python ecosystem, we identified the substrate-binding pocket of the ADP-ribose phosphatase (ADRP) domain of SARS-CoV-2 nsp3 protein in the apo form (PDB ID: 6WEN).",FALSE,FALSE,"(26, 36, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"pyKVFinder successfully detected the ADRP substrate-binding cavity and determined traditional cavity properties such as volume, area and residues surrounding the ADP-ribose cavity (Fig.",FALSE,FALSE,"(0, 10, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"For instance, we used pyKVFinder calculate_frequencies and plot_frequencies functions to determine the composition of the type of residues surrounding the cavity and plotted this composition as a bar chart (Additional file 1: Fig.",FALSE,FALSE,"(22, 32, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"In pyKVFinder, this step is performed using matplotlib library [38], but users are free to analyze data and present results on their favorite graphing library.",FALSE,FALSE,"(3, 13, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"The standard workflow of pyKVFinder, as in parKVFinder, detects cavities and applies spatial and constitutional characterizations.",FALSE,FALSE,"(25, 35, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,The full workflow of pyKVFinder comprises standard workflow with depth and hydropathy characterizations,FALSE,FALSE,"(21, 31, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Since pyKVFinder stores the properties to be colored in cavities in the B-factor column of a PDB-formatted file, users can easily change the style and color scheme in most of molecular visualization programs.",FALSE,FALSE,"(6, 16, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"For this reason, we used pyKVFinder to detect the ADRP substrate-binding site in aligned ADRP domains from different species and compare their properties.",FALSE,FALSE,"(25, 35, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Finally, since pyKVFinder uses native Python dictionaries to store the residues surrounding the detected cavity, we can easily tabulate the residue frequency.",FALSE,FALSE,"(15, 25, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Thus, we used pyKVFinder with its box adjustment mode to detect and estimate the volume of the ADP-ribose binding site throughout 600 frames of the ADRP domain’s trajectory.",FALSE,FALSE,"(14, 24, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"The shape of the detected cavities defined by pyKVFinder and parKVFinder finely adjust to the original ligand in the binding site, as well as MSPocket (Fig.",FALSE,FALSE,"(46, 56, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"4a) Besides that, the volume calculated by pyKVFinder (346.8 ± 78.7 Å3) and parKVFinder (346.5 ± 79.3 Å3) is closely related to the volume of ADP-ribose (351.1 Å3; molecular surface volume estimated by YASARA program [40]), the ligand that originally occupied the binding site in the crystallographic structure used in the molecular dynamics simulations (Fig.",FALSE,FALSE,"(43, 53, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"For instance, pyKVFinder, parKVFinder and POVME can segment the search space, which trims points outside this custom space, while the other methods only explore the whole structure, which includes neighboring regions at the binding site.",FALSE,FALSE,"(14, 24, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,pyKVFinder outperformed all analyzed methods.,FALSE,FALSE,"(0, 10, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Even when applying the newly available characterization, depth and hydropathy, pyKVFinder's elapsed time only increased 36%, still outperforming other benchmarking methods.",FALSE,FALSE,"(79, 89, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Further, compared to its counterpart, parKVFinder, pyKVFinder was 3.3 times faster in detecting ADRP binding site.",FALSE,FALSE,"(51, 61, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Hence, experienced users requiring scripting routines are encouraged to use pyKVFinder due to its improved performance, while newcomers should prioritize parKVFinder due to its simplicity of installation and execution.",FALSE,FALSE,"(76, 86, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Further, the scalability of pyKVFinder, upon increasing number of threads, follows the same behavior presented by parKVFinder [8].",FALSE,FALSE,"(28, 38, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"However, the cavities data structure is only accessible inside the Python ecosystem in pyKVFinder, which provides ndarrays and Python dictionaries.",FALSE,FALSE,"(87, 97, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"pyKVFinder will undergo continuous improvements and updates, according to its applications by the scientific community.",FALSE,FALSE,"(0, 10, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Additionally, pyKVFinder aims to offload its routines to the GPU for performance enhancement in data-intensive applications.",FALSE,FALSE,"(14, 24, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,pyKVFinder provides an efficient and integrable Python package for cavity detection and characterization in biomolecular structures for data science and automated pipelines.,FALSE,FALSE,"(0, 10, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"In addition to fast, accurate and efficient cavity detection and characterization, pyKVFinder stores spatial and physicochemical properties in Python ndarrays, that ease scripting and data analysis.",FALSE,FALSE,"(83, 93, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Further, pyKVFinder performance was benchmarked against well-known geometrical methods for cavity detection and characterization.",FALSE,FALSE,"(9, 19, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Finally, we have successfully shown an application of pyKVFinder integration with matplotlib, NGL Viewer, SciPy and Jupyter notebook, that compared the ADRP substrate-binding site of SARS-CoV-2 in homologous proteins.",FALSE,FALSE,"(54, 64, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811," Project name: pyKVFinderProject home page: https://github.com/LBC-LNBio/pyKVFinderOperating system(s): any supporting Python >  = 3.7 (tested on Linux and macOS)Programming language: Python, COther requirements: swig >  = 4.0.1, toml >  = 0.10.2, numpy >  = 1.20.3, matplotlib >  = 3.3.3License: GNU General Public License v3.0Any restrictions to use by non-academics: None.",FALSE,FALSE,"(15, 25, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,Project name: pyKVFinder,FALSE,FALSE,"(14, 24, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,Project home page: https://github.com/LBC-LNBio/pyKVFinder,FALSE,FALSE,"(48, 58, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"pyKVFinder source code, documentation and tutorials are available in the Python Package Index (PyPI) repository, https://pypi.org/project/pyKVFinder, and the GitHub repository, https://github.com/LBC-LNBio/pyKVFinder.",FALSE,FALSE,"(0, 10, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC8685811,"Documentation and tutorials are available at pyKVFinder webpage, https://lbc-lnbio.github.io/pyKVFinder.",FALSE,FALSE,"(45, 55, 'pyKVFinder', 'pykvfinder')","Structure analysis, Workflows, Mathematics, Structural biology, Machine learning, Computational chemistry, Protein structural motifs and surfaces"
PMC9341511,"Tests on both simulated and real data sets show that TransMeta consistently outperforms PsiCLASS, StringTie2 plus its merge mode, and Scallop plus TACO, the most popular tools, in terms of precision and recall under a wide range of coverage thresholds at the meta-assembly level.",FALSE,FALSE,"(88, 96, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"The second paradigm, such as the state-of-the-art meta-assembly tool PsiCLASS (Song et al.",FALSE,FALSE,"(69, 77, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,PsiCLASS uses statistical methods to build the global subexon graphs and generates the assembly by dynamic programming optimization and voting algorithms.,FALSE,FALSE,"(0, 8, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"We evaluated the performance of TransMeta at both the meta-assembly level and the individual sample level by comparing it with the state-of-the-art multisample assembler PsiCLASS, which can produce a meta-assembly for multiple samples and a certain set of transcripts for each individual sample as well.",FALSE,FALSE,"(170, 178, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"(2019) for their evaluation of PsiCLASS, we benchmarked the TransMeta under two widely used aligners, HISAT2 and STAR, in terms of the standard criteria that have been widely used in evaluation of transcriptome assemblers.",FALSE,FALSE,"(31, 39, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"On the three simulated data sets under the HISAT2 and STAR alignments, we ran TransMeta and PsiCLASS with different filtering thresholds to get the sets of meta-assemblies, then ran StringTie2 and Scallop with their default settings for each individual sample, and finally merged them by using StringTie2-Merge and TACO, respectively, with different filtering thresholds.",FALSE,FALSE,"(92, 100, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"Specifically, on the simulated data set S1 under the HISAT2 alignments, when we adjusted the coverage thresholds of all the assemblers to set their assemblies all to the precision of 0.7 (or any other value), the recall of TransMeta reached about 0.38, which is ∼20% higher than that of PsiCLASS, ∼41% higher than StringTie2 system, and ∼90% higher than Scallop + TACO (Fig.",FALSE,FALSE,"(287, 295, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"Evaluated based on the areas under the precision-recall curve (AUC) scores, we found that the AUC score of TransMeta was ∼13.7% higher than that of PsiCLASS, 22.3% higher than that of StringTie2 system, and 49.8% higher than that of Scallop + TACO.",FALSE,FALSE,"(148, 156, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"TransMeta and PsiCLASS are the so-called meta-assemblers, but they may also produce a certain set of transcripts for each sample.",FALSE,FALSE,"(14, 22, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"Specifically, averaged on the 20 samples of data set S1 under the HISAT2 alignments, the recall of TransMeta reached about 0.38, which was ∼5.6% higher than that of PsiCLASS and >11.4% higher than those of StringTie2 and Scallop.",FALSE,FALSE,"(165, 173, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,(2019) in their evaluation of PsiCLASS.,FALSE,FALSE,"(30, 38, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"Then on the five tested data sets R1–R5 under the HISAT2 alignments, the recalls of TransMeta reached about 0.11, 0.15, 0.16, 0.14, and 0.17, respectively; those of the second-best assembler PsiCLASS were about 0.07, 0.11, 0.12, 0.11, and 0.14, respectively; those of StringTie2 were about 0.05, 0.09, 0.11, 0.09, and 0.12, respectively; and those of Scallop + TACO were relatively worse.",FALSE,FALSE,"(191, 199, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"It means that under the same precision level, TransMeta correctly identified ∼21%–57% more transcripts than PsiCLASS and 42%–120% more than the StringTie2 system.",FALSE,FALSE,"(108, 116, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"Furthermore, in terms of the AUC, TransMeta showed an improvement of ∼17%–35% over PsiCLASS, as well as 19%–62% over the StringTie2 system on the five data sets, whereas Scallop + TACO showed relatively poor performance.",FALSE,FALSE,"(83, 91, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"For instance, averaged on the 73 samples from R1, TransMeta correctly reconstructed ∼19.6% more transcripts than PsiCLASS, as well as 62.1% and 75.2% more than the single-sample assemblers StringTie2 and Scallop, respectively.",FALSE,FALSE,"(113, 121, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"Meanwhile, its precision was the highest on all 73 samples, which were on average ∼15% higher than those of PsiCLASS and over twofold higher than those of StringTie2 and Scallop (Fig.",FALSE,FALSE,"(108, 116, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,TransMeta and PsiCLASS are the so-called meta-assemblers that simultaneously analyze multiple samples.,FALSE,FALSE,"(14, 22, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"Based on the alignments, we ran TransMeta and PsiCLASS with different filtering thresholds.",FALSE,FALSE,"(46, 54, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,Comparisons of TransMeta and PsiCLASS on the large-scale data sets under the HISAT2 alignments at the meta-assembly level.,FALSE,FALSE,"(29, 37, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"(A–E) Precision-recall curves of TransMeta and PsiCLASS on 100, 200, 300, 400, and 500 subsets of GEUVADIS samples.",FALSE,FALSE,"(47, 55, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"The meta-assemblers TransMeta and PsiCLASS were run with 25 threads, and the single-sample assemblers StringTie2 and Scallop were run sequentially to assemble individual samples.",FALSE,FALSE,"(34, 42, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC9341511,"For instance, on data set R1 with 73 samples under the HISAT2 alignments, TransMeta took ∼133 min with a peak memory of 11 GB, whereas PsiCLASS took ∼228 min with a peak memory of 11.7 GB, StringTie2 took 188 min with <1 GB memory, and Scallop took 251 min with a peak memory of ∼4.9 GB.",FALSE,FALSE,"(135, 143, 'PsiCLASS', 'psiclass')",Sequence assembly
PMC11530086,"Information about the best performing definitions of IOH regarding 30-day mortality, hospital length of stay (hLOS), and postanesthesia care unit length of stay (PACU-LOS) is missing.",FALSE,TRUE,"(162, 166, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"First, we used one subset to choose the best fitting definitions of IOH for the outcomes 30-day mortality, hLOS, and PACU-LOS.",FALSE,TRUE,"(117, 121, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"The best fitting definitions were relative time with a MAP (mean arterial pressure) of <80 mmHg for 30-day mortality, lowest MAP for one minute for hLOS, and lowest MAP for one cumulative minute for PACU-LOS.",FALSE,TRUE,"(199, 203, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"Testing these three definitions of IOH in the independent second subset confirmed the associations of IOH with 30-day mortality, hLOS, and PACU-LOS.",FALSE,TRUE,"(139, 143, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"Using a data-driven approach, we identified the best fitting definitions of IOH for 30-day mortality, hLOS, and PACU-LOS.",FALSE,TRUE,"(112, 116, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"The main objective of this trial was to find the best fitting definitions of IOH and their associations with 30-day mortality, hospital LOS (hLOS), and postanesthesia care unit (PACU) LOS in a general surgical population at a large academic center.",FALSE,TRUE,"(178, 182, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,PACU-LOS was defined as the difference between the date of discharge and the date of admission to the PACU.,FALSE,TRUE,"(0, 4, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,The LOS and PACU-LOS datasets were subset of the mortality dataset.,FALSE,TRUE,"(12, 16, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"The statistical framework of this study was described similarly before in [21]: The aims of the study were structured into two sequential steps for each of the three outcomes (30-day mortality, hLOS and PACU LOS): 1) to determine which definition of hypotension has the strongest association with 30-day mortality, hLOS, and PACU-LOS and 2) to estimate the association between the best fitting hypotension definition identified in Aim 1 and the outcomes: 30-day mortality, hLOS and PACU-LOS.",FALSE,TRUE,"(203, 207, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"This was done using a univariable, a multivariable logistic regression model (for binary outcome 30-day mortality) and two linear regression models (for the metric outcomes hLOS and PACU-LOS).",FALSE,TRUE,"(182, 186, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,The 1% trimmed hLOS and PACU-LOS were log-transformed for use as dependent variables in the models in order to stabilize the residual distribution; the results were back-transformed to the original scale for graphical presentation.,FALSE,TRUE,"(24, 28, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"By further excluding all patients not admitted to a PACU, we finally included 56,990 patients in the analysis of PACU LOS (Fig 1).",FALSE,TRUE,"(52, 56, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"Abbreviations: hLOS: hospital length of stay; PACU: postanesthesia care unit; PACU-LOS: postanesthesia care unit length of stay; n, number.",FALSE,TRUE,"(46, 50, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"The median hospital LOS was 5.1 (IQR: 3.1–10.3) days, and the median PACU-LOS was 2.1 (IQR: 1.6–2.9) h.",FALSE,TRUE,"(69, 73, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"LOS: length of stay, PACU: postoperative care unit, BMI: body mass index, ASA: American association of anesthesiologist score, min: minutes, d: days, COPD: chronic obstructive pulmonary disease, AIDS: Acquired Immunodeficiency Syndrome, n: number, ENT: ear-nose-throat, non-or: non operating room",FALSE,TRUE,"(21, 25, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"LOS: length of stay, PACU: postoperative care unit, BMI: body mass index, ASA: American association of anesthesiologist score, min: minutes, d: days, n: number, MAP: mean arterial pressure, IOH: intraoperative hypotension",FALSE,TRUE,"(21, 25, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"Most of the definitions were negatively associated with mortality, hLOS, and PACU-LOS in univariable models.",FALSE,TRUE,"(77, 81, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"For PACU-LOS, we found the strongest association with “lowest MAP for one cumulative minute”, closely followed by “lowest MAP for one minute”.",FALSE,TRUE,"(4, 8, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"LOS: Length of stay, PACU: Post anesthesia care unit, LOS: length of stay, PACU: postoperative care unit, MAP: mean arterial pressure, IOH: intraoperative hypotension, min: minutes",FALSE,TRUE,"(21, 25, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,The PACU-LOS showed very similar behavior but for “lowest MAP for 1 cumulative minute” (Fig 5).,FALSE,TRUE,"(4, 8, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"MAP: mean arterial pressure, PACU: postanesthesia care unit.",FALSE,TRUE,"(29, 33, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"BMI: body mass index, MAP: mean arterial pressure, PACU: postanesthesia care unit.",FALSE,TRUE,"(51, 55, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"In addition to evaluating the association of IOH with mortality, hLOS, and PACU-LOS, we assessed the degree of influence of IOH and adjustment variables on these outcomes using the Brier score and MSE.",FALSE,TRUE,"(75, 79, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"While mortality and hLOS were mainly influenced by the ASA score (mortality) and duration of surgery (hLOS), respectively, PACU LOS was mostly influenced by duration of surgery and IOH.",FALSE,TRUE,"(123, 127, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,Regarding hLOS and PACU-LOS differences could be shown.,FALSE,TRUE,"(19, 23, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"In contrast, the 0.95 confidence set for hLOS contains only three IOH definitions (Lowest MAP for 1 minute, Lowest MAP for 1 cumulative minute, and Lowest MAP for 3 cumulative minutes) and that for PACU-LOS contains only the selected Lowest MAP for 1 cumulative minute.",FALSE,TRUE,"(198, 202, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,Data on the association of IOH and PACU-LOS were missing entirely to the authors’ best knowledge.,FALSE,TRUE,"(35, 39, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"Regarding our LOS analyses, we found Lowest MAP for one minute to be the best fitting IOH definition for hLOS and “Lowest MAP for one cumulative minute” to be the best fitting IOH definition for PACU-LOS.",FALSE,TRUE,"(195, 199, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"While IOH had less influence than length of surgery and duration from hospital admission to surgery on hLOS, it had as much influence as length of surgery on PACU-LOS.",FALSE,TRUE,"(158, 162, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,Multivariable regression analyses revealed a sigmoid relationship between IOH and both hLOS and PACU-LOS (Figs 4 and 5).,FALSE,TRUE,"(96, 100, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"In this study, we found a three-phase association of IOH with postoperative outcomes as follows: 1) below a MAP of approximately 60 mmHg, hLOS and PACU-LOS decreased with increasing MAP, followed by 2) a plateau between 60 and 75 mmHg, and 3) above a MAP of 75 mmHg, hLOS and PACU-LOS further decreased with increasing MAP.",FALSE,TRUE,"(147, 151, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC11530086,"In this retrospective trial, “Cumulative time with a MAP <80 mmHg” was the best fitting definition of intraoperative hypotension for associations with mortality, while “Lowest MAP for one minute” performed best for hospital length of stay, and “Lowest MAP for one cumulative minute” for PACU-length of stay.",FALSE,TRUE,"(287, 291, 'PACU', 'pacu')","Phylogenetics, Sequence analysis"
PMC10924745,"We applied our findings to the BDEI model and implemented its parameter estimator PyBDEI, employing targeted numerical analysis methods for accurate and fast resolution of its equations.",FALSE,FALSE,"(82, 88, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"We show the accuracy and speed of PyBDEI on simulated data and compare it to the gold standard Bayesian tool BEAST2 (Bouckaert et al., 2019) and the deep-learning-based tool PhyloDeep (Voznica et al., 2022).",FALSE,FALSE,"(34, 40, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"Lastly, we apply PyBDEI to infer the epidemiological parameters that shaped the Ebola epidemic in Sierra-Leone in 2014.",FALSE,FALSE,"(17, 23, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,We applied our theoretical findings to implement a fast and efficient parameter estimator for the BDEI model (which we called PyBDEI).,FALSE,FALSE,"(126, 132, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"To assess the performance of our maximum-likelihood estimator PyBDEI, we used the simulated data from Voznica et al.",FALSE,FALSE,"(62, 68, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"To evaluate PyBDEI performance on forests, we additionally generated two types of forests for the large data set.",FALSE,FALSE,"(12, 18, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"We applied PyBDEI to these data sets, and compared the results to those reported for BEAST2 and PhyloDeep in Voznica et al.",FALSE,FALSE,"(11, 17, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"For the large data set, we applied PyBDEI to full trees, but also to the two types of forests.",FALSE,FALSE,"(35, 41, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"Average relative errors for PyBDEI were ≤13% on the medium trees and ≤2% on the large trees (hence decreasing with the data set size, as expected), and well centered around zero (i.e., unbiased), as shown in Fig.",FALSE,FALSE,"(28, 34, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"For the medium data set BEAST2 (in orange), PhyloDeep (in green) and our estimator (PyBDEI, in blue) are compared.",FALSE,FALSE,"(84, 90, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"We show the swarmplots (colored by method) of relative errors for each test tree/forest and parameter, which are measured as the normalized distance between the median a posteriori estimate by BEAST2 or a point estimate by PhyloDeep/PyBDEI and the real value.",FALSE,FALSE,"(233, 239, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"For the infectious time, 1/ψ, PyBDEI was at least as accurate as PhyloDeep and more accurate than BEAST2 (P-value <0.05).",FALSE,FALSE,"(30, 36, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"For the incubation period, 1/μ, PyBDEI was more accurate than both other methods (see Fig.",FALSE,FALSE,"(32, 38, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"On the large data set BEAST2 was inapplicable due to computation times (57 CPU hours were already required for each medium-sized tree, on average), while PyBDEI was more accurate than PhyloDeep, both using full trees and the forests of the first type (i.e., where all the trees started at the same time, P-value <0.01 for all the parameters, see Fig.",FALSE,FALSE,"(154, 160, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"On the forests of the second type (i.e., trees starting at different times) PyBDEI’s performance was comparable to the one of PhyloDeep for all the parameters.",FALSE,FALSE,"(76, 82, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"While the mean relative errors were low (<10%), PyBDEI performed worse (P-value <0.01) on forests of type 2 than on full trees or forests of type 1 for the infectious period and incubation time.",FALSE,FALSE,"(48, 54, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"PyBDEI performed well on these two trees: real parameters were within estimated confidence intervals, relative errors for Re<15%, relative errors for incubation period and infectious time <10%.",FALSE,FALSE,"(0, 6, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"PyBDEI estimates had a higher or equal likelihood than any other method and real values for all the trees of both data sets, suggesting that PyBDEI reaches the global optimum of the likelihood function.",FALSE,FALSE,"(0, 6, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"On the medium dataset, PyBDEI estimates had an equal likelihood to the ones of BEAST2 for 85% of trees, and a higher likelihood for the other 15% of trees.",FALSE,FALSE,"(23, 29, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"Comparing to PhyloDeep, PyBDEI estimates had an equal likelihood for 48% of trees, and a higher likelihood for the other 52% of trees.",FALSE,FALSE,"(24, 30, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"For example, 0.847 in the row “BEAST2 =” and the column “PyBDEI medium” means that the estimates of BEAST2 had an equal likelihood to those of PyBDEI on 84.7% of trees of the medium data set.",FALSE,FALSE,"(57, 63, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"In terms of time, on the medium data set PyBDEI needed on average 4 seconds per tree on 1 CPU, and converged in 864 iterations (including CI calculation).",FALSE,FALSE,"(41, 47, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"These times cannot be directly compared to BEAST2 times, as BEAST2 performs a Markov Chain Monte Carlo (MCMC) parameter space exploration instead of looking for the optimum (as PyBDEI does), hence requires many more steps: for 106 MCMC steps it took on average 57 CPU hours.",FALSE,FALSE,"(177, 183, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"The average time of PyBDEI convergence on the large data set was 2 min 28 s on 1 CPU, and required 960 iterations.",FALSE,FALSE,"(20, 26, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"However, to assess PyBDEI performance with other parameters fixed, we estimated parameters for trees in the large data set under three additional settings: with (1) μ, (2) λ, or (3) ψ fixed to its real value.",FALSE,FALSE,"(19, 25, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"Using PyBDEI, we analysed the 2014 Ebola epidemic in Sierra-Leone (SLE).",FALSE,FALSE,"(6, 12, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"This application shows the advantages of PyBDEI not only in terms of calculation times, but also in terms of flexibility of input settings (extracting information from multiple trees).",FALSE,FALSE,"(41, 47, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"Our parameter estimator, PyBDEI, drastically increases parameter optimization performance, accuracy and speed with respect to previously available estimators.",FALSE,FALSE,"(25, 31, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"PyBDEI is applicable to very large data sets (2 min on a 10000-tip tree), making parameter and CI estimation instantaneous with respect to phylogenetic tree reconstruction times (hours or even days).",FALSE,FALSE,"(0, 6, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"With rapidly growing genome sequence data, castor and PyBDEI open way to fast and accurate parameter estimations for ecology and epidemiology.",FALSE,FALSE,"(54, 60, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"To facilitate the use of our estimator in Python and perform additional validation of input trees, we wrapped the core estimator into a Python 3 library PyBDEI.",FALSE,FALSE,"(153, 159, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10924745,"PyBDEI uses ETE 3 framework for tree manipulation (Huerta-Cepas et al., 2016) and NumPy package for array operations (Harris et al., 2020).",FALSE,FALSE,"(0, 6, 'PyBDEI', 'pybdei')",Phylogenetics
PMC10885866,"Because of fewer false positives and the greatest AUC, AntiBP3 is able to attain a balanced sensitivity and specificity.",FALSE,FALSE,"(55, 62, 'AntiBP3', 'antibp3')",
PMC10885866,"We integrated our best-performing models in AntiBP3, a user-friendly online server (https://webs.iiitd.edu.in/raghava/antibp3/ (accessed on 20 November 2023)) that predicts antibacterial peptides for different groups of bacteria based on sequence information for each entry.",FALSE,FALSE,"(44, 51, 'AntiBP3', 'antibp3')",
PMC10885866,The datasets constructed for this study can be retrieved from the ‘AntiBP3′ web server at https://webs.iiitd.edu.in/raghava/antibp3/downloads.php (accessed on 20 November 2023).,FALSE,FALSE,"(67, 74, 'AntiBP3', 'antibp3')",
PMC10885866,The source code for this study is freely accessible on GitHub and can be found at https://github.com/raghavagps/AntiBP3 (accessed on 20 November 2023).,FALSE,FALSE,"(112, 119, 'AntiBP3', 'antibp3')",
PMC10885866,"A flow diagram showing the process of creating AntiBP3 datasets for gram-positive, gram-negative, and gram-variable bacteria.",FALSE,FALSE,"(47, 54, 'AntiBP3', 'antibp3')",
PMC10885866,"The comparison of existing prediction tools with AntiBP3 on the validation dataset to discriminate the three groups of ABPs, i.e., gram-positive, negative and variable.",FALSE,FALSE,"(49, 56, 'AntiBP3', 'antibp3')",
PMC10877048,Our method—MRSLpred—outperforms the existing state-of-the-art classifier in terms of performance and computation efficiency.,FALSE,FALSE,"(11, 19, 'MRSLpred', 'mrslpred')",
PMC10877048,"This method, named MRSLpred, is based on machine learning and uses the composition features of mRNA sequences for prediction.",FALSE,FALSE,"(19, 27, 'MRSLpred', 'mrslpred')",
PMC10877048,"Importantly, MRSLpred can be implemented at a genome scale as its computational resource requirements are minimal.",FALSE,FALSE,"(13, 21, 'MRSLpred', 'mrslpred')",
PMC10877048,Outline of the methodology followed by MRSLpred.,FALSE,FALSE,"(39, 47, 'MRSLpred', 'mrslpred')",
PMC10877048,"The performance of both DM3Loc and MRSLpred was evaluated on the validation dataset, and it was observed that DM3Loc performs better than MRSLpred in terms of AUROC and MCC.",FALSE,FALSE,"(35, 43, 'MRSLpred', 'mrslpred')",
PMC10877048,Both MRSLpred and DM3Loc have been designed as multi-label classifiers where more than one location can be assigned to a single sequence.,FALSE,FALSE,"(5, 13, 'MRSLpred', 'mrslpred')",
PMC10877048,"On the other hand, other existing methods perform multiclass classification, assigning only one location to a single sequence, and comparing MRSLpred/DM3Loc with these tools would be unfair to them.",FALSE,FALSE,"(141, 149, 'MRSLpred', 'mrslpred')",
PMC10877048,"However, for the sake of comparison, we evaluated the performance of all these tools on the validation dataset used in MRSLpred.",FALSE,FALSE,"(119, 127, 'MRSLpred', 'mrslpred')",
PMC10877048,The detailed comparison of MRSLpred with DM3Loc and all other tools which do not support multi-label classification is provided in Table 5.,FALSE,FALSE,"(27, 35, 'MRSLpred', 'mrslpred')",
PMC10877048,Benchmarking of MRSLpred with existing prediction tools on the validation dataset used in MRSLpred.,FALSE,FALSE,"(16, 24, 'MRSLpred', 'mrslpred')",
PMC10877048,Another significant advantage of MRSLpred is that it is computationally very efficient and consumes very less time.,FALSE,FALSE,"(33, 41, 'MRSLpred', 'mrslpred')",
PMC10877048,The detailed comparison of MRSLpred and DM3Loc based on the time taken to generate predictions is provided in Table 6.,FALSE,FALSE,"(27, 35, 'MRSLpred', 'mrslpred')",
PMC10877048,Comparison of MRSLpred with DM3Loc based on the time taken for similar datasets.,FALSE,FALSE,"(14, 22, 'MRSLpred', 'mrslpred')",
PMC10877048,MRSLpred achieves an AUROC between 0.708 and 0.816 (average: 0.742) and an MCC between 0.073 and 0.319 (average: 0.232) on the validation dataset.,FALSE,FALSE,"(0, 8, 'MRSLpred', 'mrslpred')",
PMC10877048,"MRSLpred uses a much simpler approach, combining an XGBoost model with a motif-based module and using compositional features for the model.",FALSE,FALSE,"(0, 8, 'MRSLpred', 'mrslpred')",
PMC10877048,"The time taken by MRSLpred for predicting the location of 500 mRNA sequences is less than 1 min, whereas for the same dataset, DM3Loc takes approximately 32 min.",FALSE,FALSE,"(18, 26, 'MRSLpred', 'mrslpred')",
PMC10877048,"MRSLpred is available online at https://webs.iiitd.edu.in/raghava/mrslpred/, and its standalone can be downloaded from https://webs.iiitd.edu.in/raghava/mrslpred/standalone.php.",FALSE,FALSE,"(0, 8, 'MRSLpred', 'mrslpred')",
PMC11177086,"The authors have developed an in-silico tool, named PhageTB, for the prediction of phage-bacteria interactions with high accuracy.",FALSE,FALSE,"(52, 59, 'PhageTB', 'cellppd-mod')",
PMC11177086,We believe that PhageTB will be an effective method for prediction of phage-based therapy against bacterial infections.,FALSE,FALSE,"(16, 23, 'PhageTB', 'cellppd-mod')",
PMC11253343,"We introduce the open-source PyChelator web application and the Python-based Google Colaboratory notebook, PyChelator Colab.",FALSE,FALSE,"(29, 39, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,No notable differences were observed compared to the results obtained from the PyChelator web application.,FALSE,FALSE,"(79, 89, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,PyChelator is a user-friendly metal and chelator calculator that provides a platform for further development.,FALSE,FALSE,"(0, 10, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"It is provided as an interactive web application, freely available for use at https://amrutelab.github.io/PyChelator, and as a Python-based Google Colaboratory notebook at https://colab.research.google.com/github/AmruteLab/PyChelator/blob/main/PyChelator_Colab.ipynb.",FALSE,FALSE,"(106, 116, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"To address these needs and concerns, we developed PyChelator web application (https://amrutelab.github.io/PyChelator/), an open source program, based on the well-established and widely used Maxchelator framework.",FALSE,FALSE,"(50, 60, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,PyChelator offers enhanced user experience and customization options.,FALSE,FALSE,"(0, 10, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,The Python code in a Google Colaboratory notebook makes the PyChelator functionalities readily available to the Python-using scientific community for further development.,FALSE,FALSE,"(60, 70, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,PyChelator web application uses JavaScript for calculations and utilizes HTML & CSS for the frontend interface.,FALSE,FALSE,"(0, 10, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,The graphical user interface (GUI) of the PyChelator web application is designed for simplicity of use and comprises three panels.,FALSE,FALSE,"(42, 52, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"An easy-to-follow tutorial of an example calculation and manual entry of constants are included inside PyChelator, and shown in Fig.",FALSE,FALSE,"(103, 113, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,1Example uses of PyChelator.,FALSE,FALSE,"(17, 27, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,Example uses of PyChelator.,FALSE,FALSE,"(16, 26, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"PyChelator facilitates the entry of smaller concentrations of chelators and metals through a dropdown menu, enabling entry of values from molar (M) to nanomolar range (M, mM, μM, and nM).",FALSE,FALSE,"(0, 10, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,A function to calculate the ionic equivalence inside PyChelator is also included.,FALSE,FALSE,"(53, 63, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"Additionally, PyChelator includes an option for the log-transformed values of the free metal concentrations (− log10[free]), corresponding to the pX values (for example pCa for free calcium).",FALSE,FALSE,"(14, 24, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"A screenshot of the PyChelator GUI, accompanied by annotations, is presented in Fig.",FALSE,FALSE,"(20, 30, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"2Screenshot of PyChelator graphical user interface (GUI), illustrating the intuitive layout and functionality.",FALSE,FALSE,"(15, 25, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"Screenshot of PyChelator graphical user interface (GUI), illustrating the intuitive layout and functionality.",FALSE,FALSE,"(14, 24, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,PyChelator is a single page application where users can switch constants by the use of a dropdown menu.,FALSE,FALSE,"(0, 10, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,3Comparison of PyChelator results obtained from different stability constants.,FALSE,FALSE,"(15, 25, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"A PyChelator offers the selection of stability constants from four sources, and allows the input of user-defined constants.",FALSE,FALSE,"(2, 12, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"B Calculations done in PyChelator using the four sets of stability constants, sourced from the National Institute of Standards and Technology ‘NIST’ [11], ‘SPECS’ by Fabiato [2], ‘Chelator’ by Schoenmakers et al.",FALSE,FALSE,"(23, 33, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"Notably, the high-precision calculations performed in PyChelator Colab employing the NIST constants and arbitrary precision of 50 decimals in calculations (PyNIST), were similar to those obtained from PyChelator web application using the same constants (NIST)",FALSE,FALSE,"(54, 64, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,Comparison of PyChelator results obtained from different stability constants.,FALSE,FALSE,"(14, 24, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,PyChelator further enhances user customization by allowing manual input of user-defined stability constants.,FALSE,FALSE,"(0, 10, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,This feature makes it possible to use PyChelator as “Any Metal Any Chelator Calculator”.,FALSE,FALSE,"(38, 48, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,Some commonly used metal-chelator pairs are included together with references under the “Stability Constants” folder in PyChelator Github repository.,FALSE,FALSE,"(120, 130, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,PyChelator Colab offers a cloud-based interactive Python environment that lets users write and execute code in their browsers.,FALSE,FALSE,"(0, 10, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"Unlike Flask and Django, which are designed to handle server-side operations and require managing server hosting and domain registration (which can be costly), PyChelator Colab and PyChelator web applications do not require server hosting.",FALSE,FALSE,"(160, 170, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"PyChelator Colab is also modified to use the built-in Python Decimal module, introducing user-defined precision in the calculations, which are otherwise limited by double precision in the floating-point arithmetic of Python and JavaScript.",FALSE,FALSE,"(0, 10, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"Nevertheless, the results obtained from the PyChelator web application, which utilizes JavaScript in calculations, compared to PyChelator Colab, did not show a notable difference (Fig.",FALSE,FALSE,"(44, 54, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,A general comparison of the features offered by PyChelator compared to other calculator software is given in Table 1.Fig.,FALSE,FALSE,"(48, 58, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,4PyChelator Colab GUI.,FALSE,FALSE,"(1, 11, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"A To run a calculation in PyChelator Colab, the user has to run the first code cell ""Constants"" which enables the dropdown for selection/entry of constants, followed by saving the options through clicking ""Save Values"".",FALSE,FALSE,"(26, 36, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"A field for decimal precision is included to specify the level of precision in decimal places, employing arbitrary precision provided by the Decimals module of PythonTable 1Comparison of PyChelator to other softwareProgramming languageConstantsInputOutputRefsPyChelator (2024)JavaScript, PythonNIST, Schoenmakers, Fabiato, Chelator, User-defined entryM, mM, μM, nMChoose parameters, Append, ExcelThis workMaxChelator (2010)JavaScriptNIST, Schoenmakers, Editable constants fileMOne at a time[6]Calcium (1993)N/AMartell and Smith, Editable constantsmMOne at a time[5]Chelator (1992)Turbo PascalSchoenmakers, Editable constants fileMOne at a time[3]SPECS (1988)FortranFabiato and Fabiato, Editable using WordStarMOne at a time[2]",FALSE,FALSE,"(187, 197, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,PyChelator Colab GUI.,FALSE,FALSE,"(0, 10, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,Comparison of PyChelator to other software,FALSE,FALSE,"(14, 24, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"PyChelator validates the input values for temperature (0–40 °C), ionic equivalence (0–500 mM), and pH (0–14).",FALSE,FALSE,"(0, 10, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,PyChelator was prepared to facilitate improvements in these calculations.,FALSE,FALSE,"(0, 10, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,"The PyChelator delivers a significant improvement over currently available web applications by offering a user-friendly metal chelator calculator that allows, among others, selection out of four sets of stability constants, input in smaller units, the option to specify user-defined constants, and the convenient ability to download results as a single Excel file.",FALSE,FALSE,"(4, 14, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,The Python-based PyChelator Colab offers easy customization in the modern programming language with user-defined precision in decimal calculations.,FALSE,FALSE,"(17, 27, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,Project name: PyChelator.,FALSE,FALSE,"(14, 24, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,Project home page: https://amrutelab.github.io/PyChelator/.,FALSE,FALSE,"(47, 57, 'PyChelator', 'pychelator')",Biochemistry
PMC11253343,Source code: https://github.com/AmruteLab/PyChelator.,FALSE,FALSE,"(42, 52, 'PyChelator', 'pychelator')",Biochemistry
PMC11223802,The RNAscape webserver produces visualizations that can preserve topological correspondence while remaining both visually intuitive and structurally insightful.,FALSE,FALSE,"(4, 12, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"RNAscape achieves this by designing a mathematical structural mapping algorithm which prioritizes the helical segments, reflecting their tertiary organization.",FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,RNAscape runs a plotting script that is designed to generate publication-quality images.,FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"RNAscape natively supports non-standard nucleotides, multiple base-pairing annotation styles and requires no programming experience.",FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"RNAscape can also be used to analyze RNA/DNA hybrid structures and DNA topologies, including G-quadruplexes.",FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,The RNAscape webserver allows users to customize visualizations through various settings as desired.,FALSE,FALSE,"(4, 12, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,RNAscape addresses and overcomes the outlined issues and limitations of existing approaches at several levels.,FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,The RNAscape algorithm includes a mapping process that conforms to the helical geometry of RNA structures.,FALSE,FALSE,"(4, 12, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"At the same time, RNAscape optimizes each layout to place non-helical segments of the structure without sacrificing tertiary interactions.",FALSE,FALSE,"(18, 26, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,RNAscape output for various structures from the PDB.,FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"The 3D structure at the top of each panel is from the PDB structure, with its corresponding RNAscape visualization shown below it.",FALSE,FALSE,"(92, 100, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,The RNAscape webserver (Figure 2) offers various customization options for its visualizations.,FALSE,FALSE,"(4, 12, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,RNAscape encourages users to iteratively refine an image.,FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"In addition, RNAscape allows the user to modify the calculated map.",FALSE,FALSE,"(13, 21, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"Upon completion, RNAscape visualizations can be exported to vector format (SVG) or image format (PNG), enabling further refinements by the user.",FALSE,FALSE,"(17, 25, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"Additionally, RNAscape can directly fetch structures (biological assembly 1) from the PDB (21) based on a given PDB ID.",FALSE,FALSE,"(14, 22, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,RNAscape overview.,FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,(A) RNAscape algorithm for geometric mapping.,FALSE,FALSE,"(4, 12, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,RNAscape builds a 2D ladder representation for helical segments that closely adheres to their principal component analysis (PCA) projection.,FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"(B) RNAscape webserver for plotting flexible, publication-quality visualizations.",FALSE,FALSE,"(4, 12, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,(C) RNAscape frontend for user interaction and customization.,FALSE,FALSE,"(4, 12, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"RNAscape allows users to upload a file or input a PDB ID for processing and to adjust various settings including base-pairing annotations, residue colors, nucleotide or text-label sizes and numbering schema.",FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,RNAscape also provides an associated documentation.,FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"After processing, RNAscape supports interaction with output layouts including zooming, rotating, panning, and modifying the map.",FALSE,FALSE,"(18, 26, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"RNAscape supports multiple base-pairing annotation conventions: Leontis-Westhof (LW) (16), Saenger (19), DSSR (Dissecting the Spatial Structure of RNA) (20) and a no-annotation option.",FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,The RNAscape webserver is a single-page web application.,FALSE,FALSE,"(4, 12, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"Upon upload, the structure file is sent via Hypertext Transfer Protocol Secure (HTTPS) to the RNAscape webserver where backend processing occurs.",FALSE,FALSE,"(94, 102, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,RNAscape algorithm.,FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"For each helical segment, RNAscape estimates the ladder axis by connecting the centroids of the starting and ending nucleotides with a line segment.",FALSE,FALSE,"(26, 34, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,The RNAscape backend utilizes the Matplotlib (24) and NetworkX (25) packages to plot visualizations.,FALSE,FALSE,"(4, 12, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,We present RNAscape output for various structures (Figures 1 and 4) from the PDB (21).,FALSE,FALSE,"(11, 19, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,RNAscape output preserves the L-shaped topology (as opposed to known ‘clover leaf’ shaped secondary structure (26) visualizations) and annotates non-standard bases and base-pairing geometries (critical in many RNA interactions (27)).,FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"RNAscape can also process unusual DNA structures, as shown by a single-stranded DNA with circular topology (PDB ID: 4NOE, Figure 1B).",FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,RNAscape output for large-size structures from the PDB.,FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"RNA loop modeling (28) for riboswitches is an important area of research, and RNAscape visualizations (e.g.",FALSE,FALSE,"(78, 86, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"The pistol ribozyme (PDB ID: 6R47, Figure 1D) and the Nicotinamide Adenine Dinucleotide-II (NAD-II) riboswitch (PDB ID: 8HBA, Figure 1G) illustrate how RNAscape places non-helical segments and can clearly depict their non-standard base pairs with helical segments.",FALSE,FALSE,"(152, 160, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,RNAscape natively supports multiple strands (e.g.,FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"RNAscape is also able to visualize G-quadruplexes (PDB ID: 2M18, Figure 1E).",FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"The RNAscape visualization (Figure 1J, Supplementary Figure S1) for the same reflects the high degree of conformational symmetry, based on structural coordinates of the PTC provided by Bose et al.",FALSE,FALSE,"(4, 12, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,RNAscape can run on relatively large structures (structures of up to 50 MB are processed by the webserver).,FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"stacked ladders, PDB ID: 7QDU, Figure 4D, 552 nucleotides), while RNAscape is able to reflect the 3D topology of these large RNA molecules.",FALSE,FALSE,"(66, 74, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"The RNAscape webserver (Figure 2C) displays three primary items: header, file upload, and documentation panels.",FALSE,FALSE,"(4, 12, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,Clicking the ‘Run’ button runs the RNAscape pipeline on the uploaded structure file or provided PDB ID (biological assembly 1).,FALSE,FALSE,"(35, 43, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"After running RNAscape for a structure, a user has the option to add a second structure for side-by-side viewing.",FALSE,FALSE,"(14, 22, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"The documentation panel enables easy navigation and provides a quick start guide, tips, and examples for using RNAscape.",FALSE,FALSE,"(111, 119, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,The user also has the option of downloading RNAscape mapped points in a numerical format (.npz) processable by the NumPy (32) library.,FALSE,FALSE,"(44, 52, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"RNAscape offers three base-pairing annotation styles: LW (16,33), DSSR (20) and Saenger (19).",FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,RNAscape always denotes local strand orientation by the backbone arrows (Figure 1).,FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"Through the number settings, a user instructs RNAscape to label residue numbers in the numbering schema defined by the structure file.",FALSE,FALSE,"(46, 54, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"Furthermore, RNAscape provides a functionality to modify calculated maps.",FALSE,FALSE,"(13, 21, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"The RNAscape webserver produces customizable, publication-quality visualizations of nucleic acid tertiary structure.",FALSE,FALSE,"(4, 12, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"RNAscape significantly deviates from any existing method in terms of its output quality, usability, and layout algorithm (Supplementary Table S1, Supplementary Figures S1 and S3).",FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,"Users can refine visualizations on the webserver, and RNAscape also supports non-standard nucleotides and various base-pairing annotations.",FALSE,FALSE,"(54, 62, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,The RNAscape webserver allows a maximum file size of 50 MB.,FALSE,FALSE,"(4, 12, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,We provide the RNAscape implementation via GitHub (see Data Availability) for those inclined to try the pipeline locally on even larger structures.,FALSE,FALSE,"(15, 23, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,RNAscape is freely available for all users at https://rnascape.usc.edu/.,FALSE,FALSE,"(0, 8, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11223802,The backend implementation is also available on GitHub at https://github.com/timkartar/RNAscape and preserved through figshare at https://doi.org/10.6084/m9.figshare.25201889.,FALSE,FALSE,"(87, 95, 'RNAscape', 'rnascape')","RNA, Nucleic acid structure analysis, Mathematics, Imaging"
PMC11018665,"The objectives of our study were to construct a global expression atlas for potatoes using publicly available transcriptome datasets, identify housekeeping and tissue-specific genes, construct a global co-expression network and identify co-expression clusters, investigate the transcriptional complexity of genes involved in various essential biological processes related to agronomic traits, and provide a web server (StCoExpNet) to easily access the newly constructed expression atlas and co-expression network to investigate the expression and co-expression of genes of interest.",FALSE,FALSE,"(419, 429, 'StCoExpNet', 'stcoexpnet')","Transcriptomics, RNA-Seq, Genotype and phenotype, Gene transcripts, Mapping"
PMC11018665,"The dataset compiled here constitutes a new resource (StCoExpNet), which can be accessed at https://stcoexpnet.julius-kuehn.de.",FALSE,FALSE,"(54, 64, 'StCoExpNet', 'stcoexpnet')","Transcriptomics, RNA-Seq, Genotype and phenotype, Gene transcripts, Mapping"
PMC11018665,The data presented above are easily accessible by researchers to explore the expression atlas of 2299 transcriptome samples and the co-expression network interactively via a web server called StCoExpNet.,FALSE,FALSE,"(192, 202, 'StCoExpNet', 'stcoexpnet')","Transcriptomics, RNA-Seq, Genotype and phenotype, Gene transcripts, Mapping"
PMC11018665,A web server StCoExpNet has been created for researchers to explore the constructed potato expression atlas and gene co-expression network by adopting the CoNekT framework.,FALSE,FALSE,"(13, 23, 'StCoExpNet', 'stcoexpnet')","Transcriptomics, RNA-Seq, Genotype and phenotype, Gene transcripts, Mapping"
PMC11069105,"We present shinyseg, a comprehensive web application for clinical cosegregation analysis.",FALSE,FALSE,"(11, 19, 'shinyseg', 'shinyseg')","Public health and epidemiology, Genetics, Human biology"
PMC11069105,"The shinyseg app is freely available at https://chrcarrizosa.shinyapps.io/shinyseg, with documentation and complete R source code on https://chrcarrizosa.github.io/shinyseg and https://github.com/chrcarrizosa/shinyseg.",FALSE,FALSE,"(4, 12, 'shinyseg', 'shinyseg')","Public health and epidemiology, Genetics, Human biology"
PMC11069105,"To address these shortcomings, we introduce the web application shinyseg for clinical cosegregation analysis.",FALSE,FALSE,"(64, 72, 'shinyseg', 'shinyseg')","Public health and epidemiology, Genetics, Human biology"
PMC11069105,shinyseg is an R-based tool built with Shiny (Chang et al.,FALSE,FALSE,"(0, 8, 'shinyseg', 'shinyseg')","Public health and epidemiology, Genetics, Human biology"
PMC11069105,"With all necessary information in place, shinyseg computes the full-likelihood Bayes factor (FLB) for the variant's pathogenicity (Thompson et al.",FALSE,FALSE,"(41, 49, 'shinyseg', 'shinyseg')","Public health and epidemiology, Genetics, Human biology"
PMC11069105,We showcase shinyseg by analyzing the pedigree in Fig.,FALSE,FALSE,"(12, 20, 'shinyseg', 'shinyseg')","Public health and epidemiology, Genetics, Human biology"
PMC11069105,"Instead, we use the relative risk mode of shinyseg, as it streamlines this process while ensuring transparent assumptions.",FALSE,FALSE,"(42, 50, 'shinyseg', 'shinyseg')","Public health and epidemiology, Genetics, Human biology"
PMC11069105,"We present shinyseg, an app for clinical cosegregation analysis that emphasizes flexible penetrance specification and sensitivity analysis.",FALSE,FALSE,"(11, 19, 'shinyseg', 'shinyseg')","Public health and epidemiology, Genetics, Human biology"
PMC11069105,"shinyseg is freely available at https://chrcarrizosa.shinyapps.io/shinyseg, and runs in all common browsers.",FALSE,FALSE,"(0, 8, 'shinyseg', 'shinyseg')","Public health and epidemiology, Genetics, Human biology"
PMC11069105,Documentation and complete source code can be found on https://chrcarrizosa.github.io/shinyseg and https://github.com/chrcarrizosa/shinyseg.,FALSE,FALSE,"(86, 94, 'shinyseg', 'shinyseg')","Public health and epidemiology, Genetics, Human biology"
PMC11069105,All code and data are accessible at https://github.com/chrcarrizosa/shinyseg.,FALSE,FALSE,"(68, 76, 'shinyseg', 'shinyseg')","Public health and epidemiology, Genetics, Human biology"
PMC10988918,"To streamline the gating process, we developed CITEViz which allows users to interactively gate cells in Seurat-processed CITE-Seq data.",TRUE,FALSE,"(47, 54, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,CITEViz can also visualize basic quality control (QC) metrics allowing for a rapid and holistic evaluation of CITE-Seq data.,TRUE,FALSE,"(0, 7, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"We applied CITEViz to a peripheral blood mononuclear cell CITE-Seq dataset and gated for several major blood cell populations (CD14 monocytes, CD4 T cells, CD8 T cells, NK cells, B cells, and platelets) using canonical surface protein markers.",TRUE,FALSE,"(11, 18, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,The visualization features of CITEViz were used to investigate cellular heterogeneity in CD14 and CD16-expressing monocytes and to detect differential numbers of detected antibodies per patient donor.,TRUE,FALSE,"(30, 37, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,These results highlight the utility of CITEViz to enable the robust classification of single cell populations.,TRUE,FALSE,"(39, 46, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,CITEViz is an R-Shiny app that standardizes the gating workflow in CITE-Seq data for efficient classification of cell populations.,TRUE,FALSE,"(0, 7, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,The user interface and internal workflow of CITEViz uniquely work together to produce an organized workflow and sensible data structures for easy data retrieval.,TRUE,FALSE,"(44, 51, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"In conclusion, CITEViz streamlines the flow cytometry gating workflow in CITE-Seq data to help facilitate novel hypothesis generation.",TRUE,FALSE,"(15, 22, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"To efficiently gate cell populations in CITE-Seq data, we developed CITEViz.",TRUE,FALSE,"(68, 75, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"By using the R-Shiny platform, CITEViz allows users to interactively subset cell populations of interest using surface proteins and see those cells highlighted in latent space (e.g.",TRUE,FALSE,"(31, 38, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,A secondary function of CITEViz is to provide basic multi-omic single/co-expression feature plots and quality control figures to allow biologists to quickly and holistically assess CITE-Seq data.,TRUE,FALSE,"(24, 31, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"In conclusion, CITEViz (1) streamlines the gating workflow in CITE-Seq data to identify cell populations and (2) facilitates basic visualization of multi-omic, single-cell sequencing data.",TRUE,FALSE,"(15, 22, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,A core design element of CITEViz is the Gate class—a custom S4 class written in base R (Fig.,TRUE,FALSE,"(25, 32, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,The custom Gate class in CITEViz is necessary to store detailed gating information in an organized data structure.Fig.,TRUE,FALSE,"(25, 32, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,1Implementation of CITEViz.,TRUE,FALSE,"(19, 26, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,B Back-end of CITEViz.,TRUE,FALSE,"(14, 21, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"Unlike other packages, this process can be repeated to the nth degree in CITEViz.",TRUE,FALSE,"(73, 80, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,C Screenshot of the gating page in CITEViz with an example PBMC CITE-seq dataset [5],TRUE,FALSE,"(35, 42, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,Implementation of CITEViz.,TRUE,FALSE,"(18, 25, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,The typical workflow of CITEViz can be distilled down to 4 steps.,TRUE,FALSE,"(24, 31, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"In summary, the procedures to gate cells in CITEViz are to plot cell surface markers, select the cells, input a text label, and define the gate via the Gate button.",TRUE,FALSE,"(44, 51, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,CITEViz uniquely supports a back-gate function.,TRUE,FALSE,"(0, 7, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,The back-gate function of CITEViz allows users to interactively explore gates and feature combinations that define a specific cell cluster.,TRUE,FALSE,"(26, 33, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"At a minimum, CITEViz requires a Seurat object with a normalized ADT counts matrix.",TRUE,FALSE,"(14, 21, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"The two types of input data currently supported by CITEViz are (1) an R Data Serialized (RDS) file containing a Seurat object, or (2) an RDS file with a SingleCellExperiment object derived from the as.SingleCellExperiment() function from the Seurat library.",TRUE,FALSE,"(51, 58, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"Furthermore, CITEViz can be adapted to accommodate more data structures in future updates (refer to Limitations sub-section in Discussions).",TRUE,FALSE,"(13, 20, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"CITEViz provides basic visualization of quality control (QC) metrics, single-feature, and feature co-expression plots.",TRUE,FALSE,"(0, 7, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,CITEViz provides basic visualization of QC metrics and single/multi-omic feature expression plots in addition to its primary function as a gating workflow in CITE-Seq data.,TRUE,FALSE,"(0, 7, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"To demonstrate the utility of this program, CITEViz was used to gate the major cell populations in a PBMC CITE-Seq dataset [5].",TRUE,FALSE,"(44, 51, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"Several gating schemes were used to show the utility of CITEViz and to identify CD14 monocytes, CD4 T-cells, CD8 T-cells, Natural Killer (NK) cells, B-cells, and platelets.",TRUE,FALSE,"(56, 63, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"To reduce overplotting, the dataset was randomly down-sampled to 10 K cells and then uploaded to CITEViz.",TRUE,FALSE,"(97, 104, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,2CITEViz analysis of PBMC CITE-Seq data.,TRUE,FALSE,"(1, 8, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,CITEViz analysis of PBMC CITE-Seq data.,TRUE,FALSE,"(0, 7, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"Within the back-gate tab of CITEViz, NK cells were selected in the latent space according to prior annotations [5].",TRUE,FALSE,"(28, 35, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,The secondary function of CITEViz is to visualize commonly generated plots in multi-omic CITE-Seq data like single/co-expression plots and QC metrics.,TRUE,FALSE,"(26, 33, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"For example, we used CITEViz to generate a feature plot, revealing a distinctly high expression in the CD8 T-cell population (Fig.",TRUE,FALSE,"(21, 28, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,An example of a QC metric that can be assessed with CITEViz is the number of unique antibodies detected.,TRUE,FALSE,"(52, 59, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"CITEViz can split this QC metric by individual patient donors, which clearly displayed a significant difference between patients 1–4 and patients 5–8 with a padj of 0 (Tukey HSD) (Fig.",TRUE,FALSE,"(0, 7, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"The application of CITEViz to a PBMC CITE-Seq dataset [5] led to the identification of 6 major cell populations (CD4 T cells, CD14 monocytes, CD8 T cells, NK cells, B cells, platelets) using a mix of one- or two-step gates and back-gates (Fig.",TRUE,FALSE,"(19, 26, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"By plotting the number of detected antibodies per sample, CITEViz displayed a significant difference between patients 1–4 and 5–8.",TRUE,FALSE,"(58, 65, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,These results are in line with prior analyses and suggest that the flow cytometry-like gating workflow in CITEViz provided an alternative approach to easily classify clusters in CITE-Seq data [5].,TRUE,FALSE,"(106, 113, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"is most functionally similar to CITEViz, it requires a custom tab-separated input file and is limited to exporting the cell names in the last gated population [12].",TRUE,FALSE,"(32, 39, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"In contrast, CITEViz enhances reproducibility by including important gating metadata such as surface protein markers, gate coordinates, and previous filtration steps.Table 1CITEViz compared to Single-Cell Virtual Cytometer, iSEE, and SeuratProgramsGatingBack-GatingMulti-Omic Feature/QC VisualizationPlatformCITEViz✓✓✓R-ShinySingle-Cell Virtual Cytometer [12]✓––Cascading Style Sheet & JavaScriptiSEE [13]–––R-ShinySeurat [5]✓–✓R & R-Shiny",TRUE,FALSE,"(13, 20, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"CITEViz compared to Single-Cell Virtual Cytometer, iSEE, and Seurat",TRUE,FALSE,"(0, 7, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"Unlike other programs, CITEViz fills an unmet need by (1) implementing a seamless flow cytometry gating workflow and (2) generating basic multi-omic plots in Seurat-processed CITE-Seq data.",TRUE,FALSE,"(23, 30, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"CITEViz improves upon Seurat by displaying relevant parameters and plots in the R-Shiny interface, providing an efficient user experience with continuous visual feedback.",TRUE,FALSE,"(0, 7, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,A limitation of CITEViz pertains to data sparsity where gating cells by gene expression (RNA) results in a high rate of data dropout [14].,TRUE,FALSE,"(16, 23, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"We speculate the development of better scRNA sequencing assays (and their multi-omic variants) will better resolve heterogeneous cell populations in the future, so CITEViz was built to gate cells based on any assays (RNA, ADT, SCT) and features to accommodate future improvements in sequencing technology.",TRUE,FALSE,"(164, 171, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"In addition to sequencing assays, the ever-shifting landscape of bioinformatic file formats can affect compatibility with CITEViz in the future.",TRUE,FALSE,"(122, 129, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"Currently, CITEViz accepts Seurat and BioConductor SingleCellExperiment objects.",TRUE,FALSE,"(11, 18, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"To account for the imminent introduction of new file formats or data structures, CITEViz was modularly built to accept various input file types.",TRUE,FALSE,"(81, 88, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,The modular design of CITEViz means it can be adequately maintained to accept new file formats and data structures in the future.,TRUE,FALSE,"(22, 29, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,CITEViz is intended to be used by biologists familiar with flow cytometry and who can either (1) perform basic single-cell analysis or (2) collaborate in a team with a computational scientists.,TRUE,FALSE,"(0, 7, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"The input data format for CITEViz is a pre-processed Seurat object, which requires a basic level of coding skills in R and the ability to follow public Seurat vignettes.",TRUE,FALSE,"(26, 33, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"Since the essential feature of CITEViz is its iterative filtering process, it is not intended for any data preprocessing or normalization.",TRUE,FALSE,"(31, 38, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"In our experience, we found CITEViz to be a uniquely collaborative tool that leverages the strengths of both bench and computational scientists to explore and analyze data together.",TRUE,FALSE,"(28, 35, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,CITEViz is an R-Shiny package that facilitates a seamless gating workflow in Seurat-processed CITE-Seq data.,TRUE,FALSE,"(0, 7, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,"CITEViz was ultimately designed to facilitate novel hypothesis generation, and is available to download on GitHub [15].",TRUE,FALSE,"(0, 7, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,Project name: CITEViz,TRUE,FALSE,"(14, 21, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,Project home page: https://github.com/maxsonBraunLab/CITEViz,TRUE,FALSE,"(53, 60, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,TPB identified a need for a program like CITEViz.,TRUE,FALSE,"(41, 48, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,SAC and BMC tested CITEViz prototypes.,TRUE,FALSE,"(19, 26, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC10988918,The CITEViz documentation website can be accessed here https://maxsonbraunlab.github.io/CITEViz/.,TRUE,FALSE,"(4, 11, 'CITEViz', 'citeviz')","Cytometry, Transcriptomics, Workflows, RNA-Seq, Cell biology"
PMC11056015,"Source codes for the CPPLS_MLP R, python packages and the related scripts are available at ‘CPPLS_MLP Github [https://github.com/wuzhenao/CPPLS-MLP]’.",FALSE,FALSE,"(21, 30, 'CPPLS_MLP', 'cppls_mlp')","Transcriptomics, Cell biology, Gene regulation, Genotype and phenotype, Molecular interactions, pathways and networks"
PMC11056015,"We developed an innovative model integrating neural networks and multiple linear regression functions, called CPPLS_MLP.",FALSE,FALSE,"(110, 119, 'CPPLS_MLP', 'cppls_mlp')","Transcriptomics, Cell biology, Gene regulation, Genotype and phenotype, Molecular interactions, pathways and networks"
PMC11056015,"CPPLS_MLP exhibits excellent accuracy and robustness, making it suitable for various experimental designs, single-cell sequencing presumably derived from different organs and cell communication of ST data.",FALSE,FALSE,"(0, 9, 'CPPLS_MLP', 'cppls_mlp')","Transcriptomics, Cell biology, Gene regulation, Genotype and phenotype, Molecular interactions, pathways and networks"
PMC11056015,CPPLS_MLP is provided in an open-source format and can be directly used to predict cell communication in different tissues and classify genes in their communication networks.,FALSE,FALSE,"(0, 9, 'CPPLS_MLP', 'cppls_mlp')","Transcriptomics, Cell biology, Gene regulation, Genotype and phenotype, Molecular interactions, pathways and networks"
PMC11056015,"Source codes for the CPPLS_MLP R, python packages and the related scripts are available at “CPPLS_MLP Github [https://github.com/wuzhenao/CPPLS-MLP]”.",FALSE,FALSE,"(21, 30, 'CPPLS_MLP', 'cppls_mlp')","Transcriptomics, Cell biology, Gene regulation, Genotype and phenotype, Molecular interactions, pathways and networks"
PMC11001601,"To facilitate such analysis, we developed Cat-E (Cancer Target Explorer), a novel R/Shiny web tool designed for comprehensive analysis with evaluation according to cancer-related omics data.",FALSE,FALSE,"(42, 47, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Cat-E is accessible at https://cat-e.bioinfo-wuerz.eu/.,FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Cat-E compiles information on oncolytic viruses, cell lines, gene markers, and clinical studies by integrating molecular datasets from key databases such as OvirusTB, TCGA, DrugBANK, and PubChem.",FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Cancer target evaluation by Cat-E is demonstrated here on lung adenocarcinoma (LUAD) datasets.,FALSE,FALSE,"(28, 33, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"By offering a user-friendly interface and detailed user manual, Cat-E eliminates the need for advanced computational expertise, making it accessible to experimental biologists, undergraduate and graduate students, and oncology clinicians.",FALSE,FALSE,"(64, 69, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,The challenge uniquely answered by Cat-E is to evaluate molecular targets and innovative protein targeting strategies in the light of the massive volume of available omics data.,FALSE,FALSE,"(35, 40, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"For ease of use, Cat-E was developed as a one-stop R/Shiny application integrating routines for diverse omics data and features, including expression and protein structure, for rapid cancer drug target evaluation.",FALSE,FALSE,"(17, 22, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Our new, interactive web tool, Cancer Target Explorer (Cat-E), integrates published databases, datasets, and multiple analyses in a unique framework and toolkit, allowing evaluation of potential cancer-drug targets in the light of transcriptome and proteome data; this includes pathway analysis, metabolic flux analysis, immune signature analysis, survival analysis, and single nucleotide variation analysis.",FALSE,FALSE,"(55, 60, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,We designed Cat-E to facilitate research of new cancer targets and protein structures as well as new cancer targeting strategies related to cancer pathways and weak immune responses.,FALSE,FALSE,"(12, 17, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"We are confident that Cat-E is a welcome tool for evaluating various anti-cancer targets (mainly proteins, and with suitable omics data, also genes and RNAs) in different types of cancer including evaluation in the light of prognostic markers.",FALSE,FALSE,"(22, 27, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Cat-E was implemented using Shiny package of the R programming language (version 4.2.3), and MariaDB (https://mariadb.org).",FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,1Schematic representation of Cat-E web tool analyses workflow.,FALSE,FALSE,"(29, 34, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Cat-E implements nine functional analyses related to cancer and oncolytic viruses.,FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Schematic representation of Cat-E web tool analyses workflow.,FALSE,FALSE,"(28, 33, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"The following oncolytic viruses are available for analysis in Cat-E: Adenovirus, Herpes simplex virus, Measles virus, Canine parvovirus, Vaccinia virus, Alphavirus, Reovirus, Avian influenza A virus, Sindbis virus, Vesicular stomatitis virus, Parvovirus, Newcastle disease virus, Enterovirus, Respiratory syncytial virus, Mumps virus, Measles virus, Tanapoxvirus, Poxvirus, Sendai virus, Semliki forest virus, Maraba virus, Myxoma virus, and Bovine herpesvirus.",FALSE,FALSE,"(62, 67, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"The following tumor types are included in Cat-E: Adrenocortical carcinoma (ACC), Bladder Urothelial Carcinoma (BLCA), Breast invasive carcinoma (BRCA), Cervical squamous cell carcinoma and endocervical adenocarcinoma (CESC), Cholangiocarcinoma (CHOL), Colon adenocarcinoma (COAD), Lymphoid Neoplasm Diffuse Large B-cell Lymphoma (DLBC), Esophageal carcinoma (ESCA), Glioblastoma multiforme (GBM), Head and Neck squamous cell carcinoma (HNSC), Kidney Chromophobe (KICH), Kidney renal clear cell carcinoma (KIRC), Kidney renal papillary cell carcinoma (KIRP), Acute Myeloid Leukemia (LAML), Brain Lower Grade Glioma (LGG), Liver hepatocellular carcinoma (LIHC), Lung adenocarcinoma (LUAD), Lung squamous cell carcinoma (LUSC), Mesothelioma (MESO), Ovarian serous cystadenocarcinoma (OV), Pancreatic adenocarcinoma (PAAD), Pheochromocytoma and Paraganglioma (PCPG), Prostate adenocarcinoma (PRAD), Rectum adenocarcinoma (READ), Sarcoma (SARC), Skin Cutaneous Melanoma (SKCM), Stomach adenocarcinoma (STAD), Testicular Germ Cell Tumors (TGCT), Thyroid carcinoma (THCA), Thymoma (THYM), Uterine Corpus Endometrial Carcinoma (UCEC), Uterine Carcinosarcoma (UCS), and Uveal Melanoma (UVM).",FALSE,FALSE,"(42, 47, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"To enhance the database embedded within Cat-E, we incorporated multiple data sources, including rPanglaoDB [20] for cell type information, DrugBANK [21] for drug descriptions, PubChem [22] for molecular details and drug structures, DGIdb [23] for drug-gene interactions, and STITCH [24] for drug-gene network information.",FALSE,FALSE,"(40, 45, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Cat-E provides a comprehensive approach to analyze cancer-related data, including gene expression, metabolic pathways, metabolic flux, GO and KEGG enrichment, survival, immune signature, single nucleotide variation, gene regulatory dynamics, and protein structure prediction (Fig.",FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Cat-E provides filtered outcomes derived from Differential Gene Expression (DGE) analysis, presenting refined DGE data alongside tailored parameters, including log-fold change (log2FC) thresholds, p-value thresholds, and options for selecting statistical methods such as limma or ANOVA.",FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Cat-E also enables retrieval of GEO data using GSE identifiers through the GEOquery package [30], allowing limma-based DGE analysis by selecting log2FC and p-value thresholds.",FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Cat-E enables metabolic pathway analysis either by selecting 33 different cancer types or by uploading other datasets.,FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Cat-E also allows modification of the protein-protein interactions (PPI) network and creation of the oncolytic virus models.,FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"The g3viz package [46] in Cat-E was employed to create lollipop diagrams, thereby enhancing interactivity and visualization of SNVs.",FALSE,FALSE,"(26, 31, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Jimena [47] was integrated into Cat-E, facilitating the simulation and analysis of dynamic gene regulatory networks.",FALSE,FALSE,"(32, 37, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"The database within Cat-E, comprising nearly 40,000 signaling networks obtained from OmnipathR [48], enables efficient gene searches and streamlines the creation of customized biological signaling pathways.",FALSE,FALSE,"(20, 25, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Through the combination of Cat-E and Jimena, the manipulation and simulation of these networks can be conducted, providing valuable insights into the regulatory mechanisms of cellular processes.",FALSE,FALSE,"(27, 32, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Integration of 3Dmol.js into Cat-E enabled the generation of three-dimensional protein structures utilizing Protein Data Bank (PDB) codes [52].,FALSE,FALSE,"(29, 34, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"This study introduces the Cat-E web tool for detailed analysis of gene expression, pathway enrichment, single nucleotide variations, survival patterns, immune signatures, metabolic flux, and structural characterization, particularly in cancer research.",FALSE,FALSE,"(26, 31, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Taken together, this complex approach improves our comprehension of cancer biology and highlights the potential of Cat-E as a powerful tool for cancer research and therapeutic advancement.",FALSE,FALSE,"(115, 120, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,We demonstrate the functionality of Cat-E using three distinct lung adenocarcinoma (LUAD) datasets (Fig.,FALSE,FALSE,"(36, 41, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"2): DGE data available in Cat-E (use case 1), signaling network data from non-small cell lung carcinomas (NSCLC) [13] (use case 2), and glucogenesis pathway in cancer cells [53] (use case 3).Fig.",FALSE,FALSE,"(26, 31, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,2Application of Cat-E for cancer research.,FALSE,FALSE,"(16, 21, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Summary of analytical parameters and outputs for the LUAD case studies performed using Cat-E.,FALSE,FALSE,"(87, 92, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Potential targets for anti-cancer drug action are explored using the databases in Cat-E.Fig.,FALSE,FALSE,"(82, 87, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Application of Cat-E for cancer research.,FALSE,FALSE,"(15, 20, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Potential targets for anti-cancer drug action are explored using the databases in Cat-E.,FALSE,FALSE,"(82, 87, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"The first use case of Cat-E is the LUAD dataset, which was chosen from among the 33 different types of cancer tissues available in Cat-E.",FALSE,FALSE,"(22, 27, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"To demonstrate the comparison of DGE results, we used Cat-E to compare the LUAD data set with data from GEPIA2, using an interactive Venn diagram to analyze distinct and shared genes (n = 857) (as shown in Fig.",FALSE,FALSE,"(54, 59, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,A Venn diagram showing the comparison between the LUAD data within Cat-E (Selected_Data) and the DGE LUAD data in the GEPIA2 (User_Data); C.,FALSE,FALSE,"(67, 72, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Cat-E provides comprehensive features for conducting GO enrichment analysis.,FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Cat-E allows detailed analysis of SNVs, which are significant genetic alterations affecting cellular function and disease progression.",FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,The analysis of somatic mutation patterns in 616 patients with LUAD by Cat-E (Fig.,FALSE,FALSE,"(71, 76, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Cat-E provides advanced survival analysis tools for visualizing survival outcomes using clinical data stratified by tumour classifications.,FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Moreover, Cat-E facilitates the study of immunological signatures by arranging crucial immune genes in networked and tabular layouts.",FALSE,FALSE,"(10, 15, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Cat-E systematically organized and illustrated basic immunological signatures (ImSig) and their relationships with various types of immune cells.,FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"The Cat-E framework incorporates the functionality for metabolic pathway analysis, enabling the identification of canonical metabolic pathways, with particular emphasis on those exhibiting an adjusted p-value of ≤ 0.05.",FALSE,FALSE,"(4, 9, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"As an illustrative example, we constructed a metabolic pathway network within Cat-E using LUAD data, focusing on the top 50 positively associated genes (see Fig.",FALSE,FALSE,"(78, 83, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Cat-E enabled the identification of active metabolic pathways in the LUAD data, as depicted in Fig.",FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,The XML and TXT formats of this model are uploaded to our repository in GitHub (https://github.com/salihoglu/Cat-E) to facilitate reproduction of this analysis.,FALSE,FALSE,"(109, 114, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Moreover, with Cat-E, users can generate the required files for the Jimena module [47].",FALSE,FALSE,"(15, 20, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Cat-E provides functionality for generating metabolic SBML files for users lacking pre-existing ones, using the integration between COBRA and d3flux tools (see Fig.",FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"6Interactive model of the pck2 (Q16822) protein in Cat-E, generated using AlphaFold for protein structure prediction.",FALSE,FALSE,"(51, 56, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Interactive model of the pck2 (Q16822) protein in Cat-E, generated using AlphaFold for protein structure prediction.",FALSE,FALSE,"(50, 55, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Through these functions within Cat-E, users can explore the predictive capabilities of AlphaFold by providing a UniProt ID and can adjust the structural characteristics.",FALSE,FALSE,"(31, 36, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"These include detailed analyses of cancer pathways and investigations into combination therapies, as evidenced by our previous studies on combinatorial-targeted treatment in the NSCLC with aggressive KRAS-Biomarker signatures [13], modeling of stem cell differentiation [54], and further usage of Cat-E tools for stratifying cancer types in colorectal cancer [55] or lung cancer [56].",FALSE,FALSE,"(297, 302, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"The comprehensive analyses conducted using Cat-E provide insights into the molecular landscape of cancer, offering researchers a wealth of data to explore potential therapeutic targets.",FALSE,FALSE,"(43, 48, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"The analysis shows that the upregulated muc16 gene is correlated with abagovomab, gefitinib, and bevacizumab drug treatments, as indicated in the gene-drug database integrated within Cat-E (Table 1).",FALSE,FALSE,"(183, 188, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"mutation or loss of p53), researchers can use Cat-E to create dynamic signaling networks based on the obtained data.",FALSE,FALSE,"(46, 51, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Cat-E offers a systematic dynamic framework for exploring and validating potential cancer targets, as a critical step in advancing precision medicine, by looking at individual tumor drivers, driver combinations, signature constellations and even evaluating the effect of specific mutations in the light of omics data to predict successful drug targeting or resistance.",FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"The Cat-E web tool was explicitly developed to examine proteins and protein cascades involved in cancer as promising drug targets against a background of alternative strategies (oncolytic viruses, immune strategies, cytostatics) and provides user-friendly access to crucial databases.",FALSE,FALSE,"(4, 9, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Cat-E offers a wide variety of analytical tools for cancer targeting-related studies, capable of conducting nine different types of analyses to meet the diverse requirements of the cancer research community, such as biologists, oncologists, and clinicians.",FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Cat-E can analyze TCGA-GTEx data for 33 different cancer types and perform DGE analysis on GEO data using the user's GSE ID, as well as presentation of immune gene signatures.",FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Cat-E offers datasets available through GEO via a user-friendly web tool tailored for individuals lacking advanced programming skills.,FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Moreover, Cat-E is a crucial tool for categorizing research on various cancer drug targets and targeting strategies, such as cytostatic drugs, CAR-T cells, cancer-targeting bispecific antibodies, and oncolytic virus methods, in light of all available omics data including clinical trial data, as available (e.g.",FALSE,FALSE,"(10, 15, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"This categorization is essential for evaluation of cancer targeting strategies, as Cat-E assists in navigating not only direct protein structures but also protein and pathway combinations as well as the extensive range of immunomodulatory approaches.",FALSE,FALSE,"(83, 88, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Case studies demonstrate that Cat-E enables rapid assessment of individual genes, their expression, and their significance in cancer.",FALSE,FALSE,"(30, 35, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,This gene was identified as a significant hotspot for mutations through SNV analysis using Cat-E.,FALSE,FALSE,"(91, 96, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"On a note of caution, Cat-E survival plots do not exhibit a straightforward and evident correlation between upregulation and survival.",FALSE,FALSE,"(22, 27, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Cat-E distinguishes itself by providing a wider variety of analysis tools and databases all in one place.,FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Cat-E explores targets and target pathways regarding oncolytic viruses, targeting cancer proteins and drug evaluation, combined effects of kinase inhibitors and tumor driver inhibitors, cytostatic therapy, immunomodulatory therapies like CAR-T cells, as well as interactive protein structure examination and drug targeting.",FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Cat-E does not function as a clinical study nurse tool nor is it intended for use in clinic or for monitoring or assessing patient therapy directly; instead, it concentrates on molecular interactions and mechanisms.",FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"The Cat-E platform will enhance its robust capabilities in the future by incorporating additional omics network analysis tools, embracing open-source development and integrating with advanced computational models such as large language models (LLMs).",FALSE,FALSE,"(4, 9, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,Cat-E is positioned to narrow the gap between bench research and clinical research by broad evaluation of targeting strategies and protein targets.,FALSE,FALSE,"(0, 5, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,The Cat-E (Cancer Target Explorer) web tool is a sophisticated platform that provides a multidimensional view of omics data to evaluate various cancer protein targeting strategies as well as immunological and oncolytic intervention strategies in cancer research.,FALSE,FALSE,"(4, 9, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"As shown for lung adenocarcinoma (LUAD) datasets, Cat-E demonstrates its utility in enabling users to explore genetic variations, identify diagnostic markers, and propose therapeutic targets across various cancer types.",FALSE,FALSE,"(50, 55, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"By simplifying access to as well as analysis of complex data sets, Cat-E enhances our understanding of cancer biology, including the evaluation of personalized cancer protein targeting strategies including combinations, immune modulation and oncolysis.",FALSE,FALSE,"(67, 72, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"RS programmed, tested, and implemented Cat-E, supervised by EB and TD.",FALSE,FALSE,"(39, 44, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11001601,"Specifically, all code and data can be accessed at https://github.com/salihoglu/Cat-E.",FALSE,FALSE,"(80, 85, 'Cat-E', 'cat_e')","Oncology, Protein interactions, Small molecules, Endocrinology and metabolism, Allergy, clinical immunology and immunotherapeutics"
PMC11008502,"In this paper, we present STRIDE-DB, a novel and unique platform to explore STR Instability and its Phenotypic Relevance, and a comprehensive database of STRs in the human genome.",FALSE,FALSE,"(26, 35, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,"STRIDE-DB, a user-friendly resource, plays a pivotal role in investigating the relationship between STR variation, instability and phenotype.",FALSE,FALSE,"(0, 9, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,STRIDE-DB has its broad applicability and significance in various research domains like forensic sciences and other repeat expansion disorders.,FALSE,FALSE,"(0, 9, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,"The information from STRIDE-DB can be used to build novel diagnostic tools and targeted therapeutics, as well as to gain a better understanding of the significance of STRs for human pathologies and physiology.",FALSE,FALSE,"(21, 30, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,A systematic methodology of the data collection and data processing of STRIDE-DB.,FALSE,FALSE,"(71, 80, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,The data were stored in five collections or tables under STRIDE-DB database (Figure 2).,FALSE,FALSE,"(57, 66, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,A systematic outline of the front-end and back-end architecture of STRIDE-DB.,FALSE,FALSE,"(67, 76, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,This web page is the gateway to the STRIDE-DB database.,FALSE,FALSE,"(36, 45, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,"In the search page, a basic overview of the STRIDE-DB was provided.",FALSE,FALSE,"(44, 53, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,An example view of a query gene and an STR search in STRIDE-DB.,FALSE,FALSE,"(53, 62, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,(A) The resultant page of gene-wise search in STRIDE-DB for PPP2R2B gene.,FALSE,FALSE,"(46, 55, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,"When we analysed these regions in the STRIDE-DB, within 50-kb of these markers, there were GWAS studies which were associated to cholesterol level, heart rate response to beta blockers and asthma-related disorders found, which also coincides with the symptoms/effects of Down syndrome (Supplementary Table S1) (21–24), thus suggesting that these variations in the STRs can act as a clinical marker in screening Down syndrome before pregnancy.",FALSE,FALSE,"(38, 47, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,"In contrast, STRIDE-DB provides a spectrum of features to understand these variations in the general population from a phenotypic perspective.",FALSE,FALSE,"(13, 22, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,"STRIDE-DB fills in the gaps by allowing the researchers to determine the location and frequency of STRs quickly and efficiently in the human genome, as well as to study the potential link between these polymorphisms and various traits such as illness susceptibility and demographic ancestry.",FALSE,FALSE,"(0, 9, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,Comparison of STRIDE-DB features with other databases,FALSE,FALSE,"(14, 23, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,STRIDE-DB attempts to bridge the gap of STR variability-phenotype.,FALSE,FALSE,"(0, 9, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11008502,The scripts used during Repeat Masker and the annotation of the STRs were mentioned in the link (https://raw.githubusercontent.com/bharathramh/STRIDE-DB_Codes/main/codes.md).,FALSE,FALSE,"(143, 152, 'STRIDE-DB', 'stride_db')","DNA polymorphism, Genotype and phenotype, GWAS study, Sequence composition, complexity and repeats, Exome sequencing"
PMC11052659,We developed a fast XGBoost method and software VirusPredictor leveraging an in-house viral genome database.,FALSE,FALSE,"(48, 62, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,We applied VirusPredictor to multiple real genomic and metagenomic datasets and obtained high accuracies.,FALSE,FALSE,"(11, 25, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,"VirusPredictor, a user-friendly open-source Python software, is useful for predicting the origins of patients’ unmappable sequences.",FALSE,FALSE,"(0, 14, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,www.dllab.org/software/VirusPredictor.html.,FALSE,FALSE,"(24, 38, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,Figure 1 depicts the flowchart of our method and software package (VirusPredictor).,FALSE,FALSE,"(67, 81, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,Flowchart of VirusPredictor sequence prediction pipeline.,FALSE,FALSE,"(13, 27, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,"To implement our two-step XGBoost models, we developed a new software package named VirusPredictor.",FALSE,FALSE,"(84, 98, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,VirusPredictor is written in Python and is open-source and freely available (www.dllab.org/software/VirusPredictor.html).,FALSE,FALSE,"(0, 14, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,"We developed a novel Python software, VirusPredictor, to implement our two-step XGBoost models.",FALSE,FALSE,"(38, 52, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,We then applied VirusPredictor to five publicly available real viral sequence datasets and obtained high prediction accuracies.,FALSE,FALSE,"(16, 30, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,We used VirusPredictor to predict these contigs (average length 2595 bp with minimum 1000 bp and maximum 105 439 bp).,FALSE,FALSE,"(8, 22, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,"In our second application, we used VirusPredictor to predict the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) genome (NC_045512.2; 29 903 bp).",FALSE,FALSE,"(35, 49, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,"When the whole SARS-CoV-2 genome sequence was used as input, VirusPredictor predicted it to be of viral origin, and then accurately classified it as a ssRNA(+) virus.",FALSE,FALSE,"(61, 75, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,"To challenge VirusPredictor, we randomly extracted 300 continuous fragments from the SARS-CoV-2 genome with three length gradients (150–350, 850–950, and 2000–5000 bp), and then used VirusPredictor to predict each of the 300 fragments.",FALSE,FALSE,"(13, 27, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,"In our third application, we applied VirusPredictor to directly predict the 5551 Illumina short reads (300 bp) of potential viral sequences from 19 metagenomic datasets (Tampuu et al.",FALSE,FALSE,"(37, 51, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,"In our fourth application, we applied VirusPredictor to predict the viruses (mostly phages) used in an existing study (Ren et al.",FALSE,FALSE,"(38, 52, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,"After downloading the complete genomes (mean = 70 865 bp with min = 4184 and max = 348 113) from the NCBI viral genome database and removing sequences containing missing nucleotides, we used VirusPredictor to predict the cleaned 674 genomes.",FALSE,FALSE,"(191, 205, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,"150–350, 850–950, 2000–5000, 10 000–30 000, and 30 000–100 000 bp), and applied VirusPredictor.",FALSE,FALSE,"(80, 94, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,VirusPredictor is useful specifically for predicting the origins of sequences that cannot be aligned to existing reference genomes of species of interest.,FALSE,FALSE,"(0, 14, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,"VirusPredictor can discover sequences derived from uncharacterized infectious viruses and endogenous retroviruses (for which no actual reference genomes exist), and other viral sequences that are not identifiable by alignment.",FALSE,FALSE,"(0, 14, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,"Adding to user convenience, VirusPredictor accepts assembled contigs and long/short read sequences in either FASTQ or FASTA format.",FALSE,FALSE,"(28, 42, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,2022) to enhance the predictive power of VirusPredictor.,FALSE,FALSE,"(41, 55, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,"In summary, we developed and demonstrated a novel XGBoost-based method with user-friendly software, VirusPredictor.",FALSE,FALSE,"(100, 114, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,VirusPredictor Python package: www.dllab.org/software/VirusPredictor.html,FALSE,FALSE,"(0, 14, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,VirusPredictor transposable element-masked human genome reference GRCh38.p13: www.dllab.org/software/VirusPredictor/hg38_rmsk_ERV.fa,FALSE,FALSE,"(0, 14, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11052659,VirusPredictor endogenous retrovirus training data (minimum length = 100 bp): www.dllab.org/software/VirusPredictor/hg38_ERV_100bp.fa,FALSE,FALSE,"(0, 14, 'VirusPredictor', 'viruspredictor')","Metagenomics, Sequence assembly, Sequencing, Machine learning, Infectious disease"
PMC11024640,"Finally, we developed a pipeline (Plant-LncPipe) that incorporates an ensemble of the two best-performing models and covers the entire data analysis process, including reads mapping, transcript assembly, lncRNA identification, classification, and origin, for the efficient identification of lncRNAs in plants.",FALSE,FALSE,"(34, 47, 'Plant-LncPipe', 'plant_lncpipe')","Functional, regulatory and non-coding RNA, Plant biology, Epigenetics, Workflows, Gene transcripts"
PMC11024640,"The pipeline, Plant-LncPipe, is available at: https://github.com/xuechantian/Plant-LncRNA-pipline.",FALSE,FALSE,"(14, 27, 'Plant-LncPipe', 'plant_lncpipe')","Functional, regulatory and non-coding RNA, Plant biology, Epigenetics, Workflows, Gene transcripts"
PMC11024640,"Ultimately, we implemented a pipeline (Plant-LncPipe) comprising these two models to carry out all essential steps in lncRNA identification and characterization.",FALSE,FALSE,"(39, 52, 'Plant-LncPipe', 'plant_lncpipe')","Functional, regulatory and non-coding RNA, Plant biology, Epigenetics, Workflows, Gene transcripts"
PMC11024640,We developed a pipeline (Plant-LncPipe) for the identification and characterization of plant lncRNAs by implementing key steps of lncRNA analysis: transcriptome alignment and assembly; lncRNA prediction; and lncRNA classification and origin (Fig.,FALSE,FALSE,"(25, 38, 'Plant-LncPipe', 'plant_lncpipe')","Functional, regulatory and non-coding RNA, Plant biology, Epigenetics, Workflows, Gene transcripts"
PMC11024640,"The right panel depicts the process of a computational pipeline, Plant-LncPipe, which provides an ensemble method of lncRNA identification and key steps of lncRNA characterization.",FALSE,FALSE,"(65, 78, 'Plant-LncPipe', 'plant_lncpipe')","Functional, regulatory and non-coding RNA, Plant biology, Epigenetics, Workflows, Gene transcripts"
PMC11024640,"Additionally, we developed a pipeline (Plant-LncPipe) for identifying and characterizing plant lncRNAs.",FALSE,FALSE,"(39, 52, 'Plant-LncPipe', 'plant_lncpipe')","Functional, regulatory and non-coding RNA, Plant biology, Epigenetics, Workflows, Gene transcripts"
PMC11024640,"We developed an lncRNA identification and characterization pipeline, Plant-LncPipe, to facilitate the discovery and characterization of novel plant lncRNAs (Fig.",FALSE,FALSE,"(69, 82, 'Plant-LncPipe', 'plant_lncpipe')","Functional, regulatory and non-coding RNA, Plant biology, Epigenetics, Workflows, Gene transcripts"
PMC11024640,Our Plant-LncPipe comprises three main modules for distinct tasks: (1) transcriptome alignment and transcriptome assembly; (2) lncRNA identification; and (3) lncRNA origin and classification.,FALSE,FALSE,"(4, 17, 'Plant-LncPipe', 'plant_lncpipe')","Functional, regulatory and non-coding RNA, Plant biology, Epigenetics, Workflows, Gene transcripts"
PMC11040716,"Here, based on a series of robust models, we formed a one-stop, general purpose, and AI-based drug discovery platform, MolProphet, to provide complete functionalities in the early stages of small molecule drug discovery, including AI-based target pocket prediction, hit discovery and lead optimization, and compound targeting, as well as abundant analyzing tools to check the results.",FALSE,FALSE,"(119, 129, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,MolProphet is an accessible and user-friendly web-based platform that is fully designed according to the practices in the drug discovery industry.,FALSE,FALSE,"(0, 10, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"The molecule screened, generated, or optimized by the MolProphet is purchasable and synthesizable at low cost but with good drug-likeness.",FALSE,FALSE,"(54, 64, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,More than 400 users from industry and academia have used MolProphet in their work.,FALSE,FALSE,"(57, 67, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"To remove the barriers in using AI technology, integrating multicompound databases and generating molecules with good drug-like properties and synthetic accessibility for normal researchers, we developed the SaaS (Software as a Service) and cocreation platform MolProphet (https://www.molprophet.com/).",FALSE,FALSE,"(261, 271, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"MolProphet provides a one-stop, general purpose online drug discovery platform to help investigators accelerate their new drug development process.",FALSE,FALSE,"(0, 10, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"In the following sections, we describe the key features of the MolProphet platform.",FALSE,FALSE,"(63, 73, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,The framework of MolProphet is shown in Figure 1.,FALSE,FALSE,"(17, 27, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,Framework of the AI-based drug discovery platform MolProphet.,FALSE,FALSE,"(50, 60, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,Table 2 shows MolProphet ’s target focused compound library (TFCL).,FALSE,FALSE,"(14, 24, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"Recognizing that not all users possess expertise in drug discovery software, the MolProphet platform was carefully developed to ensure user-friendliness, minimizing any potential hurdles.",FALSE,FALSE,"(81, 91, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"Moreover, the MolProphet platform has preset multitype input data methods for all modules (such as defining target pockets, submitting reference molecules, etc.) to meet different usage scenarios.",FALSE,FALSE,"(14, 24, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"For result management, the MolProphet platform provides task objectives and conclusion record functions for each task, which provides convenience for later review and also facilitates communication among users.",FALSE,FALSE,"(27, 37, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"In the future, the MolProphet platform will add more content related to results and records, including but not limited to automatically generated task reports, molecular reports, experimental record management, etc.",FALSE,FALSE,"(19, 29, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"For project management, the MolProphet platform establishes a set of project-based data management solutions to solve users’ data management problems.",FALSE,FALSE,"(28, 38, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"The development of MolProphet started in 2017, and since then, the platform has been used in more than 20 hit discovery and lead optimization projects with impressive results.",FALSE,FALSE,"(19, 29, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"MolProphet is a one-stop, general purpose, and AI-based platform for the early stages of small molecule drug discovery.",FALSE,FALSE,"(0, 10, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"With MolProphet, users can access the platform from anywhere, eliminating the need for a complex hardware or software setup.",FALSE,FALSE,"(5, 15, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"In summary, MolProphet is a valuable online AIDD tool that empowers researchers to accelerate their work in the early stages of small molecule drug development.",FALSE,FALSE,"(12, 22, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"Test application case on MolProphet, 2.",FALSE,FALSE,"(25, 35, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11040716,"Software technology framework of MolProphet, 3.",FALSE,FALSE,"(33, 43, 'MolProphet', 'molprophet')","Drug discovery, Machine learning, Small molecules, Drug development, Molecular modelling"
PMC11027269,"Through the Power-FDR curve, the GbyE algorithm can detect more significant genetic loci at different levels of genetic correlation and heritability, especially at low heritability levels.",FALSE,FALSE,"(33, 37, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The additive effect of GbyE exhibits high significance on certain chromosomes, while the interactive effect detects more significant sites on other chromosomes, which were not detected in the first two parts.",FALSE,FALSE,"(23, 27, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In prediction accuracy testing, in most cases of heritability and genetic correlation, the majority of prediction accuracy of GbyE is significantly higher than that of the mean method, regardless of whether the rrBLUP model or BGLR model is used for statistics.",FALSE,FALSE,"(126, 130, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The GbyE algorithm improves the prediction accuracy of the three Bayesian models BRR, BayesA, and BayesLASSO using information from genetic by environmental interaction (G × E) and increases the prediction accuracy by 9.4%, 9.1%, and 11%, respectively, relative to the Mean value method.",FALSE,FALSE,"(4, 8, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The GbyE algorithm is significantly superior to the mean method in the absence of a single environment, regardless of the combination of heritability and genetic correlation, especially in the case of high genetic correlation and heritability.",FALSE,FALSE,"(4, 8, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"Therefore, this study constructed a new genotype design model program (GbyE) for GWAS and GS using Kronecker product.",FALSE,FALSE,"(71, 75, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,The results showed that GbyE can provide higher statistical power for the GWAS and more prediction accuracy of the GS models.,FALSE,FALSE,"(24, 28, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In addition, GbyE gives varying degrees of improvement of prediction accuracy in three Bayesian models (BRR, BayesA, and BayesCpi).",FALSE,FALSE,"(13, 17, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"Whatever the phenotype were missed in the single environment or multiple environments, the GbyE also makes better prediction for inference population set.",FALSE,FALSE,"(91, 95, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,The GbyE source code is available at the GitHub website (https://github.com/liu-xinrui/GbyE).,FALSE,FALSE,"(4, 8, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"This study developed a novel genotype-by-environment method based on R, termed GbyE, which leverages the interaction among multiple environments or phenotypes to enhance the association study and prediction performance of environmental susceptibility traits.",FALSE,FALSE,"(79, 83, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The development purpose of GbyE is to apply it to GWAS and GS research, therefore it uses the genome association and prediction integrated tool (GAPIT) [19], Bayesian Generalized Linear Regression (BGLR) [20], and Ridge Regression Best Linear Unbiased Prediction (rrBLUP) [21]package as support packages, where GbyE only provides conversion of interactive formats and file generation.",FALSE,FALSE,"(27, 31, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In order to simplify the operation of the GbyE function package, the basic calculation package is attached to this package to support the operation of GbyE, including four function packages GbyE.Simulation.R (Dual environment phenotype simulation based on heritability, genetic correlation, and QTL quantity), GbyE.Calculate.R (For numerical genotype and phenotype data, this package can be used to process interactive genotype files of GbyE), GbyE.Power.FDR.R (Calculate the statistical power and false discovery rate (FDR) of GWAS), and GbyE.Comparison.Pvalue.R (GbyE generates redundant calculations in GWAS calculations, and SNP effect loci with minimal p-values can be filtered by this package).",FALSE,FALSE,"(42, 46, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"Among them, our phenotype data was simulated using a self-made R simulation function, and the Mean and GbyE phenotype files were calculated.",FALSE,FALSE,"(103, 107, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The pipeline analysis process of GbyE includes three steps: data preprocessing, production converted, Association analysis.",FALSE,FALSE,"(33, 37, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,Normalize the phenotype data matrix Y of the dual environment and perform GbyE conversion to generate phenotype data in GbyE.Y format.,FALSE,FALSE,"(74, 78, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The G (n × m) originally of genotype matrix was converted as GbyE.GD(2n × 2 m) \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$$\left[\begin{array}{cc}G& 0\\ G& G\end{array}\right]$$\end{document}G0GG during the Kronecker product, and the Y vector (n × 1) was also converted as the GbyE.Y vector (2n × 1) after normalization.",FALSE,FALSE,"(61, 65, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In the GbyE algorithm, we coded the first environment as background as default, that means the genotype in the first environment are 0, the others are 1.",FALSE,FALSE,"(7, 11, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,Then the Kronecker product of G and environment index matrix was named as GbyE.GD.,FALSE,FALSE,"(74, 78, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,The interactive effect part of the GbyE.GD matrix in the GWAS and GS were the relative values based on the first environment (Fig.,FALSE,FALSE,"(35, 39, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The GbyE environmental interaction matrix can be easily obtained by constructing the interaction matrix E (e.g., Eq.",FALSE,FALSE,"(4, 8, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"\documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$$\left[\begin{array}{cc}G& 0\\ G& G\end{array}\right]$$\end{document}G0GG matrix is called gene by environment interaction matrix, hereinafter referred to as the GbyE matrix.",FALSE,FALSE,"(430, 434, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,The phenotype file (GbyE.Y) and genotype file (GbyE.GD) after transformation by GbyE will be inputted into the GWAS and GS models and computed as standard phenotype and genotype files.,FALSE,FALSE,"(20, 24, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,GbyE mainly uses the Kronecker product of the genetic matrix (G) and the environmental matrix (E) as the genotype for subsequent GWAS as a way to distinguish between additive and interactive effects.Fig.,FALSE,FALSE,"(0, 4, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,1The workflow pipeline of GbyE.,FALSE,FALSE,"(26, 30, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,The GbyE contains three main steps.,FALSE,FALSE,"(4, 8, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"Meanwhile, all genotype from HapMap, VCF, BED, and other types were converted to numeric genotype; (Step 2) Generate GbyE phenotype and interactive genotype matrix through the transformation of GbyE.",FALSE,FALSE,"(117, 121, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In GbyE.GD matrix, the blue characters indicate additive effect, and red ones indicate interactive effect; (Step 3) The MLM and rrBLUP and BGLR were used to perform GWAS and GS",FALSE,FALSE,"(3, 7, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,The workflow pipeline of GbyE.,FALSE,FALSE,"(25, 29, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"This method obtains the mean of phenotypic values under different conditions as the phenotypic values for GWAS analysis, called the Mean value method, Compare the calculation results of GbyE with the additive and interactive effects of the mean method to evaluate the detection power of the GbyE strategy.",FALSE,FALSE,"(186, 190, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"Through the comprehensive analysis of these evaluation indicators, we aim to comprehensively evaluate the statistical power of the GbyE strategy in GWAS and provide a reference for future optimization research.",FALSE,FALSE,"(131, 135, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"To comparison the prediction accuracy of different GS models using GbyE, we performed rrBLUP, Bayesian methods using R packages.",FALSE,FALSE,"(67, 71, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In order to distinguish the additive and interactive effects in GbyE, we designed two lists of additive and interactive effects in the ""ETA"" of BGLR, and put the additive and interactive effects into the model as two kinships for random objects.",FALSE,FALSE,"(64, 68, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"We also validated the GbyE method using four other Bayesian methods (BayesA, BayesB, BayesCpi, and Bayesian LASSO) in addition to RRB in BGLR.",FALSE,FALSE,"(22, 26, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"Power-FDR plots were used to demonstrate the detection efficiency of GbyE at three genetic correlation and three genetic power levels, with a total of nine different scenarios simulated (from left to right for high and low genetic correlation and from top to bottom for high and low genetic power).",FALSE,FALSE,"(69, 73, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In order to distinguish whether the effect of improving the detection ability of genome-wide association analysis in GbyE is an additive effect or an effect of environmental interactions, we plotted their Power-FDR curves separately and added the traditional Mean method for comparative analysis.",FALSE,FALSE,"(117, 121, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"2, GbyE algorithm can detect more statistically significant genetic loci with lower FDR under any genetic background.",FALSE,FALSE,"(3, 7, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"2A, B, C), the interactive effect detected more real loci than GbyE under low FDR, but with the continued increase of FDR, GbyE detected more real loci than other groups.",FALSE,FALSE,"(63, 67, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"Under the combination with high heritability, all groups have high statistical power at low FDR, but with the increase of FDR, the statistical effect of GbyE gradually highlights.",FALSE,FALSE,"(153, 157, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"From the analysis of heritability combinations at all levels, the effect of heritability on interactive effect is not obvious, but GbyE always maintains the highest statistical power.",FALSE,FALSE,"(131, 135, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The average detection power of GWAS in GbyE can be increased by about 20%, and with the decrease of genetic correlation, the effect of GbyE gradually highlights, indicating that the G × E plays a role.Fig.",FALSE,FALSE,"(39, 43, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,Comparing the efficacy of the GbyE algorithm with the conventional mean method in terms of detection power and FDR.,FALSE,FALSE,"(30, 34, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"(1) Inter: Interactive section extracted from GbyE; (2) AddE: Additive section extracted from GbyE; (3) \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$${{\text{h}}}_{{\text{l}}}^{2}$$\end{document}hl2, \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$${{\text{h}}}_{{\text{m}}}^{2}$$\end{document}hm2, \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$${{\text{h}}}_{{\text{g}}}^{2}$$\end{document}hg2: Low, medium, high heritability; (4) \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$${{\text{R}}}_{{\text{l}}}$$\end{document}Rl, \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$${{\text{R}}}_{{\text{m}}}$$\end{document}Rm, \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$${{\text{R}}}_{{\text{l}}}$$\end{document}Rl: where R stands for genetic correlation, represents three levels of low, medium and high",FALSE,FALSE,"(46, 50, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,The output results of GbyE could be understood as resolution of additive and interactive genetic effect.,FALSE,FALSE,"(22, 26, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"Hence, we created a combined Manhattan plots with Mean result from MLM, additive, and interactive results from GbyE.",FALSE,FALSE,"(111, 115, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"3, true marker loci were detected on chromosomes 1, 6 and 9 in Mean, and the same loci were detected on chromosomes 1 and 6 for the additive result in GbyE (the common loci detected jointly by the two results were marked as solid gray lines in the figure).",FALSE,FALSE,"(151, 155, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"Although the additive section in GbyE did not catch the locus on chromosome 9 yet (those p-values of markers did not show above the significance threshold (p-value < 3.23 × 10–6)), it has shown high significance relative to other markers of the same chromosome.",FALSE,FALSE,"(33, 37, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In the reciprocal effect of GbyE, we detected more significant loci on chromosomes 1, 2, 3 and 10, and these loci were not detected in either of the two previous sections.",FALSE,FALSE,"(28, 32, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"3D) shows that the overall statistical power of the additive section in Mean and GbyE are close, nevertheless, the interactive section in the GbyE provided a bit of inflation.Fig.",FALSE,FALSE,"(81, 85, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,GbyE-inter is the interactive section in GbyE; GbyE-AddE is the additive section in GbyE,FALSE,FALSE,"(0, 4, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,The prediction accuracy of GbyE was significantly higher than the Mean value method by model statistics of rrBLUP in most cases of heritability and genetic correlation (Fig.,FALSE,FALSE,"(27, 31, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The prediction accuracy of interactive sections in GbyE remains at the same level as in GbyE, and interactive section plays an important role in the model.",FALSE,FALSE,"(51, 55, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"4G), the prediction accuracy of GbyE was slightly higher than the Mean value method, but there was no significant difference overall.",FALSE,FALSE,"(32, 36, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In addition, we only observed that the prediction accuracy of GbyE was slightly lower than the Mean value method in \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$${{\text{h}}}_{{\text{h}}}^{2}{{\text{R}}}_{{\text{l}}}$$\end{document}hh2Rl (Fig.",FALSE,FALSE,"(62, 66, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"4H), but there was still no significant difference between GbyE and Mean value methods.",FALSE,FALSE,"(59, 63, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In summary, the GbyE algorithm can improve the accuracy of GS by capturing information on multiple environment or trait effects under the rrBLUP model.Fig.",FALSE,FALSE,"(16, 20, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,The prediction accuracy (pearson's correlation coefficient) of the GbyE algorithm was compared with the tradition al Mean value method in a simulation experiment of genomic selection under the rrBLUP operating environment.,FALSE,FALSE,"(67, 71, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The overall performance of GbyE under the 'BRR' statistical model based on the BGLR package remained consistent with rrBLUP, maintaining high predictive accuracy in most cases of heritability and genetic relatedness (Fig.",FALSE,FALSE,"(27, 31, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"However, when the heritability is set to low and medium, the difference between the prediction accuracy of GbyE algorithm and Mean value method gradually decreases with the continuous increase of genetic correlation, and there is no statistically significant difference between the two.",FALSE,FALSE,"(107, 111, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,The prediction accuracy of the model by GbyE in \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$${{\text{h}}}_{{\text{h}}}^{2}{{\text{R}}}_{{\text{l}}}$$\end{document}hh2Rl (Fig.,FALSE,FALSE,"(40, 44, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"On the contrary, when the genetic correlation is set to medium, there is no significant difference between GbyE and Mean value method in improving the prediction accuracy of the model, and the overall mean of GbyE is lower than Mean.",FALSE,FALSE,"(107, 111, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"When GbyE has relatively high heritability and low genetic correlation, its prediction accuracy is significantly higher than the mean method, such as \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$${{\text{h}}}_{{\text{m}}}^{2}{{\text{R}}}_{{\text{l}}}$$\end{document}hm2Rl (Fig.",FALSE,FALSE,"(5, 9, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"Therefore, GbyE is more suitable for situations with high heritability and low genetic correlation.",FALSE,FALSE,"(11, 15, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The GbyE algorithm and Mean value method were combined with five Bayesian algorithms in BGLR for GS analysis, and the computing R script was used for phenotypic simulation test, where heritability and genetic correlation were both set to 0.5.",FALSE,FALSE,"(4, 8, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The results indicate that among the three Bayesian models of RRB, BayesA, and BayesLASSO, the predictive accuracy of GbyE is significantly higher than that of Mean value method (Fig.",FALSE,FALSE,"(117, 121, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In contrast, under the Bayesian models of BayesB and BayesCpi, the prediction accuracy of GbyE is lower than that of the Mean value method.",FALSE,FALSE,"(90, 94, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The GbyE algorithm improves the prediction accuracy of the three Bayesian models BRR, BayesA, and BayesLASSO using information from G × E and increases the prediction accuracy by 9.4%, 9.1%, and 11%, respectively, relative to the Mean value method.",FALSE,FALSE,"(4, 8, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,Where we normalize the prediction accuracy of Mean (the prediction accuracy is all adjusted to 1); the prediction accuracy of GbyE is the increase or decrease value relative to Mean in the same group of models,FALSE,FALSE,"(126, 130, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The improvement in prediction accuracy by the GbyE algorithm was found to be significantly higher than the Mean value method in single environment deletion, regardless of the combination of heritability and genetic correlation.",FALSE,FALSE,"(46, 50, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In the case of \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$${{\text{h}}}_{{\text{h}}}^{2}{{\text{R}}}_{{\text{h}}}$$\end{document}hh2Rh, the prediction accuracy of GbyE is higher than 0.5, which is the highest value among all simulated combinations.",FALSE,FALSE,"(388, 392, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"When GbyE estimates the phenotypic values of Environment 1 and Environment 2 separately, its predictive accuracy seems too accurate.",FALSE,FALSE,"(5, 9, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"On the other hand, when the phenotypic values of both environments are missing on the same genotype, the predictive accuracy of GbyE does not show a significant decrease, and even maintains accuracy comparable to that of a single environment missing.",FALSE,FALSE,"(128, 132, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"However, when GbyE estimates Environment 1 and Environment 2 separately, the prediction accuracy significantly decreases compared to when a single environment is missing, and the prediction accuracy of Environment 1 and Environment 2 in \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$${{\text{h}}}_{{\text{l}}}^{2}{{\text{R}}}_{{\text{m}}}$$\end{document}hl2Rm is extremely low (Fig.",FALSE,FALSE,"(14, 18, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In addition, the prediction accuracy of GbyE is lower than Mean values only in \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$${{\text{h}}}_{{\text{l}}}^{2}{{\text{R}}}_{{\text{h}}}$$\end{document}hl2Rh, whether it is missing in a single or dual environment.Fig.",FALSE,FALSE,"(40, 44, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The prediction effect of GbyE was divided into two parts, environment 1 and environment 2, to compare the prediction accuracy of GbyE when predicting these two parts separately.",FALSE,FALSE,"(25, 29, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In this study, the additive effects in GbyE are essentially equivalent to the detectability of traditional models, the key advantage of GbyE is the interactive section.",FALSE,FALSE,"(39, 43, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"This allows the estimation of additive and interactive genetic effects separately during the analysis, and ultimately the estimated genetic effects for each GbyE genotype (including additive and interactive genetic effect markers) are placed in a t-distribution for p-value calculation, and the significance of each genotype is considered by multiple testing.",FALSE,FALSE,"(157, 161, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,The GbyE also expanded the estimated heritability as generalized heritability which could be explained as the rate between total genetics variance and phenotype variance.,FALSE,FALSE,"(4, 8, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,The genetic correlation among traits in multiple environments is the major immanent cause of GbyE.,FALSE,FALSE,"(93, 97, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"Therefore, the statistical power of the GbyE algorithm did not improve significantly compared with the traditional method (Mean value) when simulating high levels of genetic correlation.",FALSE,FALSE,"(40, 44, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"At this time, GbyE utilizes multiple environments or traits to highlight the statistical power.",FALSE,FALSE,"(14, 18, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"Since the GbyE algorithm obtains additive, environmental, and interactive information by encoding numerical genotypes, it only increases the volume of SNP data and can be applied to any traditional GWAS association statistical model.",FALSE,FALSE,"(10, 14, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"However, this may slightly increase the correlation operation time of the GWAS model, but compared to other multi environment or trait models [28, 29], GbyE only needs to perform a complete traditional GWAS once to obtain the results.",FALSE,FALSE,"(152, 156, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The model has been able to take into account more biological features and complexity, and therefore the overall improvement of the GbyE algorithm under BGLR is smaller than Mean method.",FALSE,FALSE,"(131, 135, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,GbyE is effective in improving the statistical power of the model under most Bayesian statistical models.,FALSE,FALSE,"(0, 4, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The overall statistical power of GbyE was significantly higher in missing single environment than in missing double environment, because in the case of missing single environment, GbyE can take full advantage of the information from the phenotype in the second environment.",FALSE,FALSE,"(33, 37, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,And the correlation between two environments can also affect the detectability of the GbyE algorithm in different ways.,FALSE,FALSE,"(86, 90, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"On the one hand, a high correlation between two environments can improve the predictive accuracy of the GbyE algorithm by using the information from one environment to predict the breeding values in the other environment, even if there is only few relationship with that environment [37, 38].",FALSE,FALSE,"(104, 108, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"On the other hand, when two environments are extremely uncorrelated, GbyE algorithm trained in one environment may not export well to another environment, which may lead to a decrease in prediction accuracy [39].",FALSE,FALSE,"(69, 73, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"In the testing, we found that when the GbyE algorithm uses a GS model trained in one environment and tested in another environment, the high correlation between environments may result to the model capturing similarities between environments unrelated to G × E information [40].",FALSE,FALSE,"(39, 43, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"However, when estimating the breeding values for each environment separately, GbyE still made effective predictions using the genotypes in that environment and maintained high prediction accuracy.",FALSE,FALSE,"(78, 82, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The correlation between the two environments may have both positive and negative effects on the detectability of the GbyE, so it is important to carefully consider the relationship between the two environments in subsequent in development and testing.",FALSE,FALSE,"(117, 121, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,A key advantage of the GbyE algorithm is that it can be applied to almost all current genome-wide association and prediction.,FALSE,FALSE,"(23, 27, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"However, the focus of GbyE is still on estimating additive and interactive effects separately, so that it is easy to determine which portion of the is playing a role in the computational estimation..",FALSE,FALSE,"(22, 26, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,The GbyE algorithm may have implications for the design of future GS studies.,FALSE,FALSE,"(4, 8, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"GbyE can simulate the effects of gene-environment interactions by building genotype files for multiple environments or multiple traits, normalizing the effects of multiple environments and multiple traits on marker effects.",FALSE,FALSE,"(0, 4, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11027269,"The GbyE source code, demo script, and demo data are freely available on the GitHub website (https://github.com/liu-xinrui/GbyE).",FALSE,FALSE,"(4, 8, 'GbyE', 'gbye')","GWAS study, Genotype and phenotype, Metagenomics, Genetic variation, Molecular interactions, pathways and networks"
PMC11039349,"To bridge this gap, we introduce RBProkCNN, a novel machine learning-driven computational model meticulously designed for the accurate prediction of prokaryotic RBPs.",FALSE,FALSE,"(33, 42, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"By leveraging a convolutional neural network (CNN) and evolutionarily significant features selected through extreme gradient boosting variable importance measure, RBProkCNN achieved the highest accuracy in five-fold cross-validation, yielding 98.04% auROC and 98.19% auPRC.",FALSE,FALSE,"(163, 172, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"Furthermore, RBProkCNN demonstrated robust performance with an independent dataset, showcasing a commendable 95.77% auROC and 95.78% auPRC.",FALSE,FALSE,"(13, 22, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"RBProkCNN is available as an online prediction tool (https://iasri-sg.icar.gov.in/rbprokcnn/), offering free access to interested users.",FALSE,FALSE,"(0, 9, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"•Prokaryotic RBPs are essential for post-transcriptional regulation, mRNA stability, and adaptation to diverse environmental conditions in prokaryotes.•Existing generic computational methods are less accurate for predicting prokaryotic-specific RBPs.•A novel computational model, RBProkCNN is introduced to predict prokaryotic RBPs with higher accuracy.•RBProkCNN achieved higher accuracy than several existing models.•The developed prediction server is freely accessible at https://iasri-sg.icar.gov.in/rbprokcnn/.",FALSE,FALSE,"(280, 289, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"A novel computational model, RBProkCNN is introduced to predict prokaryotic RBPs with higher accuracy.",FALSE,FALSE,"(29, 38, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,RBProkCNN achieved higher accuracy than several existing models.,FALSE,FALSE,"(0, 9, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"Here, we proposed a new computational model, RBProkCNN, designed explicitly for predicting prokaryote-specific RBPs.",FALSE,FALSE,"(45, 54, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"Thus, to further make a comparison with PreRBP-TL, the performance of RBProkCNN was evaluated using the training dataset of PreRBP-TL.",FALSE,FALSE,"(70, 79, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"coli and Salmonella), the performance of RBProkCNN was evaluated using the training dataset of E.",FALSE,FALSE,"(41, 50, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"It was found that for E.coli, auROC of RBProkCNN (93.62%) achieved a little higher accuracy than that of PreRBP-TL (93.33%), whereas for Salmonella, PreRBP-TL achieved higher auROC (95.20%) than that of RBProkCNN (93.87%) (Table 4).",FALSE,FALSE,"(39, 48, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"As far as auPRC is concerned, RBProkCNN achieved better accuracy as compared to the PreRBP-TL, for both E.coli and Salmonella (Table 4).",FALSE,FALSE,"(30, 39, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"Thus, on the basis of auPRC measure, it can be said that the proposed model may achieve higher accuracy than that of PreRBP-TL.Table 4Performance comparison of PreRBP-TL and the RBProkCNN using the training datasets of PreRBP-TL.Table 4ModelSpeciesAccuracyPrecisionF1-ScoreMCCauROCauPRCRBProkCNNE.",FALSE,FALSE,"(178, 187, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,Performance comparison of PreRBP-TL and the RBProkCNN using the training datasets of PreRBP-TL.,FALSE,FALSE,"(44, 53, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"The performance advantage of RBProkCNN over PreRBP-TL was observed to be small, which may be due the initial large language generative model of PreRBP-TL where the test data set of RBProkCNN were included in the model training.",FALSE,FALSE,"(29, 38, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"Nonetheless, to further validate the higher performance of RBProkCNN over PreRBP-TL, we prepared another independent test dataset comprising prokaryotic RBP sequences of four different species such as Haemophilus Influenzae (116), Mycobacterium tuberculosis (97), Shigella flexneri (108) and Yersinia pestis (96).",FALSE,FALSE,"(59, 68, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,It was ensured that none of these species were present in the training set of RBProkCNN as well as PreRBP-TL.,FALSE,FALSE,"(78, 87, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"From Table 5, it was observed that RBProkCNN achieved higher accuracy as compared to the PreRBP-TL model, for all the four species.Table 5Species-specific prediction accuracy of PreRBP-TL and the proposed model RBProkCNN.Table 5SpeciesPreRBP-TLRBProkCNNE.",FALSE,FALSE,"(35, 44, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,Species-specific prediction accuracy of PreRBP-TL and the proposed model RBProkCNN.,FALSE,FALSE,"(73, 82, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"Therefore, CNN with 920 XGB-VIM selected features was chosen for developing the RBProkCNN model.",FALSE,FALSE,"(80, 89, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"Nonetheless, the performance of RBProkCNN was also evaluated using the imbalanced training datasets of best performing existing model PreRBP-TL and was found to perform better than that of PreRBP-TL.",FALSE,FALSE,"(32, 41, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"Thus, it may be said that the RBProkCNN may perform better both with balanced and imbalanced datasets.",FALSE,FALSE,"(30, 39, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"The performance RBProkCNN was also assessed on a blind test dataset to demonstrate its robustness and generalization ability, where the performance metrics were found to be closer to that of cross-validation.",FALSE,FALSE,"(16, 25, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"To further validate the model's reliability, we compared RBProkCNN's performance with existing state-of-the-art methods using the same blind test dataset.",FALSE,FALSE,"(57, 66, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,The RBProkCNN exhibited higher accuracy compared to the other available methods.,FALSE,FALSE,"(4, 13, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"Thus, RBProkCNN is believed to address this gap by providing a model tailored for predicting prokaryote-specific RBPs, underscoring the importance of accurate predictions in unravelling gene expression patterns and enhancing our understanding of prokaryotic gene regulation.",FALSE,FALSE,"(6, 15, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"The present study introduces RBProkCNN (https://iasri-sg.icar.gov.in/rbprokcnn/), a novel computational tool specifically tailored for predicting prokaryote-specific RBPs.",FALSE,FALSE,"(29, 38, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11039349,"Utilizing a CNN-based deep learning model with an ensemble of evolutionary features, RBProkCNN addresses the specificity of RBPs to individual species and lineage-specific families, providing more accurate predictions.",FALSE,FALSE,"(85, 94, 'RBProkCNN', 'rbprokcnn')","Gene transcripts, Machine learning, Model organisms"
PMC11470080,"While there is an abundance of methods for TE quantification at the bulk level, such as Squire10, TEtranscripts11, and Telescope12, emerging single-cell methods like scTE2 and SoloTE13 remain limited.",FALSE,FALSE,"(166, 170, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"In contrast, scTE employs a similar strategy but rectifies multi-mapping errors using the count of unique-mapping reads.",FALSE,FALSE,"(13, 17, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,scTE measures TE expression by allocating reads to corresponding TE subfamilies.,FALSE,FALSE,"(0, 4, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"For instance, scTE is limited to assigning multi-mapping reads to the metagene (TEs of the same subfamily), lacking a distinct assignment to specific genomic loci.",FALSE,FALSE,"(14, 18, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"While some existing methods (e.g., scTE) can be adapted to handle full-length single-cell RNA-seq data, their performance is often suboptimal, highlighting the value of MATES’ ability to process and interpret these datasets effectively (Supplementary Fig.",FALSE,FALSE,"(35, 39, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"S5 illustrates the cell clustering based on TE and gene expression in Arabidopsis using MATES, scTE, and SoloTE.",FALSE,FALSE,"(95, 99, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"S5a shows the UMAP visualization of TE expression quantified by scTE compared with gene expression clusters, with an ARI of 0.3315 (P  < 1 × 10−6).",FALSE,FALSE,"(64, 68, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"S5a–c), MATES achieved a 0.6668 ARI score (P < 1 × 10−6), which is higher than SoloTE (ARI = 0.5916, P < 1 × 10−6) and scTE (ARI = 0.5775, P < 1 × 10−6).",FALSE,FALSE,"(119, 123, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,S6 shows clustering results based on TE and gene expression using MATES and scTE.,FALSE,FALSE,"(76, 80, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"S6a) and by scTE (ARI =  0.3078, P = 4.60 × 10−5, Supplementary Fig.",FALSE,FALSE,"(12, 16, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"This is compared with the two established methods, scTE and SoloTE.",FALSE,FALSE,"(51, 55, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,Both scTE and SoloTE are incapable of providing locus-specific TE quantification that accounts for multi-mapping reads.,FALSE,FALSE,"(5, 9, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"Specifically, scTE is confined to subfamily level quantification, while SoloTE does offer locus-specific quantification but is constrained to unique mapping reads.",FALSE,FALSE,"(14, 18, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"To ensure a fair comparison in our benchmarking, we have restricted our analysis in this section to the subfamily level, a feature shared by both scTE and SoloTE.",FALSE,FALSE,"(146, 150, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"Our analysis compared MATES with two existing single-cell TE quantification methods scTE and SoloTE, which primarily differ in their approach to handling multi-mapping reads.",FALSE,FALSE,"(84, 88, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"We observed significant differences in their performance: scTE uses a basic correction method, SoloTE selects the top-scoring alignment, and MATES utilizes a probabilistic approach informed by local read context.",FALSE,FALSE,"(58, 62, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"In the analysis that integrated both Gene and TE expression, MATES demonstrated better performance than scTE and SoloTE, especially evident in the 10x scRNA dataset for chemical reprogramming.",FALSE,FALSE,"(104, 108, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"In this context, scTE’s effectiveness was markedly inferior compared to a gene expression-only approach, highlighting the importance of accurate multi-mapping read assignment.",FALSE,FALSE,"(17, 21, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"Here again, MATES outshone scTE and SoloTE in terms of clustering efficiency, which was reflected in improved ARI and NMI scores (see the middle panels of Fig.",FALSE,FALSE,"(27, 31, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"MATES consistently outperformed scTE and SoloTE in these tests, as depicted in the middle and right panels of Fig.",FALSE,FALSE,"(32, 36, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"These methods include scTE (gene expression combined with scTE-quantified TE), SoloTE (gene expression combined with SoloTE-quantified TE), and MATES (gene expression integrated with MATES-quantified TE).",FALSE,FALSE,"(22, 26, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,MATES outperforms both scTE and SoloTE by enhancing gene expression with TE data (left).,FALSE,FALSE,"(23, 27, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"The middle panel compares clustering based solely on TE quantification methods-unique TEs, scTE, SoloTE, and MATES-with 'unique TEs' representing unique-mapping reads TE expression, highlighting MATES's consistently improved performance.",FALSE,FALSE,"(91, 95, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,The right panel confirms MATES's advantage over scTE and SoloTE when considering only multi-mapping TE reads.,FALSE,FALSE,"(48, 52, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,c The 10x scATAC Dataset of the Adult Mouse Brain is analyzed to contrast peak and TE quantification using scTE and MATES against peak-only datasets (left).,FALSE,FALSE,"(107, 111, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,TE mapping reads from scTE and MATES are also compared against unique TE mapping reads (right).,FALSE,FALSE,"(22, 26, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"In our benchmarking analysis of the 10x scATAC mouse brain dataset, we assessed the MATES approach against scTE and peak-only quantification methods.",FALSE,FALSE,"(107, 111, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"Our results indicated a clear advantage of MATES over both scTE and peak-only methods in terms of clustering accuracy, showcasing its capacity to integrate additional chromatin accessibility insights effectively.",FALSE,FALSE,"(59, 63, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"This approach significantly surpassed scTE, contributing to an enhanced clustering process.",FALSE,FALSE,"(38, 42, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"Since scTE does not support locus-level TE quantification, we only compared the results from MATES with those from SoloTE.",FALSE,FALSE,"(6, 10, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"In our validation of MATES through nanopore long-read sequencing data, we compared TE expression quantified by each method, including MATES, scTE, and SoloTE, within individual cells.",FALSE,FALSE,"(141, 145, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"MATES’s quantification of TEs demonstrated a strong correlation with the ground-truth long-read data (R2 = 0.7531), surpassing both scTE (R2 = 0.6499) and SoloTE (R2 = 0.6841) in quantifying TE expression at the subfamily level from the real 10x short-read data, as seen in Fig.",FALSE,FALSE,"(132, 136, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"This performance exceeded that of other methods such as scTE and SoloTE, which achieved R2 values of 0.8591 and 0.8654, respectively (Supplementary Fig.",FALSE,FALSE,"(56, 60, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"7Validation of MATES TE quantification using nanopore long-read single-cell sequencing and simulation.a–c Analyze the correlation between TE expression quantified by (a) MATES, (b) scTE, and (c) SoloTE from real 10x short-read data and the nanopore long-read sequencing for the same set of cells.",FALSE,FALSE,"(181, 185, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,f Comparison of quantified results by MATES and scTE to the simulated ground truth for the Alu repeat simulated data.,FALSE,FALSE,"(48, 52, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"The blue bar and orange bar represent the percentage of simulated reads captured by MATES and scTE, respectively.",FALSE,FALSE,"(94, 98, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"Among the 6 simulated Alu families, MATES on average captured 96.14% simulated reads while scTE recaptured 92.57%.",FALSE,FALSE,"(91, 95, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"a–c Analyze the correlation between TE expression quantified by (a) MATES, (b) scTE, and (c) SoloTE from real 10x short-read data and the nanopore long-read sequencing for the same set of cells.",FALSE,FALSE,"(79, 83, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"We then benchmarked MATES against scTE and SoloTE using PacBio data from the postnatal mouse brain, with the processed long-read data of 7896 cell barcodes and an average length of 1,164 bp69.",FALSE,FALSE,"(34, 38, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"The results from this analysis showed strong correlations between the long-read and short-read expression data, with MATES achieving an R2 value of 0.5096, compared to 0.3537 for scTE and 0.4199 for SoloTE (Supplementary Fig.",FALSE,FALSE,"(179, 183, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"Consequently, SoloTE is incompatible with this data, prompting a focus on comparing subfamily-level performance with scTE.",FALSE,FALSE,"(117, 121, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"S14b compares the difference in read numbers between the ground truth and the quantified results from MATES and scTE, respectively.",FALSE,FALSE,"(112, 116, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"Although scTE showed better performance in a few TE instances, MATES generally demonstrated improved performance across most subfamilies.",FALSE,FALSE,"(9, 13, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"While MATES, a deep neural network-based method, typically requires more computational resources such as GPUs than its counterparts scTE and SoloTE for quantifying TEs, its memory usage remains relatively stable (generally below 30,000M) across single-cell datasets of varying sizes.",FALSE,FALSE,"(132, 136, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"Overall, the total running time of MATES is generally comparable to that of scTE and SoloTE (Supplementary Fig.",FALSE,FALSE,"(76, 80, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"Our benchmarking process involved comparing the performance of our method with other state-of-the-art TE quantification methods, scTE and SoloTE.",FALSE,FALSE,"(129, 133, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"SoloTE is known for its ability to quantify unique read TE expression at the locus level and multi-mapping read TE expression at the subfamily level, while scTE quantifies both at the subfamily level.",FALSE,FALSE,"(156, 160, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"The focus was on comparing the TE expression levels quantified by MATES, scTE, and SoloTE from the short-read data against the long-read data, considered as the ‘ground truth’.",FALSE,FALSE,"(73, 77, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"We employed a strategy similar to the benchmarking experiments with the scNanoRNAseq data, comparing MATES against scTE and SoloTE by running on the short-read data.",FALSE,FALSE,"(115, 119, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"Since SoloTE requires cell barcodes and unique molecular identifiers (UMIs) to identify cells (and does not support Smart-seq2 formatted data), we focused on comparing the subfamily expression levels quantified by scTE and MATES.",FALSE,FALSE,"(214, 218, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC11470080,"As previously mentioned, scTE does not yet support locus-level TE quantification, and SoloTE does not natively support full-length Smart-seq-like formatted data (such as those simulated from long-read data).",FALSE,FALSE,"(25, 29, 'scTE', 'scte')","Functional, regulatory and non-coding RNA, Mobile genetic elements, RNA-Seq"
PMC10984565,"Here, we proposed the first extensive database, namely ProNet DB, that integrates multiple protein surface representations and RNA-binding landscape for 326 175 protein structures.",FALSE,FALSE,"(55, 64, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,"For each protein, ProNet DB provides access to the original protein structures along with the detailed surface property representations encompassing hydrophobicity, charge distribution and hydrogen bonding potential as well as interactive features such as the interacting face and RNA-binding sites and preferences.",FALSE,FALSE,"(18, 27, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,"To facilitate an intuitive interpretation of these properties and the RNA-binding landscape, ProNet DB incorporates visualization tools like Mol* and an Online 3D Viewer, allowing for the direct observation and analysis of these representations on protein surfaces.",FALSE,FALSE,"(93, 102, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,"In summary, we have developed ProNet DB, a comprehensive database dedicated to detailing protein surface features.",FALSE,FALSE,"(30, 39, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,"To enable users to intuitively explore and interpret these complex surface properties and RNA-binding profiles, ProNet DB is integrated with visualization tools such as Mol* and an Online 3D Viewer.",FALSE,FALSE,"(112, 121, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,"To establish a robust foundation for ProNet DB, we began by aggregating protein structures for two key proteomes.",FALSE,FALSE,"(37, 46, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,"Finally, the proteomes of these model organisms sufficiently expanded ProNet DB protein structure coverage from 29 433 to 326 175 (Table 1) and led to a more comprehensive and user-friendly database.",FALSE,FALSE,"(70, 79, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,The model organism proteomes in ProNet DB,FALSE,FALSE,"(32, 41, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,An overview of the ProNet DB and the illustration for two main outputs.,FALSE,FALSE,"(19, 28, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,"In ProNet DB, we have systematically mapped the interactions between various RNA constituents and RBPs.",FALSE,FALSE,"(3, 12, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,"ProNet DB allows users to delve into protein properties with ease, including the composition of the RNA backbone and the binding predilections for different bases.",FALSE,FALSE,"(0, 9, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,"Currently, ProNet DB encompasses an expansive collection of proteome entries, spanning over 16 model organism species and totaling 333 365 records from both AlphaFold DB and PDB.",FALSE,FALSE,"(11, 20, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,User interface of ProNet DB.,FALSE,FALSE,"(18, 27, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,ProNet DB statistics for both human and yeast results in AlphaFold DB and PDB.,FALSE,FALSE,"(0, 9, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,"ProNet DB’s analysis of the protein surface fingerprint, particularly within the Iface region, reveals the nucleic acid-binding site’s prominence on the interacting face as opposed to non-binding areas.",FALSE,FALSE,"(0, 9, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,Case study (PDB: 5AXW): ProNet DB shows comprehensive information of the protein structure surface fingerprints as well as the protein–RNA binding landscape.,FALSE,FALSE,"(24, 33, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,"The ProNet DB has conducted multi-scale data analyses on a vast array of entries, encompassing 326,175 proteins across 16 different model organism species, sorted into a multitude of functional categories.",FALSE,FALSE,"(4, 13, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,The ProNet DB link is https://proj.cse.cuhk.edu.hk/aihlab/pronet/#/Home.,FALSE,FALSE,"(4, 13, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC10984565,An example entry in ProNet DB shows the data content organization of one protein 17-beta-hydroxysteroid dehydrogenase type 1,FALSE,FALSE,"(20, 29, 'ProNet DB', 'pronet_db')","Protein structural motifs and surfaces, Proteomics, Protein properties, Sequence analysis, Structure prediction"
PMC11425685,"Shaoxia Pu, Yanhua Su, and Anzhu zhu were involved in revision of the paper for intellectual content.",FALSE,FALSE,"(0, 7, 'Shaoxia', 'shaoxia')","RNA-Seq, RNA, Workflows, Computer science, Cell biology"
PMC11031912,"We developed GenoMycAnalyzer, a web-based software that integrates functions for identifying MTBC and NTM species, lineage and spoligotype prediction, variant calling, annotation, drug-resistance determination, and data visualization.",FALSE,FALSE,"(13, 28, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"The accuracy of GenoMycAnalyzer for genotypic drug susceptibility testing (gDST) was evaluated using 5,473 MTBC isolates that underwent phenotypic DST (pDST).",FALSE,FALSE,"(16, 31, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,The GenoMycAnalyzer database was built to predict the gDST for 15 antituberculosis drugs using the World Health Organization mutational catalogue.,FALSE,FALSE,"(4, 19, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Compared to pDST, the sensitivity of drug susceptibilities by the GenoMycAnalyzer for first-line drugs ranged from 95.9% for rifampicin (95% CI 94.8–96.7%) to 79.6% for pyrazinamide (95% CI 76.9–82.2%), whereas those for second-line drugs ranged from 98.2% for levofloxacin (95% CI 90.1–100.0%) to 74.9% for capreomycin (95% CI 69.3–80.0%).",FALSE,FALSE,"(66, 81, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,The specificity of drug susceptibilities by the GenoMycAnalyzer ranged from 98.7% for amikacin (95% CI 97.8–99.3%) to 79.5% for ethionamide (95% CI 76.4–82.3%).,FALSE,FALSE,"(48, 63, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"GenoMycAnalyzer also perfectly predicted lineages for 1,935 MTBC and spoligotypes for 54 MTBC.",FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"GenoMycAnalyzer offers both web-based and graphical user interfaces, which can help biologists with limited access to high-performance computing systems or limited bioinformatics skills.",FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"By streamlining the interpretation of WGS data, the GenoMycAnalyzer has the potential to significantly impact TB management and contribute to global efforts to combat this infectious disease.",FALSE,FALSE,"(52, 67, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,GenoMycAnalyzer is available at http://www.mycochase.org.,FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"In this study, we developed GenoMycAnalyzer, a web-based software program that integrates functions for the identification of MTBC and NTM species and their lineages and spoligotype prediction, variant calling, annotation, drug resistance prediction, and visualization.",FALSE,FALSE,"(28, 43, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,The performance of the GenoMycAnalyzer pipeline was evaluated using publicly available WGS data.,FALSE,FALSE,"(23, 38, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,The receiver operating characteristic (ROC) curve and area under the curve (AUC) were used to compare the predictive values of the WHO mutational catalogue and GenoMycAnalyzer datasets.,FALSE,FALSE,"(160, 175, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,The GenoMycAnalyzer is accessible at https://www.mycochase.org/.,FALSE,FALSE,"(4, 19, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,The manual for the software can be found via the “help” tab on the GenoMycAnalyzer website and is accessible without the need to register or log in.,FALSE,FALSE,"(67, 82, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Additionally, the source code for the data processing pipeline is available in the GitHub repository at https://github.com/IRCGP-Lab/GenoMycAnalyzer_Source.",FALSE,FALSE,"(133, 148, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,The GenoMycAnalyzer server encrypts all transmissions using the Fernet module from the cryptography package (https://github.com/pyca/cryptography).,FALSE,FALSE,"(4, 19, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,GenoMycAnalyzer is a freely available web-based pipeline for users to analyze Mycobacterium genomes.,FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,The unique features of the GenoMycAnalyzer are listed in Table 1.,FALSE,FALSE,"(27, 42, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"The GenoMycAnalyzer consists of five sequential steps: 1) pre-processing and quality control, 2) species identification and molecular typing, 3) variant calling and annotation, 4) gDST, and 5) visualization and report generation (Fig.",FALSE,FALSE,"(4, 19, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"GenoMycAnalyzer ingests single-end or paired-end fastq files generated by Illumina instruments as input, and supports the multiple file uploads and batch analyses.",FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"In the pre-processing step, GenoMycAnalyzer removes sequencing adaptors, low-quality bases, and sequencing reads originating from the host genome.",FALSE,FALSE,"(28, 43, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"If the isolate is predicted to be MTBC, GenoMycAnalyzer is used to perform subsequent analyses, such as lineage and spoligotype prediction, variant calling, annotation, and RAV identification.",FALSE,FALSE,"(40, 55, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,The GenoMycAnalyzer is available at http://www.mycochase.org.,FALSE,FALSE,"(4, 19, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Table 1Features of GenoMycAnalyzerFeatureDescriptionQuality control● Provide various quality control statistics, including sequencing depth and mapping statusIdentification● Identify MTBC and NTM at species levels based on Kraken2● Provide improved species prediction based on a custom-built databaseMolecular typing● Provide lineage prediction based on genome-wide SNPs● Provide spoligotype based on the direct repeat locusGenotypic DST● Provide gDST results for 15 antituberculosis drugs using the WHO mutational catalogue● Detection of large deletions associated with drug resistanceVisualization● Detected RAVs are visualized in a Circos plot, along with the sequencing depth of the corresponding gene● Integrate the IGV browser to visualize and review the detected variantsReport● Provide pdf formatted report with sample details, assay details, and genomic characteristics● Users can edit additional comment in the reportFlexibility● Users can modify the analysis parameters● Users can add newly discovered RAVs to the knowledge databaseFig.",FALSE,FALSE,"(19, 34, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,1GenoMycAnalyzer pipelines.,FALSE,FALSE,"(1, 16, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"A The GenoMycAnalyzer platform includes five modules: pre-processing, identification, variant calling, genotypic DST, and visualization and report.",FALSE,FALSE,"(6, 21, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,(B-D) Example of WGS analyzed by GenoMycAnalyzer.,FALSE,FALSE,"(33, 48, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"D The reads mapping status of gyrA p.D94G, which confers resistance to fluoroquinolone, is shown in IGV implemented in GenoMycAnalyzer",FALSE,FALSE,"(119, 134, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,Features of GenoMycAnalyzer,FALSE,FALSE,"(12, 27, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,GenoMycAnalyzer pipelines.,FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"The GenoMycAnalyzer knowledge database comprises the 13,221 unique mutations reported in the WHO mutational catalogue, including 1,149 group 1 and 2 mutations known to confer drug resistance [10].",FALSE,FALSE,"(4, 19, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"To evaluate the predictive performance of the GenoMycAnalyzer for gDST, we analyzed 5,473 MTBC genomes with pDST results for at least one antituberculosis drug.",FALSE,FALSE,"(46, 61, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Overall, the GenoMycAnalyzer gDST for first-line drugs exhibited excellent predictive values (Fig.",FALSE,FALSE,"(13, 28, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Each row and column represents the resistance-associated gene and strain, respectivelyTable 2Performances of GenoMycAnalyzer for genotypic drug susceptibility testingDrugPhenotypically resistantPhenotypically susceptiblePerformancesbRAVaTotalRAVaTotalSensitivity(95% CI)Specificity(95% CI)PPV(95% CI)NPV(95% CI)PresentAbsentPresentAbsentRifampicin1688731761933315340895.9%(94.8%-96.7%)97.3%(96.7%-97.8%)94.8%(93.7%-95.7%)97.9%(97.3%-98.3%)Isoniazid18271812008713075314691.0%(89.7%-92.2%)97.7%(97.2%-98.2%)96.3%(95.3%-97.0%)94.4%(93.7%-95.1%)Ethambutol99811211102843201348589.9%(88.0%-91.6%)91.9%(90.9%-92.7%)77.9%(75.8%-79.7%)96.6%(96.0%-97.2%)Pyrazinamide747191938892276236579.6%(76.9%-82.2%)96.2%(95.4%-97.0%)89.4%(87.2%-91.2%)92.3%(91.3%-93.1%)Levofloxacin531542485098.2%(90.1%-100.0%)96.0%(86.3%-99.5%)96.4%(87.2%-99.0%)98.0%(87.3%-99.7%)Moxifloxacin1371315011856067891.3%(85.6%-95.3%)82.6%(79.5%-85.4%)53.7%(49.5%-58.0%)97.7%(96.2%-98.6%)Amikacin21345258141042105682.6%(77.4%-87.0%)98.7%(97.8%-99.3%)93.8%(90.0%-96.3%)95.9%(94.7%-96.8%)Capreomycin20067267421104114674.9%(69.3%-80.0%)96.3%(95.1%-97.4%)82.6%(77.8%-86.6%)94.3%(93.1%-95.3%)Kanamycin46539504251129115492.3%(89.6%-94.4%)97.8%(96.8%-98.6%)94.9%(92.7%-96.5%)96.7%(95.5%-97.5%)Streptomycin7622169781102176228677.9%(75.2%-80.5%)95.2%(94.2%-96.0%)87.4%(85.2%-89.3%)91.0%(90.0%-91.9%)Ethionamide2807335315861176979.3%(74.7%-83.4%)79.5%(76.4%-82.3%)63.9%(60.4%-67.3%)89.3%(87.2%-91.2%)aPresent is the number of isolates with resistance-associated variants that overlap with high-confidence variants (grade 1 or 2) of the WHO mutational catalogueRAV resistance-associated variantbTo calculate the predictive performances of GenoMycAnalyzer, pDST was assumed to be the gold standardPPV positive predictive value, NPV negative predictive value",FALSE,FALSE,"(109, 124, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,Performances of GenoMycAnalyzer for genotypic drug susceptibility testing,FALSE,FALSE,"(16, 31, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"bTo calculate the predictive performances of GenoMycAnalyzer, pDST was assumed to be the gold standard",FALSE,FALSE,"(45, 60, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Next, we calculated the differences in AUC between the GenoMycAnalyzer and WHO mutational catalogue datasets and found that the predictive values for pyrazinamide, levofloxacin, and kanamycin were significantly better than those reported in the WHO mutational catalogue (Additional file 1: Table S5).",FALSE,FALSE,"(55, 70, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"The predictive values for the remaining six drugs were not significantly different from those reported in the WHO mutational catalogue, suggesting the non-inferiority of the GenoMycAnalyzer (Additional file 1: Table S5).",FALSE,FALSE,"(174, 189, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"To this end, we further analyzed isolates for which GenoMycAnalyzer predicted resistance while pDST was reported as susceptible (false positive; FP), and vice versa (false negative; FN) using TBProfiler (Additional file 3: Table S6) [19].",FALSE,FALSE,"(52, 67, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"GenoMycAnalyzer called 74 FP predictions for isoniazid, and all of them had RAVs corresponding to group 1 or 2 mutations: katG p.S315T (n = 24), fabG1 c.-15C > T (n = 22), fabG1 c.-8 T > C (n = 14), fabG1 p.L203L (n = 7), fabG1 c.-8 T > A (n = 3), katG p.P429fs (n = 2), katG p.199 fs (n = 1), and katG p.Q471* (n = 1).",FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Similarly, all 101 FP predictions for rifampicin by GenoMycAnalyzer had RAVs corresponding to group 1 or 2 mutations, of which 88 (87.1%) were concordant with those of TBProfiler.",FALSE,FALSE,"(52, 67, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Notably, most variants detected in isolates predicted to be resistant by TBProfiler were also detected using GenoMycAnalyzer (n = 105, 80.8%); however, they were group 3 (uncertain significance) mutations (n = 98) or mutations not included in the WHO mutational catalogue (n = 7).",FALSE,FALSE,"(109, 124, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Regarding rifampicin, 62 of the 73 FN predictions made by GenoMycAnalyzer (84.9%) were concordant with those made by TBProfiler.",FALSE,FALSE,"(58, 73, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"GenoMycAnalyzer identified 25 large deletions in katG (0.5%), 58 in pncA (1.8%), 69 in gid (2.1%), and nine in ethA (0.8%).",FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"In contrast, when large deletions were predicted using DELLY, the number of large deletions detected was higher than that identified using the GenoMycAnalyzer: 114 in katG (2.2%), 36 in pncA (1.1%), 90 in gid (2.8%), and 33 in ethA (2.9%).",FALSE,FALSE,"(143, 158, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Most large deletions detected by the GenoMycAnalyzer (63.0%) overlapped with those detected by DELLY, whereas 60 large deletions were specific to the GenoMycAnalyzer (Fig.",FALSE,FALSE,"(37, 52, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Manual inspection using IGV confirmed that all deletions detected by the GenoMycAnalyzer were true positives; however, only 35.1% of the DELLY-specific deletions were true positives (Fig.",FALSE,FALSE,"(73, 88, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Comparisons of large deletions with the pDST results revealed that GenoMycAnalyzer had a PPV of 100% for isoniazid, 93.1% for pyrazinamide, 79.7% for streptomycin, and 44.4% for ethionamide, whereas DELLY had a PPV of 71.9% for isoniazid, 83.3% for pyrazinamide, 75.6% for streptomycin, and 24.2% for ethionamide (Additional file 1: Table S8).",FALSE,FALSE,"(67, 82, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"The sensitivity of the GenoMycAnalyzer gDST, including large deletions, improved to 92.0, 84.5, 83.3, and 80.2% for isoniazid, pyrazinamide, streptomycin, and ethionamide, respectively.Fig.",FALSE,FALSE,"(23, 38, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,3Evaluation of large deletions detected by GenoMycAnalyzer and DELLY.,FALSE,FALSE,"(43, 58, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,A Venn diagram of the large deletions detected by GenoMycAnalyzer and DELLY.,FALSE,FALSE,"(50, 65, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"In each example, the top (1), middle (2), and bottom (3) panels represent large deletions detected by GenoMycAnalyzer only, both tools, and DELLY only, respectively.",FALSE,FALSE,"(102, 117, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,GenoMycAnalyzer detects large deletions at the gene level.,FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,Evaluation of large deletions detected by GenoMycAnalyzer and DELLY.,FALSE,FALSE,"(42, 57, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"To identify MTBC and NTM at the species level, GenoMycAnalyzer was integrated with the Kraken2 and Braken software [26].",FALSE,FALSE,"(47, 62, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"The GenoMycAnalyzer reliably distinguished between MTBC and NTM at the species level, achieving an accuracy of 98.8% (1,268 concordant results out of 1,284 isolates), whereas the accuracy of the Kraken2 built-in database was 90.0% (1,156 concordant results out of 1,284 isolates) (Additional file 1: Table S9).",FALSE,FALSE,"(4, 19, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Furthermore, the GenoMycAnalyzer successfully identified isolates that had not previously been identified at the species level in the NCBI database.",FALSE,FALSE,"(17, 32, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"CF00315-00498, in which the GenoMycAnalyzer was identified as M.",FALSE,FALSE,"(28, 43, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"However, at the subspecies level, the identification performance of GenoMycAnalyzer was significantly lower than its species-level identification performance (508 concordant results out of 803 isolates; 63.3%) (Additional file 1: Table S10).",FALSE,FALSE,"(68, 83, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Although incorrect classifications at the subspecies level were identified within the same species (Additional file 1: Table S10), these results suggest that GenoMycAnalyzer subspecies identification may not be optimal.",FALSE,FALSE,"(158, 173, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Therefore, GenoMycAnalyzer reports MTBC and NTM at the species level without further subspecies identification.",FALSE,FALSE,"(11, 26, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"To evaluate the accuracy of the lineage-prediction module implemented in GenoMycAnalyzer, we analyzed 1,935 MTBC isolates with phylogenetically determined lineages [31].",FALSE,FALSE,"(73, 88, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,GenoMycAnalyzer predicts spoligotypes based on 43 spacer sequences of the direct repeat locus in the MTBC genome.,FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Notably, spoligotype predictions using the GenoMycAnalyzer were concordant with the laboratory-determined spoligotypes for all isolates, resulting in an accuracy of 100% (Additional file 1: Table S12).",FALSE,FALSE,"(43, 58, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"In this study, we present a high-confidence automated bioinformatic tool we dubbed the GenoMycAnalyzer.",FALSE,FALSE,"(87, 102, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"GenoMycAnalyzer also offers species-level identification of MTBC and NTM, prediction of the MTBC lineage and spoligotype, and visualization of the detected variants.",FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Group 1 and 2 mutations present in the catalogue accurately predicted resistance and strongly correlated with pDST for most drugs [10], and GenoMycAnalyzer reports strains harboring group 1 or 2 as resistant.",FALSE,FALSE,"(140, 155, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Using the GenoMycAnalyzer, we confirmed the excellent discriminative ability of drug resistance for most antituberculosis drugs, even in an independent large dataset.",FALSE,FALSE,"(10, 25, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Specifically, the AUC of GenoMycAnalyzer showed equivalent (rifampicin, isoniazid, ethambutol, moxifloxacin, amikacin, and capreomycin) or better (pyrazinamide, levofloxacin, and kanamycin) prediction performances than those reported by the WHO mutational catalogue, thus confirming the non-inferiority of the GenoMycAnalyzer.",FALSE,FALSE,"(25, 40, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Using WGS data, GenoMycAnalyzer successfully detected large deletions with varying frequencies in katG (0.5%), pncA (1.8%), gid (2.1%), and ethA (0.8%).",FALSE,FALSE,"(16, 31, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"In contrast, GenoMycAnalyzer uses a custom-built database that adds 107 NTM sequences, and its species identification accuracy is as high as 98.8%.",FALSE,FALSE,"(13, 28, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,The GenoMycAnalyzer has two additional functionalities that are important for mycobacterial analysis.,FALSE,FALSE,"(4, 19, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"First, the GenoMycAnalyzer includes a molecular typing function, and large-scale validation confirmed accurate lineage and spoligotype predictions.",FALSE,FALSE,"(11, 26, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Second, the GenoMycAnalyzer integrates the IGV browser to visualize the detected variants.",FALSE,FALSE,"(12, 27, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Given that most of the differences between GenoMycAnalyzer and TBProfiler results were due to group 3 variants, further evaluation of group 3 mutations is required.",FALSE,FALSE,"(43, 58, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"GenoMycAnalyzer includes a function for users to edit the knowledge database, which serves as a valuable bridge until regular database updates occur.",FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Finally, although the GenoMycAnalyzer accurately distinguished clinically important mycobacteria at the species level, further efforts are needed to improve the accuracy of subspecies identification.",FALSE,FALSE,"(22, 37, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"GenoMycAnalyzer software provides flexible and rapid analysis of WGS data from the Illumina platform to predict species, drug resistance, and molecular profiles with high accuracy.",FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"GenoMycAnalyzer also offers both web-based and GUI interfaces, which can help biologists with limited access to high-performance computing systems or limited bioinformatics skills.",FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"Ultimately, by streamlining the interpretation of WGS data, the GenoMycAnalyzer has the potential to significantly impact TB management and contribute to global efforts to combat this infectious disease.",FALSE,FALSE,"(64, 79, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,Project name: GenoMycAnalyzer.,FALSE,FALSE,"(14, 29, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,Major functions of GenoMycAnalyzer compared to other whole genome sequencing analysis tools.,FALSE,FALSE,"(19, 34, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,GenoMycAnalyzer species predictions compared to those of the NCBI report.,FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,GenoMycAnalyzer sub-species predictions compared to those of the NCBI report.,FALSE,FALSE,"(0, 15, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,Comparison of GenoMycAnalyzer spoligotype predictions with reported spoligotype for 54 MTBC isolates.Additional file 2: Table S4.,FALSE,FALSE,"(14, 29, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,Comparison of GenoMycAnalyzer spoligotype predictions with reported spoligotype for 54 MTBC isolates.,FALSE,FALSE,"(14, 29, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,"To evaluate the performance of the GenoMycAnalyzer, we collected a dataset of 8,259 Illumina raw sequence reads for which laboratory-based metadata were available from public datasets.",FALSE,FALSE,"(35, 50, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11031912,The source code for the data processing pipeline is available in the GitHub repository at https://github.com/IRCGP-Lab/GenoMycAnalyzer_Source.,FALSE,FALSE,"(119, 134, 'GenoMycAnalyzer', 'genomycanalyzer')","Whole genome sequencing, Public health and epidemiology, Infectious disease, Genetic variation"
PMC11019567,Python for Population Genomics (PyPop) is a software package that processes genotype and allele data and performs large-scale population genetic analyses on highly polymorphic multi-locus genotype data.,FALSE,FALSE,"(32, 37, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"In particular, PyPop tests data conformity to Hardy-Weinberg equilibrium expectations, performs Ewens-Watterson tests for selection, estimates haplotype frequencies, measures linkage disequilibrium, and tests significance.",FALSE,FALSE,"(15, 20, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"Here, we present PyPop 1.0.0, a new major release of the package, which implements new features using the more robust infrastructure of GitHub, and is distributed via the industry-standard Python Package Index.",FALSE,FALSE,"(17, 22, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"PyPop (Python for Population Genomics) was initially developed between 2002 and 2007 (8, 9) as a Python 2-based framework that performed multiple population genetic analyses on highly-polymorphic, multilocus genotype data, and generated both standardized, “publication ready” text-formatted outputs and machine-readable XML outputs, allowing for further downstream analyses and meta-analyses.",FALSE,FALSE,"(0, 5, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"A standard PyPop analysis is initiated by running the “pypop” command-line program that is supplied with one or more plaintext input “population” or “dataset” files (with the suffix “.pop”), along with a plaintext input configuration file (with the suffix “.ini”).",FALSE,FALSE,"(11, 16, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"The input configuration file defines both the expected input format, as well as the specific analyses that will be run, including tests of Hardy-Weinberg equilibrium expectations, Ewens-Watterson tests of selection, and estimation of haplotype frequencies and linkage disequilibrium [a full list of the configuration options is available in the PyPop User Guide (10)].",FALSE,FALSE,"(345, 350, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"These primary analyses can be aggregated to generate cross-dataset meta analyses using “popmeta”, another tool in the PyPop suite.",FALSE,FALSE,"(118, 123, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"Here, we describe PyPop version 1.0.0, which is built using Python 3 and includes new features and improvements as well as a new development platform.",FALSE,FALSE,"(18, 23, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,We first document the ongoing use of PyPop in the immunogenetics and other research communities in the years since the last release of PyPop (version 0.7.0).,FALSE,FALSE,"(37, 42, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"We close by describing features in development, as well the porting of the project to GitHub to support future Python versions and new machine architectures, providing a stable home for PyPop to evolve as a community resource.",FALSE,FALSE,"(186, 191, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"Since the first public release of the software in 2003 and the subsequent publication of descriptions in 2003 (8) and 2007 (9), PyPop has been in regular and continuous use within the HLA and the larger genomics communities, as shown in an analysis of Google Scholar citations (Figure 1).",FALSE,FALSE,"(128, 133, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"This analysis estimates that there have been 433 unique citations of PyPop since its inception (134 for the 2003 paper alone, 220 for the 2007 paper, and 79 for both).",FALSE,FALSE,"(69, 74, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"PyPop has been applied extensively within the immunogenetics community since its first release, as expected given its origins as part of the 13th International Histocompatibility Workshop (IHWS) in 2002 (11).",FALSE,FALSE,"(0, 5, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"A notable early meta-analysis of the action of natural selection on HLA polymorphism across 497 populations (12), relied heavily on PyPop 0.7.0 analyses and has 360 citations in Google Scholar at the time of writing.",FALSE,FALSE,"(132, 137, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,Number of unique citations over time for the two previous PyPop publications: Pacific Symposium in Biocomputing (PSB) (8) and Tissue Antigens (9).,FALSE,FALSE,"(58, 63, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,Some publications cited both PyPop papers.,FALSE,FALSE,"(29, 34, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"However, PyPop has been used in many studies, far from its home research community.",FALSE,FALSE,"(9, 14, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,These two examples illustrate the wide utility of PyPop as a computational population genomics resource.,FALSE,FALSE,"(50, 55, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"The conditional asymmetric linkage disequilibrium (ALD) measures, first described by Thomson and Single (15), are the major new analytic feature of PyPop 1.0.0.",FALSE,FALSE,"(148, 153, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"Previous PyPop versions computed two measures of overall linkage disequilibrium: D’ (16), which uses the product of pairwise allele frequencies to weight the individual haplotype-level coefficients of LD, and Wn  (17), which is a multi-allelic extension of the “r” correlation measure commonly used for LD with bi-allelic SNPs.",FALSE,FALSE,"(9, 14, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"Comparison of the default text-based output for a single two-locus pairwise LD measures for a pre-1.0.0 version (a) and 1.0.0 version (b) of PyPop, which include the new ALD measures, W12  and W21 , denoted by ALD_1_2 and ALD_2_1 in the output, respectively.",FALSE,FALSE,"(141, 146, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"These ALD measures, computed using PyPop, have been used in anthropological studies dissecting LD in human populations (18, 19); studies of permissible mismatches in HLA donor registries (20); and studies of HLA haplotypes and amino acid motifs that predispose for disease (21).",FALSE,FALSE,"(35, 40, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"Since the major release of PyPop 0.7.0 in 2008, the allele-name nomenclatures for MHC and HLA genes have changed significantly.",FALSE,FALSE,"(27, 32, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"This nomenclature change also means that much longer HLA allele names (eg., A*02:01:01:134Q or DPB1*1372:01:01:02) are now valid, and PyPop can continue to process such data.",FALSE,FALSE,"(134, 139, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"In PyPop 1.0.0, a two locus haplotype of alleles at two loci, A and B respectively, is represented as A~B, where this haplotype had been represented as A:B in earlier PyPop releases.",FALSE,FALSE,"(3, 8, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"Although previously there was nothing actively preventing a user of PyPop from using the 2010 HLA/MHC nomenclature for PyPop input data, PyPop 0.7.0’s separation of haplotype elements with colons meant that a “:” within an allele name could lead to ambiguous output.",FALSE,FALSE,"(68, 73, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"We introduced changes in version 1.0.0 to seamlessly handle the 2010 nomenclature, and now PyPop output includes the GL String ‘~’ separator by default, facilitating use of the output in publications or further downstream analyses (Table 2).",FALSE,FALSE,"(91, 96, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"PyPop’s capacity for “custom binning”, which combines allele-names into specific categories for analysis, is now available on all platforms.",FALSE,FALSE,"(0, 5, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,PyPop custom binning is not restricted to these specific community-defined examples; variant names can be combined into any user-defined category for PyPop analysis.,FALSE,FALSE,"(0, 5, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,Extract of an example PyPop “CustomBinning” filter that could be included within the configuration “.ini” file for a PyPop run.,FALSE,FALSE,"(22, 27, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"When the filter is applied, any alleles in the dataset that are in a group will be converted to the group identifier for PyPop analysis.",FALSE,FALSE,"(121, 126, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"PyPop analyses are always output as machine-readable XML files, with one XML file per population or dataset.",FALSE,FALSE,"(0, 5, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"Previous versions of PyPop included a feature to aggregate these individual dataset or population-level XML files into a set of files in tab-separated value (TSV) format, suitable for input into spreadsheets or other downstream software (Table 3).",FALSE,FALSE,"(21, 26, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"In PyPop 1.0.0, we have overhauled and re-tooled the output mechanism for general use.",FALSE,FALSE,"(3, 8, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"These changes should increase the utility of PyPop for meta-analyses in a wider range of research use-cases, particularly for studies that need to aggregate analyses where haplotypes were estimated at more than four loci.",FALSE,FALSE,"(45, 50, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,When PyPop development started in late 2001 Python was at version 2.,FALSE,FALSE,"(5, 10, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"Soon after the last release of PyPop (0.7.0) in 2008, Python 3 was released.",FALSE,FALSE,"(31, 36, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,Python 3 unfortunately introduced breaking changes (breaking the existing PyPop code).,FALSE,FALSE,"(74, 79, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"With the end-of-life of Python 2 in 2020, migration from PyPop to Python 3 became an imperative.",FALSE,FALSE,"(57, 62, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"In addition to the new scientific features described above, and the desired transition to Python 3, other major goals of the PyPop 1.0.0 release were (a) to improve ease of installation and the overall experience for end-users, (b) to make it easier to contribute to PyPop, and (c) reduce “technical debt” (32) and thus improve overall project longevity.",FALSE,FALSE,"(125, 130, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"In 2013 we migrated the source code version control system of PyPop from an internal Concurrent Versions System (CVS) repository to Git, and subsequently imported it as a public project on the GitHub platform.",FALSE,FALSE,"(62, 67, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"Apart from its direct utility in detecting regressions introduced during development, this test suite has resulted in a wider set of configuration (“.ini”) and data (“.pop”) files that provide examples for end-users of PyPop to emulate.",FALSE,FALSE,"(219, 224, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"These wheels include, for the first time, an official pre-compiled MacOS X version of PyPop, on both Intel (x86) and Apple Silicon (arm64) architectures.",FALSE,FALSE,"(86, 91, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,This vastly simplifies installation for end users who can install PyPop directly from PyPI via a single “pip install pypop-genomics” command.,FALSE,FALSE,"(66, 71, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"The previous version of the PyPop User Guide (10) was written using DocBook XML (41) which, while powerful, has a steep learning curve.",FALSE,FALSE,"(28, 33, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,PyPop development continues beyond this 1.0.0 release.,FALSE,FALSE,"(0, 5, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"A preliminary, but incomplete implementation is already contained within PyPop 1.0.0 for alpha testing, but should not be used for production analyses.",FALSE,FALSE,"(73, 78, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"Since the last release 16 years ago, PyPop has been in active and continuous use across a range of research communities.",FALSE,FALSE,"(37, 42, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"Despite a relative stasis in development during that period, PyPop has illustrated its durability as a framework for producing standardized reports for population genomics analyses.",FALSE,FALSE,"(61, 66, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"Spaaks, for contributions to the PyPop code base, software testing and documentation.",FALSE,FALSE,"(33, 38, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11019567,"We thank the Histocompatibility, Immunogenetics and Disease Profiling Laboratory in the Department of Pathology at Stanford University Medical School for support in upgrading PyPop to enable analysis of colon-delimited allele names and increase its multi-locus analysis capacity as part of the 17th International HLA & Immunogenetics Workshop.",FALSE,FALSE,"(175, 180, 'PyPop', 'pypop')","Immunoproteins and antigens, Population genomics, Population genetics, Mapping, Immunogenetics"
PMC11010338,"We develop a Python tool called PySmooth, that offers an easy-to-use command line interface for the removal and correction of genotyping errors.",FALSE,FALSE,"(32, 40, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,PySmooth uses the approach of a previous tool called SMOOTH with some modifications.,FALSE,FALSE,"(0, 8, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"PySmooth provides additional features such as imputing missing data, better user-friendly usage, generates summary and visualization files, has flexible parameters, and handles more genotype codes.",FALSE,FALSE,"(0, 8, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,PySmooth is available at https://github.com/lncRNAAddict/PySmooth.,FALSE,FALSE,"(0, 8, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"Here, we present a Python implementation of SMOOTH called PySmooth which offers an easy-to-use command line interface and solves the drawbacks mentioned above.",FALSE,FALSE,"(58, 66, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"PySmooth reads the input genotype file and identifies singletons based on the algorithm described in SMOOTH with some modifications to allow four genotype codes, and flexible parameters.",FALSE,FALSE,"(0, 8, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"Unlike SMOOTH which doesn’t correct the singletons and missing data, PySmooth corrects genotype errors using a k-nearest algorithm [6].",FALSE,FALSE,"(69, 77, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"At each step, PySmooth generates summary files and visualizations that can be inspected by the user for further interpretation.",FALSE,FALSE,"(14, 22, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,PySmooth was implemented in Python 3.8.,FALSE,FALSE,"(0, 8, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,PySmooth detects the unique number of chromosomes and runs the algorithm separately on each chromosome.,FALSE,FALSE,"(0, 8, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,PySmooth primarily processes the input file in three stages.,FALSE,FALSE,"(0, 8, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"In the first stage, PySmooth inspects the input genotype file (Fig.",FALSE,FALSE,"(20, 28, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"In the second stage, PySmooth assigns a singleton score (Si) to a marker locus i by comparing the genotype code at locus i with genotype codes within a defined number of loci L flanking locus i on either side.",FALSE,FALSE,"(21, 29, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,1Example files of PySmooth.,FALSE,FALSE,"(18, 26, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,Example files of PySmooth.,FALSE,FALSE,"(17, 25, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,Same values of the weights used in SMOOTH [1] are used in PySmooth.,FALSE,FALSE,"(58, 66, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"Unlike SMOOTH, PySmooth provides the user an option to input the thresholds and the gap allowing experimentation with different values for thresholds and gap.",FALSE,FALSE,"(15, 23, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"After the second stage where the singletons are identified, PySmooth generates a new genotype file with the singletons marked as “S” and summary file that indicates how many of each original genotype code were switched to singleton “S” (Fig.",FALSE,FALSE,"(60, 68, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"In the third stage, PySmooth imputes the missing genotype and the singleton using a k-nearest neighbor algorithm [6] with a default value of k = 30.",FALSE,FALSE,"(20, 28, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,The default value of 30 is chosen because 30 closest neighbors are used to score singletons in PySmooth.,FALSE,FALSE,"(95, 103, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"After the third stage, PySmooth generates the corrected genotype file along with bar plot, heatmap, and a summary file.",FALSE,FALSE,"(23, 31, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,The summary files generated by PySmooth can be opened as excel spreadsheets and investigated further by the users.,FALSE,FALSE,"(31, 39, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,2Example color-coded heatmap and bar plots generated by PySmooth.,FALSE,FALSE,"(56, 64, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"After singletons identification by PySmooth, the heatmap is shown in (b), and after genotype correction, the heatmap is shown in (c).",FALSE,FALSE,"(35, 43, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,Example color-coded heatmap and bar plots generated by PySmooth.,FALSE,FALSE,"(55, 63, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"PySmooth can run on windows, Linux, MacOs, and computing cluster systems with python and required python dependencies installed.",FALSE,FALSE,"(0, 8, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,PySmooth offers an easy-to-use command line interface to run a complete analysis through one main script called “run_smooth.py”.,FALSE,FALSE,"(0, 8, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"To run PySmooth analysis, the user can simply execute the following python command.",FALSE,FALSE,"(7, 15, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338," PySmooth also offers several options to control the name of the output files, the chromosomes to be analyzed, number of k-nearest neighbors, thresholds, and gap values for singletons identification as shown below with options -o, -c, -l, -u, -g, -k, respectively.",FALSE,FALSE,"(1, 9, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338," The above command executes PySmooth for three chromosomes chr1, chr2, and chr3, and uses the number of k-nearest neighbors, upper threshold, lower threshold, and gap values for singletons identification as 34, 0.98, 0.80, and 0.02 respectively.",FALSE,FALSE,"(28, 36, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,We tested PySmooth on an example input genotype file named “my_genotype_file.csv” (Additional file 1).,FALSE,FALSE,"(10, 18, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"If the command “python run_smooth.py -i my_genotype_file.csv -o my_output” is executed, since this specific input genotype file contains only one chromosome (chr1), PySmooth generates three output summary files (Additional file 1) that contain percentages of homozygous, heterozygous calls for each individual for the raw genotype file, after singleton detection, and after error correction, respectively.",FALSE,FALSE,"(165, 173, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"Finally, PySmooth also outputs the genotype file with singletons and the final genotype file after correction of the singletons.",FALSE,FALSE,"(9, 17, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"To compare the accuracy of PySmooth and SMOOTH in predicting singletons in a genotype file, we simulated an F2 population consisting of 120 individuals and six chromosomes with 5720 marker locations.",FALSE,FALSE,"(27, 35, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,PySmooth and SMOOTH were both applied to the same genotype file that contains errors and missing values.,FALSE,FALSE,"(0, 8, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,We found that PySmooth achieved superior accuracy by correctly predicting 96.64% of the introduced errors as singletons compared to 73.32% by SMOOTH.,FALSE,FALSE,"(14, 22, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,PySmooth predicted only 0.03% of the correct genotype labels as singletons compared to 24% misprediction by SMOOTH.,FALSE,FALSE,"(0, 8, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"When the error rate was increased to 30%, PySmooth was able to recover 82.47% of the introduced errors as singletons compared to 68% by SMOOTH.",FALSE,FALSE,"(42, 50, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,These results show that PySmooth performs better than SMOOTH.,FALSE,FALSE,"(24, 32, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"Our tool PySmooth offers several improvements over the SMOOTH tool by allowing a user-friendly command interface, summary and visualization files, more genotype codes, flexible parameters, and correcting genotype errors.",FALSE,FALSE,"(9, 17, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,The main limitation of the current version of PySmooth is the lack of the feature of parallel processing to reduce computation time in large genotype files.,FALSE,FALSE,"(46, 54, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"However, this can be overcome manually with the current version of PySmooth.",FALSE,FALSE,"(67, 75, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,Users can execute PySmooth in computing clusters or systems with multiple cores for different chromosomes simultaneously in parallel to reduce computing time.,FALSE,FALSE,"(18, 26, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"For this, the user must manually create different files that correspond to different chromosomes and execute PySmooth on these files separately.",FALSE,FALSE,"(109, 117, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"In the future version of PySmooth, an automated multi-core processing feature will be incorporated.",FALSE,FALSE,"(25, 33, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11010338,"In future versions of PySmooth, we plan to add more methods which the user can choose from.",FALSE,FALSE,"(22, 30, 'PySmooth', 'pysmooth')","DNA polymorphism, Functional, regulatory and non-coding RNA, Genotype and phenotype, Mapping"
PMC11060868,"Here, we present rnaCrosslinkOO (RNA Crosslink Object-Oriented), a novel software package for the comprehensive analysis of data derived from the COMRADES (Crosslinking of Matched RNA and Deep Sequencing) method.",FALSE,FALSE,"(17, 31, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,rnaCrosslinkOO offers a comprehensive pipeline from raw sequencing reads to the identification and comparison of RNA structural features.,FALSE,FALSE,"(0, 14, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,"rnaCrosslinkOO also enables comparisons between conditions, the identification of inter-RNA interactions, and the incorporation of reactivity data to improve structure prediction.",FALSE,FALSE,"(0, 14, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,"rnaCrosslinkOO is freely available to noncommercial users and implemented in R, with the source code and documentation accessible at https://CRAN.R-project.org/package=rnaCrosslinkOO.",FALSE,FALSE,"(0, 14, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,"We present the rnaCrosslinkOO (RNA Crosslinking Object-Oriented) R package, a novel and versatile R package, that focusses on the downstream analysis of RNA crosslinking data.",FALSE,FALSE,"(15, 29, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,"Although the package was designed to analyze COMRADES data, the rnaCrosslinkOO R package will accept any crosslinking data presented in the correct format.",FALSE,FALSE,"(64, 78, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,"To process these raw sequencing reads for downstream analysis with the rnaCrosslinkOO package, we have developed a Nextflow (Di Tommaso et al.",FALSE,FALSE,"(71, 85, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,The rnaCrosslinkOO package can be installed using install.packages in R.,FALSE,FALSE,"(4, 18, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,A full vignette and usage documentation can be found on the CRAN website (https://CRAN.R-project.org/package=rnaCrosslinkOO) and through the vignette function.,FALSE,FALSE,"(109, 123, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,Loading the data into the rnaCrosslinkOO package requires; (i) Sample metadata in the form of a tab-separated table.,FALSE,FALSE,"(26, 40, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,rnaCrosslinkOO.,FALSE,FALSE,"(1, 15, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,(a) Input for rnaCrosslinkOO and the main slots of the rnaCrosslinkDataSet object displayed with grey boxes with the functions used to access the slots in green.,FALSE,FALSE,"(14, 28, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,"(a–i) Schematics and examples of steps in the rnaCrosslinkOO package, further detail for each step can be found in the main text.",FALSE,FALSE,"(46, 60, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,"In rnaCrosslinkOO, an adjacency matrix is created for all chimeric reads based on the nucleotide difference between their g values.",FALSE,FALSE,"(3, 17, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,To allow the user to fold smaller parts of the RNA of interest rnaCrosslinkOO employs the plotDomains method.,FALSE,FALSE,"(63, 77, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,"To demonstrate the functionality of rnaCrosslinkOO, Fig.",FALSE,FALSE,"(36, 50, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,S2F is very similar to the canonical structure of the 3ʹm domain which has been predicted by rnaCrosslinkOO.,FALSE,FALSE,"(93, 107, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC11060868,The rnaCrosslinkOO R package complements current pipelines by providing infrastructure for the downstream analysis of RNA crosslinking experiments.,FALSE,FALSE,"(4, 18, 'rnaCrosslinkOO', 'rnacrosslinkoo')","RNA, Structure prediction, Nucleic acid structure analysis, Probes and primers, Small molecules"
PMC10689045,scPipe is a flexible R/Bioconductor package originally developed to analyse platform-independent single-cell RNA-Seq data.,FALSE,FALSE,"(1, 7, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"To expand its preprocessing capability to accommodate new single-cell technologies, we further developed scPipe to handle single-cell ATAC-Seq and multi-modal (RNA-Seq and ATAC-Seq) data.",FALSE,FALSE,"(105, 111, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,We demonstrate that scPipe can efficiently identify ‘true’ cells and provides flexibility for the user to fine-tune the quality control thresholds using various feature and cell-based metrics collected during data preprocessing.,FALSE,FALSE,"(20, 26, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,The scPipe package enables a complete beginning-to-end pipeline for single-cell ATAC-Seq and RNA-Seq data analysis in R.,FALSE,FALSE,"(4, 10, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"In this study, we extend scPipe (10) to enable handling of scATAC-Seq data and generation of SCE objects that can be manipulated using various SCE-friendly downstream analysis tools available in R/Bioconductor (11).",FALSE,FALSE,"(25, 31, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"scPipe is able to take scATAC-Seq reads (FASTQ format) as input, which are demultiplexed (if needed) and filtered based on quality and Ns (i.e.",FALSE,FALSE,"(0, 6, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,These improvements also allow scPipe to be used for multiome projects that collect both scRNA-Seq and scATAC-Seq on the same cells.,FALSE,FALSE,"(30, 36, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045," scPipe was developed using the R (12) / Bioconductor (13) platform, with the underlying code written in C++, R and Python with the Rcpp (14) and reticulate (15) packages used to wrap the C++ and Python code for R, respectively.",FALSE,FALSE,"(1, 7, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,Data from both UMI (Unique Molecular Identifiers) and non-UMI protocols can be handled by scPipe.,FALSE,FALSE,"(90, 96, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,Demultiplexing is performed by the sc_atac_trim_barcode() function (Figure 1A) using a similar approach to that used in scPipe for scRNA-Seq analysis.,FALSE,FALSE,"(120, 126, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,Overview of the scPipe scATAC-Seq module and its QC outputs.,FALSE,FALSE,"(16, 22, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,(B) QC plot showing the separation of ‘cell’ and ‘non-cell’ based on the fraction of fragments overlappping peaks (y-axis) vs total number of fragments (x-axis) after cell calling step of scPipe.,FALSE,FALSE,"(188, 194, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,(C) QC plot showing the separation of cell and ‘non-cell’ based on read density (y-axis) versus total number of fragments (x-axis) after cell calling step of scPipe.,FALSE,FALSE,"(158, 164, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"scPipe corrects barcodes that are not matched to the valid barcode list by allowing for one mismatched base in comparison with the valid barcode list, and counting the number of corrected barcodes in the complete dataset.",FALSE,FALSE,"(0, 6, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,This step can be run externally to scPipe and the resulting BAM file can be re-entered to the scPipe pipeline if samtools is not installed locally.,FALSE,FALSE,"(35, 41, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,This python-based capability was integrated into the scPipe R package using basilisk (20).,FALSE,FALSE,"(53, 59, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,via Cell Ranger) or scPipe generated feature matrix and fragment file is used as the main input to generate the feature × cell count matrix.,FALSE,FALSE,"(20, 26, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"It has been previously been shown that filtering cells based on multiple QC metrics is the most effective approach to do cell calling (7), and this approach has been adopted in scPipe.",FALSE,FALSE,"(177, 183, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"Another important aspect of scPipe is the ability to integrate datasets where a common barcode file is available to match the cells between SCE objects to create a combined SCE object, as occurs for example in 10X Genomics multiome experiments.",FALSE,FALSE,"(28, 34, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"We have processed the scATAC-Seq data in two ways; (i) via the Cell Ranger ATAC pipeline, and (ii) via the scPipe pipeline.",FALSE,FALSE,"(107, 113, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,We ran the scPipe scATAC-Seq pipeline on both the 20% and 80% GEMs to profile time and memory usage.,FALSE,FALSE,"(11, 17, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"We compared the clusters identified from scPipe preprocessed data to those obtained from the Cell Ranger ATAC pipeline, a popular tool for 10X scATAC-Seq preprocessing.",FALSE,FALSE,"(41, 47, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"Cell Ranger returned 5728 cells and scPipe 5599 cells after QC, with 5267 in common (Figure 2B).",FALSE,FALSE,"(36, 42, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"On the other hand, the mitochondrial contamination is lower and similar for scPipe-only called cells and those identified by scPipe in common with Cell Ranger (Figure 2C’).",FALSE,FALSE,"(76, 82, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"Moreover, ‘scPipe-only’ called cells contained counts and features that were more similar those found in common than the counts and features from ‘Cell Ranger-only’ called cells, whose distributions were concentrated towards the lower ranges for both quantities.",FALSE,FALSE,"(11, 17, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,The UMAP (28) generated from the Cell Ranger output shows that the 129 cells that appear in the Cell Ranger results but not in scPipe tend to cluster together away from the large clusters or in the margins of them (Figure 2E).,FALSE,FALSE,"(127, 133, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"In contrast, the UMAP generated from the scPipe output shows that the cells that only appear in scPipe results but not in Cell Ranger tend to be located within the main clusters (Figure 2E’).",FALSE,FALSE,"(41, 47, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,Comparing scPipe and Cell Ranger on a 10× dataset.,FALSE,FALSE,"(10, 16, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,FASTQ files were generated by Cell Ranger ARC 2.0.0 and these reads were processed by scPipe and Cell Ranger.,FALSE,FALSE,"(86, 92, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,(B) Venn diagram showing the overlap of cell barcodes detected by Cell Ranger and scPipe.,FALSE,FALSE,"(82, 88, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,(C) Box plot showing the percentage of mitochondrial gene counts in cells that are called by Cell Ranger and are common with/unique in comparison to scPipe or (C’) scPipe and are common with/unique in comparison to Cell Ranger output.,FALSE,FALSE,"(149, 155, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,(D) Scatter plot of the per cell total counts and (D’) number of features per cell obtained from Cell Ranger and scPipe in cells called in common between the two and cells that were unique to each of the two pipelines.,FALSE,FALSE,"(113, 119, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,(E) UMAP plot generated for Cell Ranger and (E’)scPipe output.,FALSE,FALSE,"(48, 54, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,Cell barcodes that only exist in (E) Cell Ranger or (E’) scPipe are highlighted in red.,FALSE,FALSE,"(57, 63, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,(F) UMAP coloured by the ground truth for Cell Ranger and (F’)scPipe.,FALSE,FALSE,"(62, 68, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"The scPipe generated output resulted in a higher ARI of 0.68 and NMI of 0.75 (Figure 2F’), indicating better concordance between the Seurat clustering and demuxlet results.",FALSE,FALSE,"(4, 10, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"Taken together, scPipe seemed to identify higher quality cells that were better separated according to the biological signal present in the data relative to the Cell Ranger processed data.",FALSE,FALSE,"(16, 22, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"To ensure flexibility, scPipe can preprocess data from a variety of different scATAC-Seq protocols that includes droplet-based and plate-based methods.",FALSE,FALSE,"(23, 29, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"scPipe can also handle combinatorial barcoding options when demultiplexing the reads, and can handle Unique Molecular Identifier (UMI) based scATAC-Seq approaches if they arise in the future.",FALSE,FALSE,"(0, 6, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"The resulting preprocessed data output by scPipe is stored in a versatile SingleCellExperiment (SCE) format, which means that the data can be further analysed downstream using SCE-object friendly tools available in R/Bioconductor.",FALSE,FALSE,"(42, 48, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,We demonstrate that data preprocessing with scPipe’s scATAC-Seq preprocessing workflow produces comparable results to those from 10×’s Cell Ranger ATAC pipeline.,FALSE,FALSE,"(44, 50, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045,"As the integration of numerous large-scale data modalities becomes more routine, scPipe provides convenient and scalable preprocessing options for both scRNA-Seq and scATAC-Seq data, allowing data integration and joint analyses.",FALSE,FALSE,"(81, 87, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC10689045," scPipe’s scATAC-Seq preprocessing module is available from Bioconductor, DOI: https://doi.org/doi:10.18129/B9.bioc.scPipe.",FALSE,FALSE,"(1, 7, 'scPipe', 'scpipe')","Gene expression, RNA-Seq, Sequencing"
PMC11510761,The three-dimensional structure of malanin was created by Swiss-model and viewed by PyMOL 2.3 (Figure 3).,FALSE,FALSE,"(84, 89, 'PyMOL', 'pymol')","Molecular modelling, Proteins, Protein structure analysis"
PMC11510761,The difference in amino acid residues in the three-dimensional structures between ricin and malanin was analyzed by PyMOL 2.3.,FALSE,FALSE,"(116, 121, 'PyMOL', 'pymol')","Molecular modelling, Proteins, Protein structure analysis"
PMC11510761,"The three-dimensional modeling overlays of malanin and ricin by PyMOL 2.3 are shown in Figure 6 in green and yellow, respectively.",FALSE,FALSE,"(64, 69, 'PyMOL', 'pymol')","Molecular modelling, Proteins, Protein structure analysis"
PMC11510761,The bonding of cys188 and cys207 in the malanin B chain and of cys188 and cys205 in the ricin B chain were analyzed by PyMOL 2.3 (Figure 7).,FALSE,FALSE,"(119, 124, 'PyMOL', 'pymol')","Molecular modelling, Proteins, Protein structure analysis"
PMC11510761,The positions of the disulfide bonds in the three-dimensional structure of malanin and ricin were analyzed by PyMOL 2.3 [74].,FALSE,FALSE,"(110, 115, 'PyMOL', 'pymol')","Molecular modelling, Proteins, Protein structure analysis"
PMC11510761,"The active sites in the primary and three-dimensional structure of malanin and ricin were analyzed by DNAMAN 9.0 and PyMOL 2.3, respectively [75,76].",FALSE,FALSE,"(117, 122, 'PyMOL', 'pymol')","Molecular modelling, Proteins, Protein structure analysis"
PMC11510761,The structure of malanin created by Swiss-model and viewed by PyMOL 2.3.,FALSE,FALSE,"(62, 67, 'PyMOL', 'pymol')","Molecular modelling, Proteins, Protein structure analysis"
PMC11510761,Comparison of the three-dimensional structure of malanin and cinnamonin III by PyMOL 2.3.,FALSE,FALSE,"(79, 84, 'PyMOL', 'pymol')","Molecular modelling, Proteins, Protein structure analysis"
PMC11510761,Comparison of the three-dimensional structures of malanin and ricin by PyMOL 2.3.,FALSE,FALSE,"(71, 76, 'PyMOL', 'pymol')","Molecular modelling, Proteins, Protein structure analysis"
PMC11510761,The bonding of cys188 and cys207 in malanin B chain with cys188 and cys205 in ricin B chain by PyMOL 2.3.,FALSE,FALSE,"(95, 100, 'PyMOL', 'pymol')","Molecular modelling, Proteins, Protein structure analysis"
PMC11510761,The difference in amino acid (AA) residues in the three-dimensional structures between ricin and malanin by PyMOL 2.3.,FALSE,FALSE,"(108, 113, 'PyMOL', 'pymol')","Molecular modelling, Proteins, Protein structure analysis"
PMC10659926,Examples are eTBLAST (http://etest.vbi.vt.edu/etblast3) and turnitin (https://www.turnitin.com/).,FALSE,FALSE,"(13, 20, 'eTBLAST', 'etblast')","Natural language processing, Literature and language"
PMC11223810,"To address this need, we introduce ChemoDOTS, an easy-to-use web server for hit-to-lead chemical optimization freely available at https://chemodots.marseille.inserm.fr/.",FALSE,FALSE,"(35, 44, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,"ChemoDOTS rapidly generates synthetically feasible, hit-focused, large, diverse chemical libraries with finely-tuned physicochemical properties via a user-friendly interface providing a powerful resource for researchers engaged in hit-to-lead optimization.",FALSE,FALSE,"(0, 9, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,"In response to this gap, we introduce the ChemoDOTS web server designed to facilitate the generation of focused virtual libraries starting from a user-defined activated fragment.",FALSE,FALSE,"(42, 51, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,"The comprehensive list of reactions used in ChemoDOTS, along with their SMARTS representations, is available in Supplementary Tables S3–S5.",FALSE,FALSE,"(44, 53, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,"(B) To test the ability to generate such compounds, the activated fragment was uploaded in SMILES format on the ChemoDOTS server.",FALSE,FALSE,"(112, 121, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,We tested the ability of ChemoDOTS to generate these compounds.,FALSE,FALSE,"(25, 34, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,"In summary, ChemoDOTS is a user-friendly web server that enables the generation and exploration of a vast chemical space around an initial hit molecule by combining molecular building blocks and predefined chemistry rules.",FALSE,FALSE,"(12, 21, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,The current version of ChemoDOTS relies on a collection of more than 500 000 BBs from MolPort and almost a million from Enamine.,FALSE,FALSE,"(23, 32, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,"However, the virtual chemical space covered by ChemoDOTS can be easily extended through the integration of additional BBs from other providers or user-defined sources.",FALSE,FALSE,"(47, 56, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,We also anticipate benefiting from users’ feedback to upgrade ChemoDOTS and to deliver a better service.,FALSE,FALSE,"(62, 71, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,"To our knowledge, ChemoDOTS is the only freely accessible functional and maintained web server to combine the design of medchem-compatible focused virtual libraries with an integrated graphical postprocessing analysis.",FALSE,FALSE,"(18, 27, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,"Our appreciation extends to Drs Sébastien Abel, Paul Brémond and Sébastien Combes for their insightful discussions about the chemical reactions used in ChemoDOTS.",FALSE,FALSE,"(152, 161, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,"Lastly, we extend our thanks to the DISC platform for providing the facilities to host the ChemoDOTS web server.",FALSE,FALSE,"(91, 100, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,The ChemoDOTS web server is freely available at https://chemodots.marseille.inserm.fr/.,FALSE,FALSE,"(4, 13, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,All scripts used in ChemoDOTS backend have been deposited on GitHub (https://github.com/iSCBTeam/ChemoDOTS).,FALSE,FALSE,"(20, 29, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC11223810,"Permanent DOI of the code used for ChemoDOTS: Backend: https://doi.org/10.6084/m9.figshare.25585089 Frontend: https://doi.org/10.6084/m9.figshare.25585092 The list of chemical functions, the list of reactions, and the final BBs from MolPort and Enamine (in SMILES format) are available via Zenodo repository at https://dx.doi.org/10.5281/zenodo.10776787.",FALSE,FALSE,"(35, 44, 'ChemoDOTS', 'chemodots')","Compound libraries and screening, Medicinal chemistry, Molecular modelling, Molecular biology, Small molecules"
PMC10787363,Project name: X-omics ACTION demonstrator multi-omics analysis workflow,FALSE,FALSE,"(14, 71, 'X-omics ACTION demonstrator multi-omics analysis workflow', 'x-omics_action_demonstrator_multi-omics_analysis_workflow')","Omics, Metabolomics, Epigenomics, Machine learning, Data visualisation"
PMC11425048,"Some of the search engines supporting this approach include MSFragger, 22 ,  23  Sage, 24  pFind3, 25  TagGraph, 26  MetaMorpheus, 27  and several others.",FALSE,FALSE,"(60, 69, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,MSFragger stands out as the mainstream search engine in shotgun proteomics.,FALSE,FALSE,"(0, 9, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"23  By default, MSFragger operates within a mass error tolerance range of −150–500 Da for peptide precursor ions in open search mode.",FALSE,FALSE,"(16, 25, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"This expansion makes constructing the MSFragger index time‐consuming and resource‐intensive, especially when considering modifications such as phosphorylation.",FALSE,FALSE,"(38, 47, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"In such cases, MSFragger's memory usage can skyrocket to hundreds of gigabytes, and the speed in open search mode notably decreases.",FALSE,FALSE,"(15, 24, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Unlike MSFragger, which necessitates a large theoretical fragment‐ion index, Dear‐PSM generates an experimental spectra index that usually requires only several hundred megabytes of memory, rendering it far more memory‐efficient than MSFragger.",FALSE,FALSE,"(7, 16, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"In contrast to MSFragger, which relies solely on hyper‐score, the dual‐score approach offers a more comprehensive means of identifying the best matching results.",FALSE,FALSE,"(15, 24, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"MSFragger and Sage address this challenge by leveraging inverted indices of theoretical fragment ions, bypassing pairwise comparisons between peptides and experimental spectra, thereby significantly expediting the search process.",FALSE,FALSE,"(0, 9, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"For subsequent peptide validation, MSFragger retains and processes search results with over 4 matched fragment ions to compute the expected value, significantly increasing the computational time required.",FALSE,FALSE,"(35, 44, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"To evaluate the performance of Dear‐PSM, we compared it with mainstream peptide search engines MSFragger and the latest open search engine, Sage.",FALSE,FALSE,"(95, 104, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,MSFragger searches all DDA files and outputs search results individually.,FALSE,FALSE,"(0, 9, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"The MSFragger and Sage search engines were set to open search mode, with the default peptide mass search range from −150 to 500 Da.",FALSE,FALSE,"(4, 13, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Red, blue, and purple denote Dear‐PSM, MSFragger, and Sage, respectively, based on data collected by Orbitrap QE HF‐X.",FALSE,FALSE,"(39, 48, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Dear‐PSM utilizes the full‐database search strategy, while MSFragger and Sage employ open search strategies.",FALSE,FALSE,"(59, 68, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"For the data from TripleTOF 6600+, Dear‐PSM, MSFragger, and Sage reported 25,015, 20,789, and 22,070 peptides, respectively.",FALSE,FALSE,"(45, 54, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,Dear‐PSM discovered 20% more peptides than MSFragger and 13% more peptides than Sage (Figure 3B).,FALSE,FALSE,"(43, 52, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Dear‐PSM, MSFragger, and Sage reported 4788, 3215, and 4764 proteins, respectively.",FALSE,FALSE,"(10, 19, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"The coverage of Dear‐PSM compared to MSFragger and Sage was 92% and 87%, respectively (Figure 3C).",FALSE,FALSE,"(37, 46, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Specifically, for data from TripleTOF 6600+, Dear‐PSM, MSFragger, and Sage reported 26,371, 24,565, and 25,911 peptides, respectively (Figure 3F).",FALSE,FALSE,"(55, 64, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Dear‐PSM covered 94% and 89% of the results reported by MSFragger and Sage, respectively (Figure 3G).",FALSE,FALSE,"(56, 65, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Dear‐PSM's peptide coverage exceeded 90% for both MSFragger and Sage, indicating its ability to replicate a substantial portion of the results from the other two search engines (Supporting Information S1: Figure S9).",FALSE,FALSE,"(50, 59, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Under the open search strategy, Dear‐PSM, MSFragger, and Sage discovered 156,754, 154,210, and 131,065 peptides, respectively.",FALSE,FALSE,"(42, 51, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Dear‐PSM achieved coverage rates of 78% and 85% compared to MSFragger and Sage, respectively.",FALSE,FALSE,"(60, 69, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Additionally, Dear‐PSM uniquely identified 33,826 peptides, while MSFragger and Sage individually identified 18,953 and 5740 peptides, respectively (Figure 4A).",FALSE,FALSE,"(66, 75, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Dear‐PSM, MSFragger, and Sage reported 14,183, 9270, and 12,151 proteins, respectively.",FALSE,FALSE,"(10, 19, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Dear‐PSM achieved coverage rates of 99% and 95% compared to MSFragger and Sage, respectively.",FALSE,FALSE,"(60, 69, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,The right subplot shows the results reported by MSFragger in the open search mode.,FALSE,FALSE,"(48, 57, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"The red and blue colors represent the distributions of Dear‐PSM and MSFragger, respectively.",FALSE,FALSE,"(68, 77, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,The red and blue curves represent the number of identified peptides by Dear‐PSM and MSFragger respectively at different q‐values.,FALSE,FALSE,"(84, 93, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"This matches closely with what MSFragger reported, showing that Dear‐PSM's findings are trustworthy.",FALSE,FALSE,"(31, 40, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,We also looked at the length distribution of peptides reported by Dear‐PSM and MSFragger.,FALSE,FALSE,"(79, 88, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Interestingly, Dear‐PSM found more peptides with over 20 amino acids compared to MSFragger (Figure 4E).",FALSE,FALSE,"(81, 90, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Comparing Dear‐PSM's full‐database search mode with MSFragger's open search mode, we sorted Hyperscores in descending order to compute Q‐values.",FALSE,FALSE,"(52, 61, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"The FDR curves of Dear‐PSM and MSFragger exhibit consistent trends, with Dear‐PSM detecting more peptides than MSFragger at a 1% q‐value threshold under the full‐database search mode (Figure 4G).",FALSE,FALSE,"(31, 40, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Under the open search mode, Dear‐PSM, MSFragger, and Sage identified 7377, 7182, and 6222 peptides, respectively, when comparing unmodified peptide sequences (Figure 5A).",FALSE,FALSE,"(38, 47, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Furthermore, Dear‐PSM covered 80% and 86% of the peptides discovered by MSFragger and Sage, respectively.",FALSE,FALSE,"(72, 81, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"When comparing phosphorylated peptides, Dear‐PSM detected 12,320 phosphorylated peptides, while MSFragger and Sage identified 11,686 and 9666 phosphorylated peptides, respectively (Figure 5B).",FALSE,FALSE,"(96, 105, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,Dear‐PSM reported 5% more phosphorylated peptides than MSFragger.,FALSE,FALSE,"(55, 64, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Results from Dear‐PSM, MSFragger, and Sage are represented by red, light blue, and dark blue, respectively.",FALSE,FALSE,"(23, 32, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Dear‐PSM, after increasing the upper limit of variable modifications, could identify peptides with up to 8 variable modifications in the PXD041271 dataset, whereas MSFragger and Sage could only detect peptides with a maximum of 3 variable modifications (Figure 5C).",FALSE,FALSE,"(164, 173, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"For instance, the number of peptides with 1 variable modification reported by Dear‐PSM, MSFragger, and Sage were 7544, 7015, and 6492, respectively (Figure 5C).",FALSE,FALSE,"(88, 97, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"The proportion reported by Dear‐PSM was consistent with that reported by MSFragger and Sage, indicating that Dear‐PSM can be used to search for and validate phosphorylated peptides (Figure 5D).",FALSE,FALSE,"(73, 82, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,We tested the running performance of Dear‐PSM and MSFragger on a desktop computer.,FALSE,FALSE,"(50, 59, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,We conducted tests using the PXD028735 dataset for Dear‐PSM's full database search and MSFragger's open search strategy.,FALSE,FALSE,"(87, 96, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"The results showed that Dear‐PSM identified 11,103,192 peptide sequences, whereas MSFragger identified 10,626,494 peptide sequences.",FALSE,FALSE,"(82, 91, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Despite Dear‐PSM searching a peptide mass range 10 times larger than MSFragger, Dear‐PSM achieved a speed 3–6 times faster than MSFragger (Figure 6A).",FALSE,FALSE,"(69, 78, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"In terms of memory consumption, MSFragger used 30–136 times more memory than Dear‐PSM, while Dear‐PSM used an experimental spectral index table to greatly reduce memory consumption (Figure 6B).",FALSE,FALSE,"(32, 41, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Although Sage saves approximately five times more memory compared to MSFragger, Dear‐PSM still consumes 6–25 times less memory than Sage (Figure 6B).",FALSE,FALSE,"(69, 78, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Red, light blue and dark blue boxes in both (A), (B) and (C) represent Dear‐PSM MSFragger, and Sage, respectively.",FALSE,FALSE,"(80, 89, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"After increasing the maximum number of variable modifications per peptide to 20, Dear‐PSM's search space expanded to 3 billion peptide sequences, while MSFragger's search space was 140 million peptide sequences (Figure 6C).",FALSE,FALSE,"(152, 161, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Dear‐PSM's search space was approximately 21 times larger than that of MSFragger, reaching the order of 1 billion.",FALSE,FALSE,"(71, 80, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Despite the immense search space, Dear‐PSM achieved a search speed 7 times faster than MSFragger and used 241 times less memory than MSFragger (Figure 6C).",FALSE,FALSE,"(87, 96, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"Dear‐PSM can reproduce results from MSFragger and Sage search engines in over 90% of cases in full database search mode, while also discovering more peptides and proteins.",FALSE,FALSE,"(36, 45, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11425048,"In performance comparisons, Dear‐PSM's search speed is 3–7 times faster than MSFragger, with memory consumption reduced by 100–200 times.",FALSE,FALSE,"(77, 86, 'MSFragger', 'msfragger')","Proteomics experiment, Proteomics, Protein modifications"
PMC11413572,"Alignments were created using the L-INS-i algorithm in MAFFT (Katoh and Standley 2013) and assessed in AliView (Larsson 2014), and phylogenetically informative sites were selected with trimAl (Capella-Gutiérrez et al.",FALSE,FALSE,"(185, 191, 'trimAl', 'trimal')","Sequence analysis, Sequencing, Sequence sites, features and motifs"
PMC8651056,"WebMaBoSS is an easy-to-use web interface for conversion, storage, simulation and analysis of Boolean models that allows to get insight from these models without any specific knowledge of modeling or coding.",FALSE,FALSE,"(0, 9, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,"The goal of WebMaBoSS is to simplify the use and the analysis of Boolean models coping with two main issues: 1) the simulation of Boolean models of intracellular processes with MaBoSS, or any modeling tool, may appear as non-intuitive for non-experts; 2) the simulation of already-published models available in current model databases (e.g., Cell Collective, BioModels) may require some extra steps to ensure compatibility with modeling tools such as MaBoSS.",FALSE,FALSE,"(12, 21, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,"With WebMaBoSS, new models can be created or imported directly from existing databases.",FALSE,FALSE,"(5, 14, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,"This application is open-source under LGPL license, and available at https://github.com/sysbio-curie/WebMaBoSS.",FALSE,FALSE,"(101, 110, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,WebMaBoSS is a user-friendly tool that simulates Boolean models available in standard format using MaBoSS tool.,FALSE,FALSE,"(0, 9, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,"What we wish to present here is an even simpler version, WebMaBoSS, which offers the possibility to study online, without any prior installation, any Boolean model, provided that they are available in standard formats.",FALSE,FALSE,"(57, 66, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,"We developed a web interface, WebMaBoSS, to target novices in modeling.",FALSE,FALSE,"(30, 39, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,WebMaBoSS can be accessed at the following address: https://maboss.curie.fr/webmaboss/.,FALSE,FALSE,"(0, 9, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,WebMaBoSS also allows the simulation of more complex tasks such as parameter sensitivity analyses.,FALSE,FALSE,"(0, 9, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,"However, this cannot be set explicitly in WebMaBoSS but can be done externally in the configuration file (.cfg) directly and then reimported in WebMaBoSS.",FALSE,FALSE,"(42, 51, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,"The compatibility with these formats enable users to directly import models, through WebMaBoSS, from public databases of qualitative models such as Cell Collective (Helikar et al., 2012) or BioModels (Le Novere et al., 2006).",FALSE,FALSE,"(85, 94, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,"As previously mentioned, an important added value of this functionality is the interoperability: users can easily build a model with software like GINsim (Gonzalez et al., 2006), Boolnet (Müssel et al., 2010) or CaSQ (Aghamiri et al., 2020), and simulate them using MaBoSS, inscribing MaBoSS and WebMaBoSS into a community combined effort to reproduce and exchange models.",FALSE,FALSE,"(296, 305, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,"WebMaBoSS allows the configuration of such servers (host, port), which immediately become accessible to all users.",FALSE,FALSE,"(0, 9, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,WebMaBoSS can be accessed through a browser at https://maboss.curie.fr/webmaboss/.,FALSE,FALSE,"(0, 9, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,"We illustrate the use of WebMaBoSS with an example of a published model of the regulation of the interleukins IL17 (Corral-Jara et al., 2021), which is accessible to guest users and already loaded into the default project of new accounts.",FALSE,FALSE,"(25, 34, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,Other model analyses and step-by-step tutorials can be found on the GitHub at the following address: https://github.com/sysbio-curie/WebMaBoSS.,FALSE,FALSE,"(133, 142, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,"To showcase a full study with WebMaBoSS, we studied a published model of T-helper cells for the regulation of IL-17A/IL-17F (Corral-Jara et al., 2021).",FALSE,FALSE,"(30, 39, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,The step-by-step tutorial showing all the functionalities of the web tool along with the interpretation of the results can be found in Supplementary File S1 and on the GitHub of WebMaBoSS (see above).,FALSE,FALSE,"(178, 187, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,WebMaBoSS interface.,FALSE,FALSE,"(0, 9, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,(A) Web server welcome page of WebMaBoSS.,FALSE,FALSE,"(31, 40, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,(B) Loading or importing a model in WebMaBoSS.,FALSE,FALSE,"(36, 45, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,WebMaBoSS can also perform sensitivity analyses to check the effect of a knock-in/knock-out of each node on the network.,FALSE,FALSE,"(0, 9, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,WebMaBoSS then ouptuts the corresponding pie chart for each simulation and the user can filter the results to verify which mutation leads to the phenotype of interest.,FALSE,FALSE,"(0, 9, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC8651056,This data can be found here: https://github.com/sysbio-curie/WebMaBoSS.,FALSE,FALSE,"(61, 70, 'WebMaBoSS', 'webmaboss')","Statistics and probability, Molecular interactions, pathways and networks, Genetic variation"
PMC11127412,"We present two new developments in the continuous time Boolean simulators: MaBoSS.MPI, a parallel implementation of MaBoSS which can exploit the computational power of very large CPU clusters, and MaBoSS.GPU, which can use GPU accelerators to perform these simulations.",FALSE,FALSE,"(75, 81, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"Here, we present adaptations of MaBoSS [15, 16]—a stochastic Boolean simulator that performs estimations of state probability trajectories based on Gillespie stochastic simulation algorithm [17]—to modern HPC computing architectures, which provide significant speedups of the computation, thus allowing scrutinization and analysis of much larger Boolean models.",FALSE,FALSE,"(32, 38, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"The main contributions comprise two new implementations of MaBoSS:MaBoSS.GPU, a GPU-accelerated implementation of MaBoSS, which is designed to exploit the computational power of massively parallel GPU hardware.MaBoSS.MPI, a parallel implementation of MaBoSS which can scale to multinode environments, such as large CPU clusters.The source code of the proposed implementations is publicly available at their respective GitHub repositories.1 We also provide the scripts, presented plots, data and instructions to reproduce the benchmarks in the replication package.2",FALSE,FALSE,"(59, 65, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"MaBoSS.GPU, a GPU-accelerated implementation of MaBoSS, which is designed to exploit the computational power of massively parallel GPU hardware.",FALSE,FALSE,"(0, 6, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"MaBoSS.MPI, a parallel implementation of MaBoSS which can scale to multinode environments, such as large CPU clusters.",FALSE,FALSE,"(0, 6, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"As the main results, MaBoSS.GPU provided over 200\documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$$\times$$\end{document}× speedup over the current version of MaBoSS on a wide range of models using contemporary GPU accelerators, and MaBoSS.MPI is capable of almost linear performance scaling with added HPC resources, allowing similar speedups by utilizing the current HPC infrastructures.",FALSE,FALSE,"(21, 27, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"MaBoSS simulates the asynchronous update strategy, where only a single node changes its value in each transition (as opposed to the synchronous update strategy, for which all nodes that can be updated are updated [15]).",FALSE,FALSE,"(0, 6, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"} \end{aligned}$$\end{document}Bi(S)=0ifSi=fi(S)rotherwiseMaBoSS algorithm simulates the above process to produce stochastic trajectories: sequences of states \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$$S^0, S^1, \dots , S^k$$\end{document}S0,S1,⋯,Sk and time points \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$$t^0< t^1< \dots < t^k$$\end{document}t0<t1<⋯<tk where \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$$t^0 = 0$$\end{document}t0=0 and \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$$S^0$$\end{document}S0 is the initial state, and for each \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$$i \in \{0, \dots , k-1\}$$\end{document}i∈{0,⋯,k-1}, \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$$S^i$$\end{document}Si transitions to \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$$S^{i+1}$$\end{document}Si+1 at time \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$$t^{i+1}$$\end{document}ti+1.",FALSE,FALSE,"(58, 64, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412," Algorithm 1A single iteration of the MaBoSS simulation of a trajectory, given the state S and time t.",FALSE,FALSE,"(38, 44, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"A single iteration of the MaBoSS simulation of a trajectory, given the state S and time t.",FALSE,FALSE,"(26, 32, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"The probabilities of the corresponding windows are then averaged across all subtrajectories.Final states—The last sampled states from the trajectories are used to compute a final state distribution.Fixed states—All reached fixed points are used to compute a fixed state distribution.To maintain the brevity in the statistics, MaBoSS additionally allows marking some nodes internal.",FALSE,FALSE,"(326, 332, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"MaBoSS was initially developed as a single-core application, but swiftly, it was extended with a basic parallelism to exploit the multi-core nature of modern CPUs.",FALSE,FALSE,"(0, 6, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"To better understand how a researcher can use MaBoSS output, in the following section, we discuss the differences between the statistics in greater detail and show the standard ways of their visualization.",FALSE,FALSE,"(46, 52, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"In the CPU version of MaBoSS, the simulation part is the most computationally demanding part, with up to 80% of MaBoSS runtime spent by just evaluating the Boolean formulae (the exact number depends on the model).",FALSE,FALSE,"(22, 28, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"The original formula evaluation algorithm in MaBoSS used a recursive traversal of the expression tree, which (apart from other issues) causes memory usage patterns unsuitable for GPUs: the memory required per each core is not achievable in current GPUs, and there are typically too many cache misses [20].",FALSE,FALSE,"(45, 51, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"A possible drawback of the runtime compilation stems from the relative slowness of the compiler—for small models, the total execution time of MaBoSS.GPU may be easily dominated by the compilation.",FALSE,FALSE,"(142, 148, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"For optimizing the statistics aggregation, MaBoSS.GPU heavily relies on the fact that the typical number of non-internal nodes in a real-world MaBoSS model rarely exceeds 10 nodes, regardless of the size of the model.",FALSE,FALSE,"(43, 49, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,MaBoSS.MPI is a straightforward extension of the original MaBoSS CPU code to the MPI programming interface.,FALSE,FALSE,"(0, 6, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"To evaluate the impact of the implemented optimizations, we present the results of performance benchmarks for MaBoSS.GPU and MaBoSS.MPI by comparing their runtimes against the original CPU implementation.",FALSE,FALSE,"(110, 116, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,3Wall time comparison of MaBoSS and MaBoSS.GPU on real-world models.,FALSE,FALSE,"(25, 31, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,Wall time comparison of MaBoSS and MaBoSS.GPU on real-world models.,FALSE,FALSE,"(24, 30, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,4Wall time comparison of MaBoSS and MaBoSS.GPU on synthetic models with sizes ranging from 10 to 1000 nodes (x-axis) and the formula size of 10.,FALSE,FALSE,"(25, 31, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,Wall time comparison of MaBoSS and MaBoSS.GPU on synthetic models with sizes ranging from 10 to 1000 nodes (x-axis) and the formula size of 10.,FALSE,FALSE,"(24, 30, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,Figure 6 shows the efficiency of the MaBoSS.MPI implementation on the sizek model.,FALSE,FALSE,"(37, 43, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"In this work, we presented two new implementations of MaBoSS tool, a continuous time Boolean model simulator, both of which are designed to enable utilization of the HPC computing resources: MaBoSS.GPU is designed to exploit the computational power of massively parallel GPU hardware, and MaBoSS.MPI enables MaBoSS to scale to many nodes of HPC clusters via the MPI framework.",FALSE,FALSE,"(54, 60, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"Overall, we believe that the new MaBoSS implementations enable simulation and exploration of the behavior of very large, automatically generated models, thus becoming a valuable analysis tool for the systems biology community.",FALSE,FALSE,"(33, 39, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"During the development, we identified several optimization directions that could be taken by researchers to further scale up the MaBoSS simulation approach.",FALSE,FALSE,"(129, 135, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"Mainly, the parallelization scheme used in MaBoSS.GPU could be enhanced to also parallelize over the evaluation of Boolean formulae.",FALSE,FALSE,"(43, 49, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"To avoid GPU thread divergence, this would however require a specialized Boolean formula representation, entirely different from the current version of MaBoSS; likely even denying the relative efficiency of the use of runtime compilation.",FALSE,FALSE,"(152, 158, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"In the long term, easier optimization paths might lead to sufficiently good results: For example, backporting the GPU implementation improvements back to the MaBoSS CPU implementation could improve the performance even on systems where GPU accelerators are not available.",FALSE,FALSE,"(158, 164, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"Similarly, both MaBoSS.GPU and MaBoSS.MPI could be combined into a single software that executes distributed GPU-based analysis over multiple MPI nodes, giving a single high-performance solution for extremely large problems.",FALSE,FALSE,"(16, 22, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412," Project name: MaBoSS.GPUProject home page: https://github.com/sysbio-curie/MaBoSS.GPUOperating system(s): Platform independentProgramming language: C++, CUDAOther requirements: Flex, Bison, CMake \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$$>=$$\end{document}>= 3.18, Cuda toolkit \documentclass[12pt]{minimal} 				\usepackage{amsmath} 				\usepackage{wasysym}  				\usepackage{amsfonts}  				\usepackage{amssymb}  				\usepackage{amsbsy} 				\usepackage{mathrsfs} 				\usepackage{upgreek} 				\setlength{\oddsidemargin}{-69pt} 				\begin{document}$$>=$$\end{document}>= 12.0License: MITAny restrictions to use by non-academics: NoneProject name: MaBoSS.MPIProject home page: https://github.com/sysbio-curie/MaBoSSOperating system(s): Platform independentProgramming language: C++Other requirements: Flex, BisonLicense: BSD3-clauseAny restrictions to use by non-academics: None ",FALSE,FALSE,"(15, 21, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,Project name: MaBoSS.GPU,FALSE,FALSE,"(14, 20, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,Project home page: https://github.com/sysbio-curie/MaBoSS.GPU,FALSE,FALSE,"(51, 57, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,Project name: MaBoSS.MPI,FALSE,FALSE,"(14, 20, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,Project home page: https://github.com/sysbio-curie/MaBoSS,FALSE,FALSE,"(51, 57, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"https://github.com/sysbio-curie/MaBoSS.GPU, https://github.com/sysbio-curie/MaBoSS.",FALSE,FALSE,"(32, 38, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,"implemented MaBoSS.GPU, V.N.",FALSE,FALSE,"(12, 18, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11127412,implemented MaBoSS.MPI.,FALSE,FALSE,"(12, 18, 'MaBoSS', 'maboss')","Systems biology, Statistics and probability"
PMC11223864,Goslin (4) offers capabilities for assigning chain lengths and double bond numbers in fatty acids or lipid species through lipid name analysis.,FALSE,FALSE,"(0, 6, 'Goslin', 'goslin')","Lipids, Computational chemistry, Metabolomics, Bioinformatics, Ontology and terminology, Cheminformatics"
PMC11223864,"LipidSig 2.0 integrates Goslin in lipidomics data analysis, efficiently recognizing and converting systematic names, common names, synonymous names, and shorthand notation into standardized nomenclature.",FALSE,FALSE,"(24, 30, 'Goslin', 'goslin')","Lipids, Computational chemistry, Metabolomics, Bioinformatics, Ontology and terminology, Cheminformatics"
PMC11223864,"Goslin supports various styles and annotations, covering seven lipid categories and providing detailed classifications up to the stereospecific numbering (sn)-position level.",FALSE,FALSE,"(0, 6, 'Goslin', 'goslin')","Lipids, Computational chemistry, Metabolomics, Bioinformatics, Ontology and terminology, Cheminformatics"
PMC11223864,"In LipidSig 2.0, the assignment of lipid characteristics to each lipid species has been substantially enhanced, encompassing 29 characteristics derived from a combination of resources, including the packages LipidOne, LION, and Goslin, and three individual studies (13–15).",FALSE,FALSE,"(228, 234, 'Goslin', 'goslin')","Lipids, Computational chemistry, Metabolomics, Bioinformatics, Ontology and terminology, Cheminformatics"
PMC11223864,"In LipidSig 2.0, the lipid ID annotation process has been significantly refined and expanded, utilizing data curated from LIPID MAPS, MetaNetX (18), and SwissLipids (19), which comprise 28 964, 792 127 and 775 273 lipid names with shorthand notations can be recognized by Goslin, respectively.",FALSE,FALSE,"(272, 278, 'Goslin', 'goslin')","Lipids, Computational chemistry, Metabolomics, Bioinformatics, Ontology and terminology, Cheminformatics"
PMC11223864,"In addition, LipidSig 2.0 analyzes lipid names or features from user-provided lipidomics data using Goslin, which assigns corresponding nomenclature at various levels, including species (only total carbon and double bond counts), molecular species (with individual fatty acid chain compositions), and sn-position (detail in the exact positions of fatty acids on the backbone).",FALSE,FALSE,"(100, 106, 'Goslin', 'goslin')","Lipids, Computational chemistry, Metabolomics, Bioinformatics, Ontology and terminology, Cheminformatics"
PMC11099699,"In this study, we proposed a new method called Domain2GO that infers associations between protein domains and function‐defining gene ontology (GO) terms, thus redefining the problem as domain function prediction.",FALSE,FALSE,"(47, 56, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,Domain2GO uses documented protein‐level GO annotations together with proteins' domain annotations.,FALSE,FALSE,"(0, 9, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"As a use‐case study, we evaluated the biological relevance of examples selected from the Domain2GO‐generated domain‐GO term mappings via literature review.",FALSE,FALSE,"(89, 98, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Then, we applied Domain2GO to predict unknown protein functions by propagating domain‐associated GO terms to proteins annotated with these domains.",FALSE,FALSE,"(17, 26, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"The results demonstrated the high potential of Domain2GO, particularly for predicting molecular function and biological process terms, along with advantages such as producing interpretable results and having an exceptionally low computational cost.",FALSE,FALSE,"(47, 56, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"The source code, datasets, results, and user instructions for Domain2GO are available at https://github.com/HUBioDataLab/Domain2GO.",FALSE,FALSE,"(62, 71, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Additionally, we offer a user‐friendly online tool at https://huggingface.co/spaces/HUBioDataLab/Domain2GO, which simplifies the prediction of functions of previously unannotated proteins solely using amino acid sequences.",FALSE,FALSE,"(97, 106, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,Mutual annotation‐based prediction of protein domain functions with Domain2GO .,FALSE,FALSE,"(68, 77, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"To address the issues outlined above, we present a new method, Domain2GO, that utilizes the associations between protein domains and functions in order to infer GO term annotations of uncharacterized proteins (Figure 1).",FALSE,FALSE,"(63, 72, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Domain2GO links two types of relational information to each other: domain‐protein and protein‐function, in order to obtain GO term predictions for both InterPro domains and full proteins.",FALSE,FALSE,"(0, 9, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"InterPro domains and GO terms that display statistically significant co‐occurrence patterns on different proteins are found to be related and included in our association list called “Domain2GO mappings.” Accordingly, these GO terms are used to annotate the proteins that contain the corresponding domains, resulting in protein function predictions.",FALSE,FALSE,"(183, 192, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Additionally, we employed Domain2GO to predict the functions of the target proteins from the third version of the CAFA challenge (CAFA3) and compared the prediction performance against leading methods in this challenge, domain‐based approaches and baseline protein function prediction methods.",FALSE,FALSE,"(26, 35, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,This analysis aimed to assess Domain2GO's ability to generate protein annotations at a large scale as a secondary downstream task.,FALSE,FALSE,"(30, 39, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"As a use‐case study, we examined selected Domain2GO pairs to observe whether they possess biological relevance.",FALSE,FALSE,"(42, 51, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,The finalized Domain2GO mappings were used to obtain function predictions for the proteins in the whole UniProtKB/Swiss‐Prot database.,FALSE,FALSE,"(14, 23, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"(a) The source datasets were downloaded and organized; (b) initial mappings between the InterPro domains and GO terms were obtained, and the mapping parameters were calculated; (c) generation of the randomized annotation and mapping sets were constructed; (d) co‐occurrence similarity distributions were plotted, and thresholds were selected based on statistical resampling; (e) an ablation study was conducted by calculating the enrichment of top predictions ranked by different statistical measures and finalized Domain2GO mappings were generated by filtering initial mappings; (f) protein function predictions were generated by propagating Domain2GO mappings to target proteins.",FALSE,FALSE,"(515, 524, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,The original and randomized Domain2GO mapping generation process is explained in detail in Section 4.2.,FALSE,FALSE,"(28, 37, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"The numbers of Domain2GO pairs, domains, and GO terms in the original and randomized mapping sets at different co‐occurrence similarity thresholds are shown in Table S1.",FALSE,FALSE,"(15, 24, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,The co‐occurrence similarity distributions of the initial/raw original Domain2GO mappings.,FALSE,FALSE,"(71, 80, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"While this value pair seems appropriate for use as official thresholds, we selected n ≥ 2 and S > 0.2 to make a safe choice and eliminate all the initial Domain2GO mappings other than those with high reliability.",FALSE,FALSE,"(154, 163, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Following this analysis, the finalized Domain2GO mapping set contained 26,696 associations between 4742 InterPro domains and 11,742 GO terms, which are available at https://github.com/HUBioDataLab/Domain2GO.",FALSE,FALSE,"(39, 48, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"To compare the prediction performance of each different statistical measure (i.e., S, θ  i , θ, and E), ideally, the likelihood ratio test should have been performed for each Domain2GO pair in the initial set (2,069,796 mappings) by rerunning the EM until the likelihood values (Equation 6) stop increasing noticeably.",FALSE,FALSE,"(175, 184, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,The enrichment of manually curated domain‐GO term associations in the top‐ranking Domain2GO mappings.,FALSE,FALSE,"(82, 91, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"To evaluate our method in terms of generating biologically relevant domain‐GO term associations, we compared the finalized Domain2GO mappings with InterPro2GO as a reference domain annotation system.",FALSE,FALSE,"(123, 132, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"According to these results, Domain2GO managed to find connections to more than half of the domains and GO terms presented in InterPro2GO and many more.",FALSE,FALSE,"(28, 37, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,Many of the associations retrieved by Domain2GO contain GO terms that are closely related (on the directed acyclic graph of Gene Ontology) to GO terms annotated to the same domain in InterPro2GO.,FALSE,FALSE,"(38, 47, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"To evaluate the biological significance of our findings, we examined three Domain2GO mappings.",FALSE,FALSE,"(75, 84, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,A case study comparing Domain2GO with curated InterPro2GO annotations on a selected domain.,FALSE,FALSE,"(23, 32, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Accordingly, the proteins that contain the domain IPR003583, and thus annotated to the function term GO:0051103 thanks to the corresponding Domain2GO mapping, are all DNA ligases from different organisms according to the information provided in UniProtKB (e.g., UniProt accessions: P15042, Q9WXV5, Q8A9C1, Q8DPS9, etc.).",FALSE,FALSE,"(140, 149, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,This is another clear example of Domain2GO associating domains with biologically relevant GO terms.,FALSE,FALSE,"(33, 42, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"The main aim of Domain2GO is to predict the functions of domains, not full proteins.",FALSE,FALSE,"(16, 25, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Nevertheless, it is interesting to examine the capabilities of Domain2GO in this regard.",FALSE,FALSE,"(63, 72, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"We evaluated the complete protein function prediction performance of Domain2GO using the CAFA3 challenge benchmark dataset, which includes proteins that acquired manually curated GO associations during the annotation collection period.",FALSE,FALSE,"(69, 78, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"By comparing Domain2GO with DomFun and the other aforementioned methods, we gained valuable insights into the strengths and weaknesses of utilizing domain‐function associations for predicting full protein functions.",FALSE,FALSE,"(13, 22, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,We tested two individual sets of protein function predictions for Domain2GO.,FALSE,FALSE,"(66, 75, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"The first one, “Domain2GO‐S,” was generated via propagating the domain‐GO term mappings that were filtered with an S‐score ≥0.05, to the proteins in the CAFA benchmark dataset.",FALSE,FALSE,"(16, 25, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"By filtering mappings based on S‐score ≥0.05, we eliminated non‐reliable domain‐GO term mappings and still ended up with a prediction set of reasonable coverage (resulting in 169,534 Domain2GO mappings, which led to 8,695,580 function predictions between 24,665 GO terms and 75,354 CAFA3 target proteins).",FALSE,FALSE,"(183, 192, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"For the second set, “Domain2GO‐E,” we generated protein‐function predictions this time using Domain2GO mappings previously used as the input of the EM algorithm (78,477 mappings, as explained in Section 2.2) and assigned their E‐value (i.e., the output of the EM algorithm) as the probabilistic scores of the corresponding protein‐GO association predictions.",FALSE,FALSE,"(21, 30, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"The coverage of Domain2GO‐S, Domain2GO‐E and InterPro2GO on the CAFA3 no‐knowledge benchmark set was %0.53, %0.43, and %0.22, respectively.",FALSE,FALSE,"(16, 25, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Domain2GO's training data relies on domain‐GO term mappings, which is more limited in terms of dataset size compared to the comprehensive datasets (e.g., readily available amino acid sequences) used by other models.",FALSE,FALSE,"(0, 9, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Consequently, it was expected that both Domain2GO‐S and Domain2GO‐E would get lower coverage values than other methods.",FALSE,FALSE,"(40, 49, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Despite these limitations, it is worth noting that both Domain2GO‐S and Domain2GO‐E generally achieved higher coverage values in comparison to DomFun.",FALSE,FALSE,"(56, 65, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"The coverage difference between Domain2GO and DomFun can be attributed to the utilization of different protein‐domain annotation datasets (Rojano et al., 2022).",FALSE,FALSE,"(32, 41, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,Figure 5 shows the performance comparison of Domain2GO with other methods in terms of Fmax  values.,FALSE,FALSE,"(45, 54, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"In this evaluation, Domain2GO‐S, Domain2GO‐E and the hybrid models that contain Domain2GO were beaten by the challenge top scorers.",FALSE,FALSE,"(20, 29, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,The score difference between Domain2GO and the fifth‐best scorer was around %4 (Fmax ) for the molecular function (MF) category.,FALSE,FALSE,"(29, 38, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Whereas the difference between Domain2GO and the third‐best scorer was around %2 (Fmax ) for the biological process (BP) category (not considering Domain2GO's hybrid models, which had higher performances).",FALSE,FALSE,"(31, 40, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Furthermore, Domain2GO‐S and Domain2GO‐E outperformed the baseline predictors and DomFun when predicting MF and BP terms, achieving Fmax  scores of 0.48 and 0.46 for MFO, and 0.36 and 0.35 for BPO, respectively.",FALSE,FALSE,"(13, 22, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"However, in predicting cellular component terms, domain‐centric methods, including Domain2GO, encountered difficulties matching the performance of state‐of‐the‐art models.",FALSE,FALSE,"(83, 92, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,S_E_IPR2GO: Domain2GO‐S + Domain2GO‐E + InterPro2GO; S_BLAST: Domain2GO‐S + BLAST; S_E_BLAST: Domain2GO‐S + Domain2GO‐E + BLAST; S_E_IPR2GO_BLAST: Domain2GO‐S + Domain2GO‐E + InterPro2GO + BLAST).,FALSE,FALSE,"(12, 21, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"This mode revealed an enhancement in the performance of all domain‐based predictors, including both Domain2GO variants, attributed to their inherently low coverage.",FALSE,FALSE,"(100, 109, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"In the MFO category, Domain2GO‐E and Domain2GO‐S outperformed all other methods, achieving Fmax  values of 0.68 and 0.63, respectively.",FALSE,FALSE,"(21, 30, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Similarly, in the BPO category, Domain2GO‐E and Domain2GO‐S delivered Fmax  values of 0.49 and 0.46, surpassing all other methods.",FALSE,FALSE,"(32, 41, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"This observed performance boost in the partial‐mode highlights a significant challenge in our methodology: while Domain2GO can provide highly accurate predictions, its applicability is constrained by the limited range of proteins it can effectively assess.",FALSE,FALSE,"(113, 122, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,Another key observation from this evaluation is the contrasting performance of Domain2GO‐S and Domain2GO‐E.,FALSE,FALSE,"(79, 88, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"While Domain2GO‐S demonstrated greater enrichment in manually curated domain‐GO term mappings (Figure 3) due to its broader coverage, Domain2GO‐E outperformed Domain2GO‐S in the partial‐mode evaluation of the CAFA challenge.",FALSE,FALSE,"(6, 15, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"This indicates that despite its lower coverage, Domain2GO‐E is capable of offering highly accurate predictions within its narrower prediction range and suggests that it could potentially surpass Domain2GO‐S in predictive performance if not for the high computational requirements that forced us to limit its training dataset.",FALSE,FALSE,"(48, 57, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,This insight highlights the potential of Domain2GO‐E.,FALSE,FALSE,"(41, 50, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,The relatively lower predictive performance of Domain2GO and InterPro2GO in the CCO category could potentially be attributed to the inherent difficulty in associating domains with cellular structures.,FALSE,FALSE,"(47, 56, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"To further validate our findings, we conducted a comparative study between Domain2GO‐S and BLAST, investigating their intersecting and differing true‐positive, false‐positive, and false‐negative predictions at the optimal thresholds (i.e., the threshold where Fmax  is obtained) for all three ontologies in the full evaluation mode (Figure S8).",FALSE,FALSE,"(75, 84, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Even though Domain2GO's low coverage meant that it made fewer true‐positive predictions than BLAST, it also made fewer false‐positive predictions.",FALSE,FALSE,"(12, 21, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,This underscores Domain2GO‐S's precision and contributes to its overall better performance compared to BLAST in certain aspects.,FALSE,FALSE,"(17, 26, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"These results emphasize Domain2GO's strength in providing accurate predictions within its defined scope, illustrating its reliability.",FALSE,FALSE,"(24, 33, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"However, Domain2GO adopts a cautious approach, refraining from making predictions in situations with uncertain or insufficient data.",FALSE,FALSE,"(9, 18, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"While this approach ensures high reliability, it also indicates that Domain2GO might overlook potential predictions due to its conservative nature.",FALSE,FALSE,"(69, 78, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"In the MFO category, Domain2GO‐S secured the second position with an S min value of 6.22, showcasing comparable performance with the top‐performing model, DomFun.",FALSE,FALSE,"(21, 30, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Furthermore, in the BPO category, Domain2GO‐S outperformed other domain‐based methods and baseline methods, achieving an S min value of 15.93.",FALSE,FALSE,"(34, 43, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Here, we observed that Domain2GO‐S and Domain2GO‐E consistently outperformed all state‐of‐the‐art methods when predicting molecular function and biological process terms for proteins of Mus musculus.",FALSE,FALSE,"(23, 32, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Similarly, in the case of Rattus norvegicus, Domain2GO‐S and Domain2GO‐E exhibited the best performance values in the BPO category with Fmax  scores of 0.54 and 0.42 and ranked among the top‐performing models in the MFO category with Fmax  values of 0.48 and 0.35, respectively (Figure 6b).",FALSE,FALSE,"(45, 54, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"When predicting functions of Drosophila melanogaster proteins, Domain2GO‐S and Domain2GO‐E achieved Fmax  values of 0.49 and 0.57 for MFO and 0.41 and 0.29 for BPO, demonstrating comparable performance with the best‐performing models (Figure 6c).",FALSE,FALSE,"(63, 72, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"A comparison of Domain2GO's performance with other methods concerning five organisms, including the performances in the CCO category, is provided in Supplementary Material, Section 7 and Figures S3–S7.",FALSE,FALSE,"(16, 25, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Additionally, we created hybrid protein function prediction approaches that combine multiple prediction sets, including Domain2GO‐S, Domain2GO‐E, InterPro2GO, and BLAST, with the aim of evaluating their collective predictive capabilities.",FALSE,FALSE,"(120, 129, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Among these hybrid approaches, we introduced S_E_IPR2GO, a combination of domain‐based techniques that incorporates Domain2GO‐S, Domain2GO‐E, and InterPro2GO.",FALSE,FALSE,"(116, 125, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,This approach yielded results very similar to Domain2GO‐S and Domain2GO‐E in both full and partial‐mode evaluations without introducing any significant enhancements in terms of performance or coverage (Figure 5).,FALSE,FALSE,"(46, 55, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"In these assessments, S_E_IPR2GO outperformed Domain2GO‐S and Domain2GO‐E slightly, achieving Fmax  values of 0.71 and 0.42, making it the top‐performing model (Figure 6a).",FALSE,FALSE,"(46, 55, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"We also introduced three different combinations of domain‐based models with BLAST: S_BLAST combines Domain2GO‐S with BLAST, S_E_BLAST combines Domain2GO‐S, Domain2GO‐E, and BLAST, while S_E_IPR2GO_BLAST combines Domain2GO‐S, Domain2GO‐E, InterPro2GO, and BLAST.",FALSE,FALSE,"(100, 109, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Expanding on our previous analysis of Domain2GO‐S and BLAST's individual performances, outlined in Section 2.5.1 and depicted in Figure S8, we further investigated the impact of their integration, the performance of the Domain2GO‐BLAST method.",FALSE,FALSE,"(38, 47, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,The high number of mutual predictions between Domain2GO‐S and BLAST across all three ontologies (Figure S8) suggests similar predictive capabilities.,FALSE,FALSE,"(46, 55, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,This shared predictive strength is crucial for understanding the similar performance levels of the Domain2GO‐BLAST hybrid set when compared individually to Domain2GO‐S and BLAST.,FALSE,FALSE,"(99, 108, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Specifically, in the BPO category, the performance of Domain2GO‐BLAST was slightly better than BLAST alone but considerably lower than Domain2GO‐S.",FALSE,FALSE,"(54, 63, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,We also developed a user‐friendly tool with a graphical user interface accessible at https://huggingface.co/spaces/HUBioDataLab/Domain2GO.,FALSE,FALSE,"(128, 137, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,We conducted a comparative analysis of the best‐performing CAFA3 models with currently available tools in each GO category against Domain2GO‐S and Domain2GO‐E (Table S5).,FALSE,FALSE,"(131, 140, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,Predictive performance results demonstrated that Domain2GO outscored the best available CAFA3 methods in the MFO and BPO categories in the partial evaluation mode.,FALSE,FALSE,"(49, 58, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Finally, we employed final Domain2GO mappings to predict GO term annotations for 566,996 proteins in the UniProtKB/SwissProt database (release 2022_01), by propagating domain‐associated GO terms to the proteins that contain those domains, based on annotations provided in the InterPro database.",FALSE,FALSE,"(27, 36, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"The resulting protein function prediction set contains 5,046,060 GO term predictions for 291,519 proteins and 11,742 GO terms, which are available at https://github.com/HUBioDataLab/Domain2GO.",FALSE,FALSE,"(182, 191, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"In this study, we proposed Domain2GO; a straightforward domain function prediction approach that maps structural domains of proteins to function‐defining GO terms.",FALSE,FALSE,"(27, 36, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,An ablation study was performed on manually curated domain function annotations to assess the accuracy of different statistical measures utilized in Domain2GO.,FALSE,FALSE,"(149, 158, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Additionally, a literature‐based case study was performed to investigate the significance of Domain2GO mappings.",FALSE,FALSE,"(93, 102, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Even though Domain2GO is not specifically designed to predict protein functions, we looked at how well it did in this area using the CAFA challenge data.",FALSE,FALSE,"(12, 21, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,The reason behind evaluating the prediction performance of Domain2GO using the task of protein function prediction is the lack of well‐acknowledged benchmarks that are designed for domain function prediction.,FALSE,FALSE,"(59, 68, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"The results demonstrate Domain2GO's strong performance, particularly in the MFO and BPO categories, where it outperforms all other methods in Fmax  evaluations in the partial evaluation mode, thus emphasizing the robustness of the proposed method.",FALSE,FALSE,"(24, 33, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Domain2GO also scored high in the organism‐specific evaluations, particularly in the case of model organisms, consistently ranking as one of the leading models when predicting, again, MFO and BPO terms.",FALSE,FALSE,"(0, 9, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Furthermore, the web‐based tool we designed for Domain2GO simplifies the function prediction process.",FALSE,FALSE,"(48, 57, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"This is especially valid for proteins with no prior information available in databases, as the Domain2GO tool solely requires the amino acid sequence of the query protein.",FALSE,FALSE,"(95, 104, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"In this mode, a general decline in the performance of all domain‐based predictors, including Domain2GO, was observed.",FALSE,FALSE,"(93, 102, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"These findings suggest that while Domain2GO is highly reliable in its predictions, offering accurate insights when it does provide a prediction, its performance is constrained when evaluated across a broader range.",FALSE,FALSE,"(34, 43, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"In this sense, a potential area of exploration could be extending the Domain2GO framework by incorporating various complementary protein centric data sources.",FALSE,FALSE,"(70, 79, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Such advancements would not only enhance the accuracy of Domain2GO, but also broaden its applicability to encompass the diverse functional landscape.",FALSE,FALSE,"(57, 66, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,We identified each pair as a(n) initial/raw Domain2GO mapping.,FALSE,FALSE,"(44, 53, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"First, we calculated a co‐occurrence similarity measure (S) for each Domain2GO mapping.",FALSE,FALSE,"(69, 78, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Second, we applied the expectation maximization (EM) algorithm (Dempster et al., 1977), which is a method for obtaining a maximum‐likelihood estimate of the probability of association (θ), and the confidence of its probability (E), independently for each Domain2GO mapping.",FALSE,FALSE,"(255, 264, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"All Domain2GO mappings were ranked independently by four of the calculated measures (i.e., S, θ  i , θ, and E) and the enrichment of manually curated Domain2GO annotations in the highest‐ranking mappings was analyzed.",FALSE,FALSE,"(4, 13, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"If a UniProt ID is shared between (co‐annotated with) an individual domain and a GO term, we identify this pair as a(n) initial/raw Domain2GO mapping.",FALSE,FALSE,"(132, 141, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Therefore, a threshold co‐occurrence similarity value can be set to differentiate the relevant Domain2GO pairs from the ones that occurred by chance.",FALSE,FALSE,"(95, 104, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Assuming that some pairs with a high similarity score can still be random, especially when N Di and N GOj are very low, we employed N Di,GOj as a second parameter abbreviated as “n.” Accordingly, Domain2GO pairs with both high S and n values are considered to be more reliable.",FALSE,FALSE,"(196, 205, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"In order to assign optimal S and n values to be used as thresholds, we compared the co‐occurrence similarity distribution obtained from Domain2GO mappings to the score distribution of randomly generated domain‐GO term pairs.",FALSE,FALSE,"(136, 145, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"For this, a randomized mapping table was created by shuffling domain and GO term columns on the original Domain2GO mappings (Figure 1c), and then the S and n score calculation steps were repeated for the newly generated random Domain2GO mappings.",FALSE,FALSE,"(105, 114, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,Figure S1 depicts a toy example of EM algorithm implementation on the Domain2GO mapping set.,FALSE,FALSE,"(70, 79, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"The algorithm was initialized by obtaining an estimate of the association probability for each Domain2GO mapping, based on the ratio of proteins they are co‐annotated to.",FALSE,FALSE,"(95, 104, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Initialized values of θ Di,GOj and other variables for all domain‐GO term pairs were then used to estimate the initial likelihood L (Equation 6) of the Domain2GO mapping set: (6) L=∏Di,GOjθDi,GOjMDi,GOj+α1−θDi,GOjKDi,GOj+ZDi,GOj+β, where α and β are arbitrary pseudocounts to ensure that obtaining too high or too low θ Di,GOj values were not due to the low frequencies of Di and GOj annotations, but to the large numbers of co‐occurrences indicating the potential association of them.",FALSE,FALSE,"(152, 161, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Di, GOj is each domain‐GO term pair in Domain2GO mapping set.",FALSE,FALSE,"(39, 48, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"The probability matrix of all Domain2GO domains, θ, was obtained as the result of the EM algorithm.",FALSE,FALSE,"(30, 39, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,This resulted in a maximum likelihood estimate of all Domain2GO mappings excluding Di‐GOj pair.,FALSE,FALSE,"(54, 63, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"While θ can be considered as the probability of a mapping, the E score aims to detect highly specific Domain2GO mappings with extensive evidence in the co‐annotation data.",FALSE,FALSE,"(102, 111, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Two baseline methods, Naive and BLAST, were built in order to compete with the co‐occurrence similarity and E score‐based function predictions of Domain2GO.",FALSE,FALSE,"(146, 155, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"DomFun adopts a similar approach to Domain2GO, predicting domain functions through protein domain associations.",FALSE,FALSE,"(36, 45, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"We employed the CAFA3 challenge (Zhou et al., 2019) benchmark set to investigate whether Domain2GO can be extended to predict protein functions, even though it is primarily proposed to predict the functions of domains.",FALSE,FALSE,"(89, 98, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"To facilitate a fair comparison, we recalibrated the Domain2GO mappings to be in sync with the specific timeframe of the CAFA3 experiment.",FALSE,FALSE,"(53, 62, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"These predictions were subsequently assessed against the benchmarks established in the CAFA3 experiment, thereby allowing us to evaluate the efficacy and accuracy of Domain2GO in the context of a recognized and rigorous protein function prediction challenge.",FALSE,FALSE,"(166, 175, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,"Domain2GO is shared as an open access programmatic tool, along with all datasets used and results generated, at https://github.com/HUBioDataLab/Domain2GO.",FALSE,FALSE,"(0, 9, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11099699,It is also offered as an online web‐based tool with a graphical user interface at https://huggingface.co/spaces/HUBioDataLab/Domain2GO.,FALSE,FALSE,"(125, 134, 'Domain2GO', 'domain2go')","Protein folds and structural domains, Ontology and terminology, Function analysis, Protein interactions"
PMC11090762,"MerCat2 (“Mer—Catenate2”) is a versatile, parallel, scalable and modular property software package for robustly analyzing features in omics data.",FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"Using massively parallel sequencing raw reads, assembled contigs, and protein sequences from any platform as input, MerCat2 performs k-mer counting of any length k, resulting in feature abundance counts tables, quality control reports, protein feature metrics, and graphical representation (i.e.",FALSE,FALSE,"(116, 123, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"MerCat2 allows for direct analysis of data properties in a database-independent manner that initializes all data, which other profilers and assembly-based methods cannot perform.",FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,MerCat2 represents an integrated tool to illuminate omics data within a sample for rapid cross-examination and comparisons.,FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,MerCat2 is written in Python and distributed under a BSD-3 license.,FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,The source code of MerCat2 is freely available at https://github.com/raw-lab/mercat2.,FALSE,FALSE,"(19, 26, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,MerCat2 is compatible with Python 3 on Mac OS X and Linux.,FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,MerCat2 can also be easily installed using bioconda: mamba create -n mercat2 -c conda-forge -c bioconda mercat2,FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,MerCat2 improves on MerCat v1 (White III et al.,FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"Here we describe MerCat2, a tool that can accommodate any size sequence file by utilizing a “divide and conquer” approach that performs integrated analysis, including quality control, k-mer counting, and visualization.",FALSE,FALSE,"(17, 24, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"MerCat2 provides a rapid, robust, versatile analysis of MPS data using DIPA.",FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,MerCat2 is a versatile and scalable Python-based open-source software package.,FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"MerCat2 scales from laptop to high-performance computing resources, all within the same user-friendly package.",FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"MerCat2 computes k-mer frequency counting to any length k on assembled contigs as nucleotide fasta, raw reads or trimmed (e.g.",FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"Although raw read inputs can be used in MerCat2, it is not recommended due to low quality and sequencing errors.",FALSE,FALSE,"(40, 47, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"For raw reads, MerCat2 provides fastqc reports pre- and post-trimming, which are also included within the final HTML-based report (Andrews 2010) (Fig.",FALSE,FALSE,"(15, 22, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,Flow graph of MerCat2.,FALSE,FALSE,"(14, 21, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,MerCat2 can be run in protein or nucleotide mode using the naive k-mer counter algorithm 2 (k-mer counter—Supplementary Fig.,FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,MerCat2 has two analysis modes utilizing nucleotide or protein files (Fig.,FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"To demonstrate the scaling, versatility, and robustness of MerCat2, we compared large microbial genome databases, metagenomic, and metatranscriptomic data from a diversity of samples.",FALSE,FALSE,"(59, 66, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"For the GTDB archaea genome database, MerCat2 was able to complete counting whether 4- or 31-mer as either nucleotides or amino acids in under <100 secs, using <15 GB of RAM and <700 Mb of disc space (Table 1).",FALSE,FALSE,"(38, 45, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"MerCat2 counted GTDB bacterial genome database with whether 4- or 31-mer as either nucleotides or amino acids in <1 h, <30 GB of RAM, and <10 GB of disc space (Table 1).",FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"We included metatranscriptome samples from modern hypersaline microbial mats to test scalability, disc space, and memory for MerCat2.",FALSE,FALSE,"(125, 132, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"Scalability for 5 billion metagenomic reads was possible with MerCat2 as it counted all eight datasets with whether 4- or 31-mer as either nucleotides or amino acids in under 90 min, <35 GB of RAM, and <10 Mb of disc space (Table 1).",FALSE,FALSE,"(62, 69, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"We benchmarked MerCat2 against two other k-mer counters KMC and Jellyfish2 (Marçais and Kingsford 2011, Kokot et al.",FALSE,FALSE,"(15, 22, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,MerCat2 currently is the only k-mer counter that can count both amino acid and nucleotide fasta files; neither are currently supported in KMC or Jellyfish2.,FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"For our five-genome benchmark using nucleotide fasta for k = 4, MerCat2 is slower, uses more memory, and leaves more disk space; however, with k = 31, MerCat2 provides similar speed to Jellyfish2 and utilizes less memory with a maximum of 250 Mb required (Fig.",FALSE,FALSE,"(64, 71, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"We further benchmarked MerCat2, KMC, and Jellyfish2 against 100 randomly selected GTDB bacteria, GTDB archaea, and 78 genomes from the candidate phyla radiation (CPR).",FALSE,FALSE,"(23, 30, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"For 4-mer based nucleotide counting single threaded, MerCat2 was the slowest; however, it approached speeds of Jellyfish using single threads, and had a maximum of 250 Mb of RAM required total (Figs 3–5).",FALSE,FALSE,"(53, 60, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"With 31-mers, MerCat2 was faster than Jellyfish and provided the lowest RAM required (maximum 250 Mb) to complete counting when compared directly to kmc and Jellyfish (Figs 3–5).",FALSE,FALSE,"(14, 21, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,MerCat2 provides scaling benefits with multiple threads utilization.,FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"MerCat2 provides plots and dashboards as html, whereas kmc and Jellyfish do not, thus leaving more disc space post run.",FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"Five bacterial genomes Agrococcus pavilionensis strain RW1, Azotobacter vinelandii strain DJ, Rhizobium leguminosarum, and two genomes of Exiguobacterium chiriqhucha strain RW2 and strain GIC31 were compared against MerCat2, kmc, and Jellyfish using nucleotide whole-genome fasta files for k = 4 and k = 31.",FALSE,FALSE,"(216, 223, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"One hundred randomly selected GTDB archaeal genomes as whole-genome nucleotide fasta where compared MerCat2, kmc, and Jellyfish with k = 4 and k = 31.",FALSE,FALSE,"(100, 107, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"One hundred randomly selected GTDB bacterial genomes as whole-genome nucleotide fasta where compared MerCat2, kmc, and Jellyfish with k = 4 and k = 31.",FALSE,FALSE,"(101, 108, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"Seventy-eight genomes from the candidate phyla radiation were randomly selected as whole-genome nucleotide fasta where compared MerCat2, kmc, and Jellyfish with k = 4 and k = 31.",FALSE,FALSE,"(128, 135, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,CCC) and enumeration of those k-mers generated by MerCat2 against other commonly used k-mer counters such as JellyFish2 and KMC.,FALSE,FALSE,"(50, 57, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"MerCat2, KMC, JellyFish2) then applied Spearman correlation against the outputs, finding 100% similarity between the outputs (Fig.",FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,We also directly compared MerCat2 and Simka for measuring Bray–Curtis dissimilarity against test data provided by Simka.,FALSE,FALSE,"(26, 33, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,Bray–Curtis dissimilarity measurement was 100% identical between MerCat2 and Simka (Fig.,FALSE,FALSE,"(65, 72, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"We used our five genomes then counted nucleotide-based k-mer using MerCat2, KMC, and JellyFish2 with k = 31.",FALSE,FALSE,"(67, 74, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,We used the Simka supplied test data for calculation comparison using Bray–Curtis dissimilarity for both (A) MerCat2 and (B) Simka.,FALSE,FALSE,"(109, 116, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"MerCat2 provides DIPA for metaomic data, utilizing all data present, in a robust, versatile manner resulting in tabular files for downstream analysis, with built-in visualizations and a dashboard.",FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"MerCat2 is scalable, accommodating for various input files, user-friendly, easy to install, and user-customizable.",FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,MerCat2 provides the same accuracy and precision of k-mer identification and enumeration of outputs as JellyFish2 and KMC.,FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,"MerCat2 is able to calculate both Alpha and Beta diversity metrics on genomes, contigs, amino acids, and reads.",FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,MerCat2 when directly compared to Simka provided identical results for the ecological dissimilarity metric (i.e.,FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11090762,MerCat2 enables rapid analysis of many datasets and large datasets in a database-independent manner.,FALSE,FALSE,"(0, 7, 'MerCat2', 'mercat2')","Ecology, Sequence assembly"
PMC11217664,"This is a correction to: Dmitry E Mylarshchikov, Arina I Nikolskaya, Olesja D Bogomaz, Anastasia A Zharikova, Andrey A Mironov, BaRDIC: robust peak calling for RNA–DNA interaction data, NAR Genomics and Bioinformatics, Volume 6, Issue 2, June 2024, lqae054, https://doi.org/10.1093/nargab/lqae054",FALSE,FALSE,"(128, 134, 'BaRDIC', 'bardic')","Functional, regulatory and non-coding RNA, Sequencing, Gene transcripts, Protein interactions, Gene expression"
PMC11217664,"In the Abstract, the github link was connecting to an incorrect url and has been updated to https://github.com/dmitrymyl/BaRDIC.",FALSE,FALSE,"(121, 127, 'BaRDIC', 'bardic')","Functional, regulatory and non-coding RNA, Sequencing, Gene transcripts, Protein interactions, Gene expression"
PMC10994858,"Here, we present scalepopgen, a collection of fully automated workflows that can carry out widely used population genomic analyses on the biallelic single nucleotide polymorphism data stored in either variant calling format files or the plink-generated binary files.",FALSE,FALSE,"(17, 28, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,"scalepopgen is developed in Nextflow and can be run locally or on high-performance computing systems using either Conda, Singularity, or Docker.",FALSE,FALSE,"(0, 11, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,The tool is freely available at https://github.com/Popgen48/scalepopgen.,FALSE,FALSE,"(60, 71, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,"Here, we employed the mentioned technologies to create scalepopgen, an easily scalable, portable, and reproducible tool that implements workflows for widely used population genomics analyses on genome-wide biallelic single nucleotide polymorphism (SNP) data.",FALSE,FALSE,"(55, 66, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,scalepopgen is mainly developed using the Nextflow workflow management system (Di Tommaso et al.,FALSE,FALSE,"(1, 12, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,scalepopgen consists of several workflows that perform a diverse range of population genetic analyses (Fig.,FALSE,FALSE,"(0, 11, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,Overview of the workflows implemented in scalepopgen.,FALSE,FALSE,"(41, 52, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,Note that the design of the workflow reflects the implementation in the current version (scalepopgen v 1.0.0).,FALSE,FALSE,"(89, 100, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,"Here, we demonstrate the application of scalepopgen to explore the genetic structure of a large number of cattle samples directly from the VCF files.",FALSE,FALSE,"(40, 51, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,nextflow run scalepopgen/-params-file test_full.yaml-profile singularity-resume,FALSE,FALSE,"(14, 25, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,The HTML report containing the details about the computational resources and time used by each process can be accessed here: https://bioinf2305.github.io/scalepopgen_results/.,FALSE,FALSE,"(154, 165, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,A complete interactive example can be assessed here: https://bioinf2305.github.io/scalepopgen_results/multiqc_report.html.,FALSE,FALSE,"(82, 93, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,The central objective behind the development of scalepopgen was to create workflows that provide easy accessibility to major population genomic analyses.,TRUE,FALSE,"(48, 59, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,The steps to contributing to the project are described on the GitHub page (https://github.com/Popgen48/scalepopgen).,TRUE,FALSE,"(103, 114, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,scalepopgen is hosted on GitHub under the popgen48 organization (https://github.com/Popgen48/scalepopgen) and released under MIT license.,TRUE,FALSE,"(0, 11, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"
PMC10994858,The results of the case study described in the paper are hosted at: https://bioinf2305.github.io/scalepopgen_results/.,TRUE,FALSE,"(97, 108, 'scalepopgen', 'scalepopgen')","Workflows, Population genomics, Metagenomics, DNA polymorphism, Genotype and phenotype"