diff --git a/_data/people.yml b/_data/people.yml index 73df7e6..dbd54d6 100644 --- a/_data/people.yml +++ b/_data/people.yml @@ -262,12 +262,6 @@ id: BlakeBunney alum: false -- name: Haarika Kathi - pos: Technician - email: hkathi@wi.mit.edu - id: HaarikaKathi - alum: false - - name: Emily He pos: Technician email: ehe@wi.mit.edu @@ -736,7 +730,8 @@ pos: Post-doc id: Gene-WeiLi alum: true - now: PI & Associate Professor of Biology | Massachusetts Institute of Technology + now: PI, Associate Professor of Biology & HHMI Investigator | Massachusetts Institute + of Technology & HHMI - name: Han Li pos: Technician diff --git a/_data/publications.yml b/_data/publications.yml index 9ed6af2..34f1a5d 100644 --- a/_data/publications.yml +++ b/_data/publications.yml @@ -1,3 +1,71 @@ +- title: High-quality peptide evidence for annotating non-canonical open reading frames + as human proteins. + authors: + - Eric W Deutsch + - Leron W Kok + - Jonathan M Mudge + - Jorge Ruiz-Orera + - Ivo Fierro-Monti + - Zhi Sun + - Jennifer G Abelin + - M Mar Alba + - Julie L Aspden + - Ariel A Bazzini + - Elspeth A Bruford + - Marie A Brunet + - Lorenzo Calviello + - Steven A Carr + - Anne-Ruxandra Carvunis + - Sonia Chothani + - Jim Clauwaert + - Kellie Dean + - Pouya Faridi + - Adam Frankish + - Norbert Hubner + - Nicholas T Ingolia + - Michele Magrane + - Maria Jesus Martin + - Thomas F Martinez + - Gerben Menschaert + - Uwe Ohler + - Sandra Orchard + - Owen Rackham + - Xavier Roucou + - Sarah A Slavoff + - Eivind Valen + - Aaron Wacholder + - Jonathan S Weissman + - Wei Wu + - Zhi Xie + - Jyoti Choudhary + - Michal Bassani-Sternberg + - "Juan Antonio Vizca\xEDno" + - Nicola Ternette + - Robert L Moritz + - John R Prensner + - Sebastiaan van Heesch + publication_date: 24/09/24 + publication_year: '2024' + pubmed_id: '39314370' + abstract: 'A major scientific drive is to characterize the protein-coding genome + as it provides the primary basis for the study of human health. But the fundamental + question remains: what has been missed in prior genomic analyses? Over the past + decade, the translation of non-canonical open reading frames (ncORFs) has been + observed across human cell types and disease states, with major implications for + proteomics, genomics, and clinical science. However, the impact of ncORFs has + been limited by the absence of a large-scale understanding of their contribution + to the human proteome. Here, we report the collaborative efforts of stakeholders + in proteomics, immunopeptidomics, Ribo-seq ORF discovery, and gene annotation, + to produce a consensus landscape of protein-level evidence for ncORFs. We show + that at least 25% of a set of 7,264 ncORFs give rise to translated gene products, + yielding over 3,000 peptides in a pan-proteome analysis encompassing 3.8 billion + mass spectra from 95,520 experiments. With these data, we developed an annotation + framework for ncORFs and created public tools for researchers through GENCODE + and PeptideAtlas. This work will provide a platform to advance ncORF-derived proteins + in biomedical discovery and, beyond humans, diverse animals and plants where ncORFs + are similarly observed.' + doi: 10.1101/2024.09.09.612016 + journal: biorxiv - title: Robustness and reliability of single-cell regulatory multi-omics with deep mitochondrial mutation profiling. authors: diff --git a/compile_info.ipynb b/compile_info.ipynb index c4e875e..cab966b 100644 --- a/compile_info.ipynb +++ b/compile_info.ipynb @@ -62,7 +62,7 @@ { "data": { "text/plain": [ - "266" + "268" ] }, "execution_count": 2, @@ -199,6 +199,28 @@ " \n", " \n", " 0\n", + " Robustness and reliability of single-cell regu...\n", + " [Chen Weng, Jonathan S Weissman, Vijay G Sanka...\n", + " 04/09/24\n", + " 2024\n", + " 39229039\n", + " The detection of mitochondrial DNA (mtDNA) mut...\n", + " 10.1101/2024.08.23.609473\n", + " biorxiv\n", + " \n", + " \n", + " 1\n", + " Multi-species genome-wide CRISPR screens ident...\n", + " [Breanna Lam, Kathrin M Kajderowicz, Heather R...\n", + " 02/08/24\n", + " 2024\n", + " 39091747\n", + " Cells must adapt to environmental changes to m...\n", + " 10.1101/2024.07.25.605098\n", + " biorxiv\n", + " \n", + " \n", + " 2\n", " Transcriptome-wide characterization of genetic...\n", " [Ajay Nadig, Joseph M Replogle, Angela N Pogso...\n", " 15/07/24\n", @@ -209,7 +231,7 @@ " biorxiv\n", " \n", " \n", - " 1\n", + " 3\n", " Brainwide silencing of prion protein by AAV-me...\n", " [Edwin N Neumann, Tessa M Bertozzi, Elaine Wu,...\n", " 27/06/24\n", @@ -220,7 +242,7 @@ " Science\n", " \n", " \n", - " 2\n", + " 4\n", " Nucleotide depletion promotes cell fate transi...\n", " [Brian T Do, Peggy P Hsu, Sidney Y Vermeulen, ...\n", " 02/06/24\n", @@ -231,28 +253,6 @@ " Developmental cell\n", " \n", " \n", - " 3\n", - " CRISPRi screens identify the lncRNA, LOUP, as ...\n", - " [Haley Halasz, Eric Malekos, Sergio Covarrubia...\n", - " 23/05/24\n", - " 2024\n", - " 38781216\n", - " Long noncoding RNAs (lncRNAs) account for the ...\n", - " 10.1073/pnas.2322524121\n", - " PNAS\n", - " \n", - " \n", - " 4\n", - " Triaging of α-helical proteins to the mitochon...\n", - " [Gayathri Muthukumar, Taylor A Stevens, Alison...\n", - " 02/03/24\n", - " 2024\n", - " 38428433\n", - " Mitochondrial outer membrane ⍺-helical protein...\n", - " 10.1016/j.molcel.2024.01.028\n", - " Molecular cell\n", - " \n", - " \n", " ...\n", " ...\n", " ...\n", @@ -264,7 +264,7 @@ " ...\n", " \n", " \n", - " 258\n", + " 261\n", " Generation of prion transmission barriers by m...\n", " [Peter Chien, Angela H DePace, Sean R Collins,...\n", " 22/08/03\n", @@ -275,7 +275,7 @@ " Nature\n", " \n", " \n", - " 259\n", + " 262\n", " Directed evolution of substrate-optimized GroE...\n", " [Jue D Wang, Christophe Herman, Kimberly A Tip...\n", " 01/01/03\n", @@ -286,7 +286,7 @@ " Cell\n", " \n", " \n", - " 260\n", + " 263\n", " The FAD- and O(2)-dependent reaction cycle of ...\n", " [Benjamin P Tu, Jonathan S Weissman]\n", " 28/11/02\n", @@ -297,7 +297,7 @@ " Molecular cell\n", " \n", " \n", - " 261\n", + " 264\n", " Origins and kinetic consequences of diversity ...\n", " [Angela H DePace, Jonathan S Weissman]\n", " 09/04/02\n", @@ -308,7 +308,7 @@ " Nature structural biology\n", " \n", " \n", - " 262\n", + " 265\n", " The utility of prions.\n", " [Lev Z Osherovich, Jonathan S Weissman]\n", " 08/02/02\n", @@ -320,76 +320,76 @@ " \n", " \n", "\n", - "

263 rows × 8 columns

\n", + "

266 rows × 8 columns

\n", "" ], "text/plain": [ " title \\\n", - "0 Transcriptome-wide characterization of genetic... \n", - "1 Brainwide silencing of prion protein by AAV-me... \n", - "2 Nucleotide depletion promotes cell fate transi... \n", - "3 CRISPRi screens identify the lncRNA, LOUP, as ... \n", - "4 Triaging of α-helical proteins to the mitochon... \n", + "0 Robustness and reliability of single-cell regu... \n", + "1 Multi-species genome-wide CRISPR screens ident... \n", + "2 Transcriptome-wide characterization of genetic... \n", + "3 Brainwide silencing of prion protein by AAV-me... \n", + "4 Nucleotide depletion promotes cell fate transi... \n", ".. ... \n", - "258 Generation of prion transmission barriers by m... \n", - "259 Directed evolution of substrate-optimized GroE... \n", - "260 The FAD- and O(2)-dependent reaction cycle of ... \n", - "261 Origins and kinetic consequences of diversity ... \n", - "262 The utility of prions. \n", + "261 Generation of prion transmission barriers by m... \n", + "262 Directed evolution of substrate-optimized GroE... \n", + "263 The FAD- and O(2)-dependent reaction cycle of ... \n", + "264 Origins and kinetic consequences of diversity ... \n", + "265 The utility of prions. \n", "\n", " authors publication_date \\\n", - "0 [Ajay Nadig, Joseph M Replogle, Angela N Pogso... 15/07/24 \n", - "1 [Edwin N Neumann, Tessa M Bertozzi, Elaine Wu,... 27/06/24 \n", - "2 [Brian T Do, Peggy P Hsu, Sidney Y Vermeulen, ... 02/06/24 \n", - "3 [Haley Halasz, Eric Malekos, Sergio Covarrubia... 23/05/24 \n", - "4 [Gayathri Muthukumar, Taylor A Stevens, Alison... 02/03/24 \n", + "0 [Chen Weng, Jonathan S Weissman, Vijay G Sanka... 04/09/24 \n", + "1 [Breanna Lam, Kathrin M Kajderowicz, Heather R... 02/08/24 \n", + "2 [Ajay Nadig, Joseph M Replogle, Angela N Pogso... 15/07/24 \n", + "3 [Edwin N Neumann, Tessa M Bertozzi, Elaine Wu,... 27/06/24 \n", + "4 [Brian T Do, Peggy P Hsu, Sidney Y Vermeulen, ... 02/06/24 \n", ".. ... ... \n", - "258 [Peter Chien, Angela H DePace, Sean R Collins,... 22/08/03 \n", - "259 [Jue D Wang, Christophe Herman, Kimberly A Tip... 01/01/03 \n", - "260 [Benjamin P Tu, Jonathan S Weissman] 28/11/02 \n", - "261 [Angela H DePace, Jonathan S Weissman] 09/04/02 \n", - "262 [Lev Z Osherovich, Jonathan S Weissman] 08/02/02 \n", + "261 [Peter Chien, Angela H DePace, Sean R Collins,... 22/08/03 \n", + "262 [Jue D Wang, Christophe Herman, Kimberly A Tip... 01/01/03 \n", + "263 [Benjamin P Tu, Jonathan S Weissman] 28/11/02 \n", + "264 [Angela H DePace, Jonathan S Weissman] 09/04/02 \n", + "265 [Lev Z Osherovich, Jonathan S Weissman] 08/02/02 \n", "\n", " publication_year pubmed_id \\\n", - "0 2024 39005298 \n", - "1 2024 38935715 \n", - "2 2024 38823395 \n", - "3 2024 38781216 \n", - "4 2024 38428433 \n", + "0 2024 39229039 \n", + "1 2024 39091747 \n", + "2 2024 39005298 \n", + "3 2024 38935715 \n", + "4 2024 38823395 \n", ".. ... ... \n", - "258 2003 12931190 \n", - "259 2003 12507429 \n", - "260 2002 12453408 \n", - "261 2002 11938354 \n", - "262 2002 11832240 \n", + "261 2003 12931190 \n", + "262 2003 12507429 \n", + "263 2002 12453408 \n", + "264 2002 11938354 \n", + "265 2002 11832240 \n", "\n", " abstract \\\n", - "0 Single cell CRISPR screens such as Perturb-seq... \n", - "1 Prion disease is caused by misfolding of the p... \n", - "2 Control of cellular identity requires coordina... \n", - "3 Long noncoding RNAs (lncRNAs) account for the ... \n", - "4 Mitochondrial outer membrane ⍺-helical protein... \n", + "0 The detection of mitochondrial DNA (mtDNA) mut... \n", + "1 Cells must adapt to environmental changes to m... \n", + "2 Single cell CRISPR screens such as Perturb-seq... \n", + "3 Prion disease is caused by misfolding of the p... \n", + "4 Control of cellular identity requires coordina... \n", ".. ... \n", - "258 Self-propagating beta-sheet-rich protein aggre... \n", - "259 GroEL/S chaperonin ring complexes fold many un... \n", - "260 The endoplasmic reticulum (ER) supports disulf... \n", - "261 A remarkable feature of prions is that infecti... \n", - "262 Infectious, self-propagating protein aggregate... \n", + "261 Self-propagating beta-sheet-rich protein aggre... \n", + "262 GroEL/S chaperonin ring complexes fold many un... \n", + "263 The endoplasmic reticulum (ER) supports disulf... \n", + "264 A remarkable feature of prions is that infecti... \n", + "265 Infectious, self-propagating protein aggregate... \n", "\n", " doi journal \n", - "0 10.1101/2024.07.03.601903 biorxiv \n", - "1 10.1126/science.ado7082 Science \n", - "2 10.1016/j.devcel.2024.05.010 Developmental cell \n", - "3 10.1073/pnas.2322524121 PNAS \n", - "4 10.1016/j.molcel.2024.01.028 Molecular cell \n", + "0 10.1101/2024.08.23.609473 biorxiv \n", + "1 10.1101/2024.07.25.605098 biorxiv \n", + "2 10.1101/2024.07.03.601903 biorxiv \n", + "3 10.1126/science.ado7082 Science \n", + "4 10.1016/j.devcel.2024.05.010 Developmental cell \n", ".. ... ... \n", - "258 10.1038/nature01894 Nature \n", - "259 10.1016/s0092-8674(02)01198-4 Cell \n", - "260 10.1016/s1097-2765(02)00696-2 Molecular cell \n", - "261 10.1038/nsb786 Nature structural biology \n", - "262 10.1016/s1534-5807(02)00118-1 Developmental cell \n", + "261 10.1038/nature01894 Nature \n", + "262 10.1016/s0092-8674(02)01198-4 Cell \n", + "263 10.1016/s1097-2765(02)00696-2 Molecular cell \n", + "264 10.1038/nsb786 Nature structural biology \n", + "265 10.1016/s1534-5807(02)00118-1 Developmental cell \n", "\n", - "[263 rows x 8 columns]" + "[266 rows x 8 columns]" ] }, "execution_count": 8, @@ -451,17 +451,17 @@ " \n", " \n", " 0\n", - " Multi-species genome-wide CRISPR screens ident...\n", - " [Breanna Lam, Kathrin M Kajderowicz, Heather R...\n", - " 02/08/24\n", + " High-quality peptide evidence for annotating n...\n", + " [Eric W Deutsch, Leron W Kok, Jonathan M Mudge...\n", + " 24/09/24\n", " 2024\n", - " 39091747\n", - " Cells must adapt to environmental changes to m...\n", - " 10.1101/2024.07.25.605098\n", + " 39314370\n", + " A major scientific drive is to characterize th...\n", + " 10.1101/2024.09.09.612016\n", " biorxiv\n", " \n", " \n", - " 5\n", + " 7\n", " Author Correction: CRISPR technologies for gen...\n", " [Lukas Villiger, Julia Joung, Luke Koblan, Jon...\n", " 14/05/24\n", @@ -471,46 +471,30 @@ " 10.1038/s41580-024-00745-9\n", " Nature reviews. Molecular cell biology\n", " \n", - " \n", - " 6\n", - " Neuronal activity rapidly reprograms dendritic...\n", - " [Ezgi Hacisuleyman, Caryn R Hale, Natalie Nobl...\n", - " 09/04/24\n", - " 2024\n", - " 38589584\n", - " Learning and memory require activity-induced c...\n", - " 10.1038/s41593-024-01615-5\n", - " Nature neuroscience\n", - " \n", " \n", "\n", "" ], "text/plain": [ " title \\\n", - "0 Multi-species genome-wide CRISPR screens ident... \n", - "5 Author Correction: CRISPR technologies for gen... \n", - "6 Neuronal activity rapidly reprograms dendritic... \n", + "0 High-quality peptide evidence for annotating n... \n", + "7 Author Correction: CRISPR technologies for gen... \n", "\n", " authors publication_date \\\n", - "0 [Breanna Lam, Kathrin M Kajderowicz, Heather R... 02/08/24 \n", - "5 [Lukas Villiger, Julia Joung, Luke Koblan, Jon... 14/05/24 \n", - "6 [Ezgi Hacisuleyman, Caryn R Hale, Natalie Nobl... 09/04/24 \n", + "0 [Eric W Deutsch, Leron W Kok, Jonathan M Mudge... 24/09/24 \n", + "7 [Lukas Villiger, Julia Joung, Luke Koblan, Jon... 14/05/24 \n", "\n", " publication_year pubmed_id \\\n", - "0 2024 39091747 \n", - "5 2024 38740926 \n", - "6 2024 38589584 \n", + "0 2024 39314370 \n", + "7 2024 38740926 \n", "\n", " abstract \\\n", - "0 Cells must adapt to environmental changes to m... \n", - "5 None \n", - "6 Learning and memory require activity-induced c... \n", + "0 A major scientific drive is to characterize th... \n", + "7 None \n", "\n", " doi journal \n", - "0 10.1101/2024.07.25.605098 biorxiv \n", - "5 10.1038/s41580-024-00745-9 Nature reviews. Molecular cell biology \n", - "6 10.1038/s41593-024-01615-5 Nature neuroscience " + "0 10.1101/2024.09.09.612016 biorxiv \n", + "7 10.1038/s41580-024-00745-9 Nature reviews. Molecular cell biology " ] }, "execution_count": 9, @@ -587,7 +571,7 @@ " \n", " \n", " \n", - " 93\n", + " 361\n", " Combinatorial genetics in liver repopulation a...\n", " [Kirk J Wangensteen, Yue J Wang, Zhixun Dou, A...\n", " 02/11/17\n", @@ -595,11 +579,11 @@ " 29091290\n", " Clustered regularly interspaced short palindro...\n", " 10.1002/hep.29626\n", - " Hepatology (Baltimore, Md.)\n", - " current\n", + " Hepatology\n", + " previous\n", " \n", " \n", - " 355\n", + " 96\n", " Combinatorial genetics in liver repopulation a...\n", " [Kirk J Wangensteen, Yue J Wang, Zhixun Dou, A...\n", " 02/11/17\n", @@ -607,11 +591,11 @@ " 29091290\n", " Clustered regularly interspaced short palindro...\n", " 10.1002/hep.29626\n", - " Hepatology\n", - " previous\n", + " Hepatology (Baltimore, Md.)\n", + " current\n", " \n", " \n", - " 122\n", + " 390\n", " Targeting the AAA ATPase p97 as an Approach to...\n", " [Daniel J Anderson, Ronan Le Moigne, Stevan Dj...\n", " 12/11/15\n", @@ -620,10 +604,10 @@ " p97 is a AAA-ATPase with multiple cellular fun...\n", " 10.1016/j.ccell.2015.10.002\n", " Cancer cell\n", - " current\n", + " previous\n", " \n", " \n", - " 384\n", + " 125\n", " Targeting the AAA ATPase p97 as an Approach to...\n", " [Daniel J Anderson, Ronan Le Moigne, Stevan Dj...\n", " 12/11/15\n", @@ -632,10 +616,10 @@ " p97 is a AAA-ATPase with multiple cellular fun...\n", " 10.1016/j.ccell.2015.10.002\n", " Cancer cell\n", - " previous\n", + " current\n", " \n", " \n", - " 428\n", + " 434\n", " Ribosome profiling provides evidence that larg...\n", " [Mitchell Guttman, Pamela Russell, Nicholas T ...\n", " 03/07/13\n", @@ -659,7 +643,7 @@ " ...\n", " \n", " \n", - " 390\n", + " 131\n", " Pharmacological dimerization and activation of...\n", " [Carmela Sidrauski, Jordan C Tsai, Martin Kamp...\n", " 16/04/15\n", @@ -668,10 +652,10 @@ " The general translation initiation factor eIF2...\n", " 10.7554/eLife.07314\n", " eLife\n", - " previous\n", + " current\n", " \n", " \n", - " 124\n", + " 127\n", " Paradoxical resistance of multiple myeloma to ...\n", " [Diego Acosta-Alvear, Min Y Cho, Thomas Wild, ...\n", " 04/09/15\n", @@ -683,7 +667,7 @@ " current\n", " \n", " \n", - " 386\n", + " 392\n", " Paradoxical resistance of multiple myeloma to ...\n", " [Diego Acosta-Alvear, Min Y Cho, Thomas Wild, ...\n", " 04/09/15\n", @@ -695,7 +679,7 @@ " previous\n", " \n", " \n", - " 354\n", + " 95\n", " The Human Cell Atlas.\n", " [Aviv Regev, Sarah A Teichmann, Eric S Lander,...\n", " 06/12/17\n", @@ -704,10 +688,10 @@ " The recent advent of methods for high-throughp...\n", " 10.7554/eLife.27041\n", " eLife\n", - " previous\n", + " current\n", " \n", " \n", - " 92\n", + " 360\n", " The Human Cell Atlas.\n", " [Aviv Regev, Sarah A Teichmann, Eric S Lander,...\n", " 06/12/17\n", @@ -716,80 +700,80 @@ " The recent advent of methods for high-throughp...\n", " 10.7554/eLife.27041\n", " eLife\n", - " current\n", + " previous\n", " \n", " \n", "\n", - "

104 rows × 9 columns

\n", + "

106 rows × 9 columns

\n", "" ], "text/plain": [ " title \\\n", - "93 Combinatorial genetics in liver repopulation a... \n", - "355 Combinatorial genetics in liver repopulation a... \n", - "122 Targeting the AAA ATPase p97 as an Approach to... \n", - "384 Targeting the AAA ATPase p97 as an Approach to... \n", - "428 Ribosome profiling provides evidence that larg... \n", + "361 Combinatorial genetics in liver repopulation a... \n", + "96 Combinatorial genetics in liver repopulation a... \n", + "390 Targeting the AAA ATPase p97 as an Approach to... \n", + "125 Targeting the AAA ATPase p97 as an Approach to... \n", + "434 Ribosome profiling provides evidence that larg... \n", ".. ... \n", - "390 Pharmacological dimerization and activation of... \n", - "124 Paradoxical resistance of multiple myeloma to ... \n", - "386 Paradoxical resistance of multiple myeloma to ... \n", - "354 The Human Cell Atlas. \n", - "92 The Human Cell Atlas. \n", + "131 Pharmacological dimerization and activation of... \n", + "127 Paradoxical resistance of multiple myeloma to ... \n", + "392 Paradoxical resistance of multiple myeloma to ... \n", + "95 The Human Cell Atlas. \n", + "360 The Human Cell Atlas. \n", "\n", " authors publication_date \\\n", - "93 [Kirk J Wangensteen, Yue J Wang, Zhixun Dou, A... 02/11/17 \n", - "355 [Kirk J Wangensteen, Yue J Wang, Zhixun Dou, A... 02/11/17 \n", - "122 [Daniel J Anderson, Ronan Le Moigne, Stevan Dj... 12/11/15 \n", - "384 [Daniel J Anderson, Ronan Le Moigne, Stevan Dj... 12/11/15 \n", - "428 [Mitchell Guttman, Pamela Russell, Nicholas T ... 03/07/13 \n", + "361 [Kirk J Wangensteen, Yue J Wang, Zhixun Dou, A... 02/11/17 \n", + "96 [Kirk J Wangensteen, Yue J Wang, Zhixun Dou, A... 02/11/17 \n", + "390 [Daniel J Anderson, Ronan Le Moigne, Stevan Dj... 12/11/15 \n", + "125 [Daniel J Anderson, Ronan Le Moigne, Stevan Dj... 12/11/15 \n", + "434 [Mitchell Guttman, Pamela Russell, Nicholas T ... 03/07/13 \n", ".. ... ... \n", - "390 [Carmela Sidrauski, Jordan C Tsai, Martin Kamp... 16/04/15 \n", - "124 [Diego Acosta-Alvear, Min Y Cho, Thomas Wild, ... 04/09/15 \n", - "386 [Diego Acosta-Alvear, Min Y Cho, Thomas Wild, ... 04/09/15 \n", - "354 [Aviv Regev, Sarah A Teichmann, Eric S Lander,... 06/12/17 \n", - "92 [Aviv Regev, Sarah A Teichmann, Eric S Lander,... 06/12/17 \n", + "131 [Carmela Sidrauski, Jordan C Tsai, Martin Kamp... 16/04/15 \n", + "127 [Diego Acosta-Alvear, Min Y Cho, Thomas Wild, ... 04/09/15 \n", + "392 [Diego Acosta-Alvear, Min Y Cho, Thomas Wild, ... 04/09/15 \n", + "95 [Aviv Regev, Sarah A Teichmann, Eric S Lander,... 06/12/17 \n", + "360 [Aviv Regev, Sarah A Teichmann, Eric S Lander,... 06/12/17 \n", "\n", " publication_year pubmed_id \\\n", - "93 2017 29091290 \n", - "355 2017 29091290 \n", - "122 2015 26555175 \n", - "384 2015 26555175 \n", - "428 2013 23810193 \n", + "361 2017 29091290 \n", + "96 2017 29091290 \n", + "390 2015 26555175 \n", + "125 2015 26555175 \n", + "434 2013 23810193 \n", ".. ... ... \n", - "390 2015 25875391 \n", - "124 2015 26327694 \n", - "386 2015 26327694 \n", - "354 2017 29206104 \n", - "92 2017 29206104 \n", + "131 2015 25875391 \n", + "127 2015 26327694 \n", + "392 2015 26327694 \n", + "95 2017 29206104 \n", + "360 2017 29206104 \n", "\n", " abstract \\\n", - "93 Clustered regularly interspaced short palindro... \n", - "355 Clustered regularly interspaced short palindro... \n", - "122 p97 is a AAA-ATPase with multiple cellular fun... \n", - "384 p97 is a AAA-ATPase with multiple cellular fun... \n", - "428 Large noncoding RNAs are emerging as an import... \n", + "361 Clustered regularly interspaced short palindro... \n", + "96 Clustered regularly interspaced short palindro... \n", + "390 p97 is a AAA-ATPase with multiple cellular fun... \n", + "125 p97 is a AAA-ATPase with multiple cellular fun... \n", + "434 Large noncoding RNAs are emerging as an import... \n", ".. ... \n", - "390 The general translation initiation factor eIF2... \n", - "124 Hallmarks of cancer, including rapid growth an... \n", - "386 Hallmarks of cancer, including rapid growth an... \n", - "354 The recent advent of methods for high-throughp... \n", - "92 The recent advent of methods for high-throughp... \n", + "131 The general translation initiation factor eIF2... \n", + "127 Hallmarks of cancer, including rapid growth an... \n", + "392 Hallmarks of cancer, including rapid growth an... \n", + "95 The recent advent of methods for high-throughp... \n", + "360 The recent advent of methods for high-throughp... \n", "\n", " doi journal update \n", - "93 10.1002/hep.29626 Hepatology (Baltimore, Md.) current \n", - "355 10.1002/hep.29626 Hepatology previous \n", - "122 10.1016/j.ccell.2015.10.002 Cancer cell current \n", - "384 10.1016/j.ccell.2015.10.002 Cancer cell previous \n", - "428 10.1016/j.cell.2013.06.009 Cell previous \n", + "361 10.1002/hep.29626 Hepatology previous \n", + "96 10.1002/hep.29626 Hepatology (Baltimore, Md.) current \n", + "390 10.1016/j.ccell.2015.10.002 Cancer cell previous \n", + "125 10.1016/j.ccell.2015.10.002 Cancer cell current \n", + "434 10.1016/j.cell.2013.06.009 Cell previous \n", ".. ... ... ... \n", - "390 10.7554/eLife.07314 eLife previous \n", - "124 10.7554/eLife.08153 eLife current \n", - "386 10.7554/eLife.08153 eLife previous \n", - "354 10.7554/eLife.27041 eLife previous \n", - "92 10.7554/eLife.27041 eLife current \n", + "131 10.7554/eLife.07314 eLife current \n", + "127 10.7554/eLife.08153 eLife current \n", + "392 10.7554/eLife.08153 eLife previous \n", + "95 10.7554/eLife.27041 eLife current \n", + "360 10.7554/eLife.27041 eLife previous \n", "\n", - "[104 rows x 9 columns]" + "[106 rows x 9 columns]" ] }, "execution_count": 11, @@ -854,7 +838,7 @@ " \n", " \n", " \n", - " 8\n", + " 11\n", " Author Correction: Efficient C•G-to-G•C base e...\n", " [Luke W Koblan, Mandana Arbab, Max W Shen, Jef...\n", " 19/10/23\n", @@ -870,17 +854,17 @@ "" ], "text/plain": [ - " title \\\n", - "8 Author Correction: Efficient C•G-to-G•C base e... \n", + " title \\\n", + "11 Author Correction: Efficient C•G-to-G•C base e... \n", "\n", - " authors publication_date \\\n", - "8 [Luke W Koblan, Mandana Arbab, Max W Shen, Jef... 19/10/23 \n", + " authors publication_date \\\n", + "11 [Luke W Koblan, Mandana Arbab, Max W Shen, Jef... 19/10/23 \n", "\n", - " publication_year pubmed_id abstract doi \\\n", - "8 2023 37853259 None 10.1038/s41587-023-02028-8 \n", + " publication_year pubmed_id abstract doi \\\n", + "11 2023 37853259 None 10.1038/s41587-023-02028-8 \n", "\n", - " journal update \n", - "8 Nature biotechnology previous " + " journal update \n", + "11 Nature biotechnology previous " ] }, "execution_count": 12, @@ -922,7 +906,65 @@ { "data": { "text/plain": [ - "[{'title': 'Multi-species genome-wide CRISPR screens identify GPX4 as a conserved suppressor of cold-induced cell death.',\n", + "[{'title': 'High-quality peptide evidence for annotating non-canonical open reading frames as human proteins.',\n", + " 'authors': ['Eric W Deutsch',\n", + " 'Leron W Kok',\n", + " 'Jonathan M Mudge',\n", + " 'Jorge Ruiz-Orera',\n", + " 'Ivo Fierro-Monti',\n", + " 'Zhi Sun',\n", + " 'Jennifer G Abelin',\n", + " 'M Mar Alba',\n", + " 'Julie L Aspden',\n", + " 'Ariel A Bazzini',\n", + " 'Elspeth A Bruford',\n", + " 'Marie A Brunet',\n", + " 'Lorenzo Calviello',\n", + " 'Steven A Carr',\n", + " 'Anne-Ruxandra Carvunis',\n", + " 'Sonia Chothani',\n", + " 'Jim Clauwaert',\n", + " 'Kellie Dean',\n", + " 'Pouya Faridi',\n", + " 'Adam Frankish',\n", + " 'Norbert Hubner',\n", + " 'Nicholas T Ingolia',\n", + " 'Michele Magrane',\n", + " 'Maria Jesus Martin',\n", + " 'Thomas F Martinez',\n", + " 'Gerben Menschaert',\n", + " 'Uwe Ohler',\n", + " 'Sandra Orchard',\n", + " 'Owen Rackham',\n", + " 'Xavier Roucou',\n", + " 'Sarah A Slavoff',\n", + " 'Eivind Valen',\n", + " 'Aaron Wacholder',\n", + " 'Jonathan S Weissman',\n", + " 'Wei Wu',\n", + " 'Zhi Xie',\n", + " 'Jyoti Choudhary',\n", + " 'Michal Bassani-Sternberg',\n", + " 'Juan Antonio Vizcaíno',\n", + " 'Nicola Ternette',\n", + " 'Robert L Moritz',\n", + " 'John R Prensner',\n", + " 'Sebastiaan van Heesch'],\n", + " 'publication_date': '24/09/24',\n", + " 'publication_year': '2024',\n", + " 'pubmed_id': '39314370',\n", + " 'abstract': 'A major scientific drive is to characterize the protein-coding genome as it provides the primary basis for the study of human health. But the fundamental question remains: what has been missed in prior genomic analyses? Over the past decade, the translation of non-canonical open reading frames (ncORFs) has been observed across human cell types and disease states, with major implications for proteomics, genomics, and clinical science. However, the impact of ncORFs has been limited by the absence of a large-scale understanding of their contribution to the human proteome. Here, we report the collaborative efforts of stakeholders in proteomics, immunopeptidomics, Ribo-seq ORF discovery, and gene annotation, to produce a consensus landscape of protein-level evidence for ncORFs. We show that at least 25% of a set of 7,264 ncORFs give rise to translated gene products, yielding over 3,000 peptides in a pan-proteome analysis encompassing 3.8 billion mass spectra from 95,520 experiments. With these data, we developed an annotation framework for ncORFs and created public tools for researchers through GENCODE and PeptideAtlas. This work will provide a platform to advance ncORF-derived proteins in biomedical discovery and, beyond humans, diverse animals and plants where ncORFs are similarly observed.',\n", + " 'doi': '10.1101/2024.09.09.612016',\n", + " 'journal': 'biorxiv'},\n", + " {'title': 'Robustness and reliability of single-cell regulatory multi-omics with deep mitochondrial mutation profiling.',\n", + " 'authors': ['Chen Weng', 'Jonathan S Weissman', 'Vijay G Sankaran'],\n", + " 'publication_date': '04/09/24',\n", + " 'publication_year': '2024',\n", + " 'pubmed_id': '39229039',\n", + " 'abstract': 'The detection of mitochondrial DNA (mtDNA) mutations in single cells holds considerable potential to define clonal relationships coupled with information on cell state in humans. Previous methods focused on higher heteroplasmy mutations that are limited in number and can be influenced by functional selection, introducing biases for lineage tracing. Although more challenging to detect, intermediate to low heteroplasmy mtDNA mutations are valuable due to their high diversity, abundance, and lower propensity to selection. To enhance mtDNA mutation detection and facilitate fine-scale lineage tracing, we developed the single-cell Regulatory multi-omics with Deep Mitochondrial mutation profiling (ReDeeM) approach, an integrated experimental and computational framework. Recently, some concerns have been raised about the analytical workflow in the ReDeeM framework. Specifically, it was noted that the mutations detected in a single molecule per cell are enriched on edges of mtDNA molecules, suggesting they resemble artifacts reported in other sequencing approaches. It was then proposed that all mutations found in one molecule per cell should be removed. We detail our error correction method, demonstrating that the observed edge mutations are distinct from previously reported sequencing artifacts. We further show that the proposed removal leads to massive elimination of bona fide and informative mutations. Indeed, mutations accumulating on edges impact a minority of all mutation calls (for example, in hematopoietic stem cells, the excess mutations on the edge account for only 4.3%-7.6% of the total). Recognizing the value of addressing edge mutations even after applying consensus correction, we provide an additional filtering option in the ReDeeM-R package. This approach effectively eliminates the position biases, leads to a mutational signature indistinguishable from bona fide mitochondrial mutations, and removes excess low molecule high connectedness mutations. Importantly, this option preserves the large majority of unique mutations identified by ReDeeM, maintaining the ability of ReDeeM to provide a more than 10-fold increase in variant detection compared to previous methods. Additionally, the cells remain well-connected. While there is room for further refinement in mutation calling strategies, the significant advances and biological insights provided by the ReDeeM framework are unique and remain intact. We hope that this detailed discussion and analysis enables the community to employ this approach and contribute to its further development.',\n", + " 'doi': '10.1101/2024.08.23.609473',\n", + " 'journal': 'biorxiv'},\n", + " {'title': 'Multi-species genome-wide CRISPR screens identify GPX4 as a conserved suppressor of cold-induced cell death.',\n", " 'authors': ['Breanna Lam',\n", " 'Kathrin M Kajderowicz',\n", " 'Heather R Keys',\n", @@ -5416,7 +5458,7 @@ { "data": { "text/plain": [ - "415914" + "421447" ] }, "execution_count": 15, @@ -5428,587 +5470,6 @@ "open('_data/publications.yml', 'w').write(yaml.dump(pubs_records, default_flow_style=False, sort_keys=False))" ] }, - { - "cell_type": "markdown", - "id": "e32e075a-79f6-436a-bfb6-5b5862ddc492", - "metadata": { - "jp-MarkdownHeadingCollapsed": true, - "tags": [] - }, - "source": [ - "### Previous Site" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "id": "c9db6a5a-bfbc-443b-9669-f171868df41f", - "metadata": {}, - "outputs": [], - "source": [ - "people_url = 'https://weissmanlab.ucsf.edu/people/people.html'\n", - "alum_url = 'https://weissmanlab.ucsf.edu/people/alumni.html'\n", - "people_page = requests.get(people_url)\n", - "alum_page = requests.get(alum_url)\n", - "\n", - "people_soup = BeautifulSoup(people_page.text, 'html.parser')\n", - "alum_soup = BeautifulSoup(alum_page.text, 'html.parser')\n", - "\n", - "def get_text(elem, id):\n", - " elem = elem.find(id=id)\n", - " if elem: return elem.get_text(separator='|')\n", - " else: return ''\n", - "\n", - "people = [dict(name=get_text(person, 'peo_name').replace('|', ' '),\n", - " pos=get_text(person, 'peo_pos'),\n", - " email=get_text(person, 'peo_email'),\n", - " img=person.find('img').get('src')) for person in people_soup.find_all(id='peo_grid')]\n", - "alums = [dict(name=get_text(person, 'peo_name').replace('|', ' '),\n", - " pos=get_text(person, 'alum_pos'),\n", - " now=get_text(person, 'alum_current_2line'),\n", - " img=(person.find('img').get('src') if person.find('img') else None)) for person in alum_soup.find_all(id='peo_grid')][1:]\n", - "\n", - "for p in people: p['first_name'] = p['name'].split(' ')[0]\n", - "for p in people: p['last_name'] = p['name'].split(' ')[-1]\n", - "for p in alums: p['first_name'] = p['name'].split(' ')[0]\n", - "for p in alums: p['last_name'] = p['name'].split(' ')[-1]\n", - "\n", - "for p in people: p['alum'] = 'false'\n", - "for p in alums: p['alum'] = 'true'" - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "id": "a5da71f6-735b-4f58-8c4b-8e6e337d8a03", - "metadata": {}, - "outputs": [], - "source": [ - "for person in people:\n", - " urllib.request.urlretrieve('https://weissmanlab.ucsf.edu/people/'+person['img'], 'assets/img/people/'+person['img'])" - ] - }, - { - "cell_type": "code", - "execution_count": 7, - "id": "3c4d06e8-a2b7-48f0-b171-056da66db1b2", - "metadata": {}, - "outputs": [], - "source": [ - "for person in alums:\n", - " urllib.request.urlretrieve('https://weissmanlab.ucsf.edu/people/'+person['img'], 'assets/img/people/'+person['img'].split('/')[-1])\n", - "\n", - " person['img'] = person['img'].split('/')[-1]" - ] - }, - { - "cell_type": "code", - "execution_count": 8, - "id": "512e3021-c766-45fa-ad1e-ceeded366531", - "metadata": {}, - "outputs": [], - "source": [ - "people = people + alums\n", - "for p in people: p['id'] = p['first_name']+p['last_name']" - ] - }, - { - "cell_type": "code", - "execution_count": 9, - "id": "ba432453-e1a0-4259-9100-333814d65c98", - "metadata": {}, - "outputs": [], - "source": [ - "def rename_img(p):\n", - " if p['img'] == 'weibezahn.jpg' or p['img'] == '':\n", - " p['img'] = ''\n", - " else:\n", - " change_from = f'assets/img/people/{p[\"img\"]}'\n", - " change_to = f'assets/img/people/{p[\"id\"]+\".\"+p[\"img\"].split(\".\")[-1]}'\n", - " if os.path.exists(change_from): os.rename(change_from, change_to)\n", - " p[\"img\"] = change_to\n", - "\n", - "for p in people: rename_img(p)" - ] - }, - { - "cell_type": "code", - "execution_count": 13, - "id": "98004665-db2f-4927-9d8e-366c79ca4dda", - "metadata": {}, - "outputs": [], - "source": [ - "pd.DataFrame(people).to_csv('old_site_people.csv', index=False)" - ] - }, - { - "cell_type": "markdown", - "id": "4e853d1d-8cbe-470c-9557-0c737bc99f80", - "metadata": { - "jp-MarkdownHeadingCollapsed": true, - "tags": [] - }, - "source": [ - "### Survey" - ] - }, - { - "cell_type": "code", - "execution_count": 15, - "id": "83b4d932-3ec7-4c34-8400-a55be0447c7a", - "metadata": {}, - "outputs": [], - "source": [ - "people = pd.read_csv('old_site_people.csv')" - ] - }, - { - "cell_type": "code", - "execution_count": 29, - "id": "17964390-6a81-4e90-aa28-0e49387c6f4d", - "metadata": { - "tags": [] - }, - "outputs": [], - "source": [ - "survey_responses = pd.read_csv('https://docs.google.com/spreadsheets/d/1uxl0DQpqHvNdgI92UVx1Vyt4TQhkgt74cPp1dEn3Gjw'+'/export?format=csv')" - ] - }, - { - "cell_type": "code", - "execution_count": 30, - "id": "504ae2e7-1a4f-49c7-a12f-31392537847b", - "metadata": { - "tags": [] - }, - "outputs": [], - "source": [ - "survey_responses = survey_responses.rename(columns={'Name':'name', 'Role':'pos', 'Email':'email', 'Portrait / head shot':'img'})[['name', 'pos', 'email', 'img']]" - ] - }, - { - "cell_type": "code", - "execution_count": 32, - "id": "280e57d6-b062-4d48-aae5-5c7d651b4c35", - "metadata": {}, - "outputs": [], - "source": [ - "survey_responses['first_name'] = survey_responses['name'].str.split(' ').str[0]\n", - "survey_responses['last_name'] = survey_responses['name'].str.split(' ').str[-1]\n", - "survey_responses['id'] = survey_responses['first_name']+survey_responses['last_name']\n", - "survey_responses['alum'] = False" - ] - }, - { - "cell_type": "code", - "execution_count": 46, - "id": "e4bc1dee-1491-4231-8d6e-3d206eee1d06", - "metadata": { - "collapsed": true, - "jupyter": { - "outputs_hidden": true - }, - "tags": [] - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "RichardShe https://drive.google.com/open?id=1pAqQi52Pr1B0xIEtMr3XaAas1hVMW08w\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=1pAqQi52Pr1B0xIEtMr3XaAas1hVMW08w\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/RichardShe.jpg\n", - "100%|██████████| 588k/588k [00:00<00:00, 15.7MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "LakshmiMiller-Vedam https://drive.google.com/open?id=1pAkanvnqJmd1D9i7Onl_6_lWLmg5nugY\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=1pAkanvnqJmd1D9i7Onl_6_lWLmg5nugY\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/LakshmiMiller-Vedam.jpg\n", - "100%|██████████| 95.3k/95.3k [00:00<00:00, 3.84MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "LukeKoblan https://drive.google.com/open?id=1IsF8g-d_w7A4XTUmI_2t21q2jGv0EKTf\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=1IsF8g-d_w7A4XTUmI_2t21q2jGv0EKTf\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/LukeKoblan.jpg\n", - "100%|██████████| 2.34M/2.34M [00:00<00:00, 15.1MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "ZebulonLevine https://drive.google.com/open?id=12ColnJvOtz18CTVoc9p1HeKm4R3hjHV7\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=12ColnJvOtz18CTVoc9p1HeKm4R3hjHV7\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/ZebulonLevine.jpg\n", - "100%|██████████| 11.4k/11.4k [00:00<00:00, 25.4MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "JosephReplogle https://drive.google.com/open?id=1ycj11mfsZUJiOY9RFpyb7svJ9n9vCGSm\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=1ycj11mfsZUJiOY9RFpyb7svJ9n9vCGSm\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/JosephReplogle.jpg\n", - "100%|██████████| 968k/968k [00:00<00:00, 7.15MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "XiaojieQiu https://drive.google.com/open?id=14JxH-Gx2PkGrvIdslelK6CgbahXjb7L7\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=14JxH-Gx2PkGrvIdslelK6CgbahXjb7L7\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/XiaojieQiu.jpg\n", - "100%|██████████| 16.5k/16.5k [00:00<00:00, 16.5MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "ReubenSaunders https://drive.google.com/open?id=10yqkD80mUAibxDNiJWbtOaT9azrITN72\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=10yqkD80mUAibxDNiJWbtOaT9azrITN72\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/ReubenSaunders.jpg\n", - "100%|██████████| 398k/398k [00:00<00:00, 6.58MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "MattJones https://drive.google.com/open?id=1rl68JZd9UYCybIeylNaRMxtVB4ktF3HJ\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=1rl68JZd9UYCybIeylNaRMxtVB4ktF3HJ\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/MattJones.jpg\n", - "100%|██████████| 561k/561k [00:00<00:00, 8.76MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "SarahSchumacher https://drive.google.com/open?id=1WJ5Kl7qaNTYB1kAHIrqmdt9fOOtlsKF3\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=1WJ5Kl7qaNTYB1kAHIrqmdt9fOOtlsKF3\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/SarahSchumacher.jpg\n", - "100%|██████████| 117k/117k [00:00<00:00, 4.44MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "TessaBertozzi https://drive.google.com/open?id=1TQJiPteaOk8HthDPapEFRKNCALgAHSZS\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=1TQJiPteaOk8HthDPapEFRKNCALgAHSZS\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/TessaBertozzi.jpg\n", - "100%|██████████| 2.70M/2.70M [00:00<00:00, 14.7MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "AnneOdera https://drive.google.com/open?id=1BPMTR0JQd6V5aXAZXH9SZZyEUm54-6_d\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=1BPMTR0JQd6V5aXAZXH9SZZyEUm54-6_d\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/AnneOdera.jpg\n", - "100%|██████████| 274k/274k [00:00<00:00, 7.57MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "AlexLeNail https://drive.google.com/open?id=1V8zAqzjdeIdUFCUeWB1lfqZI7ZRyx0la\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=1V8zAqzjdeIdUFCUeWB1lfqZI7ZRyx0la\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/AlexLeNail.jpg\n", - "100%|██████████| 857k/857k [00:00<00:00, 10.9MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "YiChen nan\n", - "AtharvOak https://drive.google.com/open?id=1AW-fszVxhPoQbhk56kCzeOxANBBjE7M0\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=1AW-fszVxhPoQbhk56kCzeOxANBBjE7M0\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/AtharvOak.jpg\n", - "100%|██████████| 626k/626k [00:00<00:00, 8.41MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "CristenMuresan https://drive.google.com/open?id=14lJw4f2eAHCqmJ3z6O_zqd8CxpfBG9am\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=14lJw4f2eAHCqmJ3z6O_zqd8CxpfBG9am\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/CristenMuresan.jpg\n", - "100%|██████████| 1.12M/1.12M [00:00<00:00, 9.71MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "GayathriMuthukumar https://drive.google.com/open?id=1acceshE6cnXyvun9ehg_5EQhADp-gn26\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=1acceshE6cnXyvun9ehg_5EQhADp-gn26\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/GayathriMuthukumar.jpg\n", - "100%|██████████| 5.27M/5.27M [00:00<00:00, 17.1MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "KaterinaPopova https://drive.google.com/open?id=1pUpF7EhZn8E7RWAQJMKqZkDf5Z65PT9s\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=1pUpF7EhZn8E7RWAQJMKqZkDf5Z65PT9s\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/KaterinaPopova.jpg\n", - "100%|██████████| 120k/120k [00:00<00:00, 4.43MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "YuanchengLu https://drive.google.com/open?id=1uH4d9gunYYbGys_pbbOdjgG-ZFjv8Zyx\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=1uH4d9gunYYbGys_pbbOdjgG-ZFjv8Zyx\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/YuanchengLu.jpg\n", - "100%|██████████| 266k/266k [00:00<00:00, 6.95MB/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "KatieYost https://drive.google.com/open?id=15BWQLjHXdd5f-6h_klvKl87e1t4Kx0gU\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Downloading...\n", - "From: https://drive.google.com/uc?id=15BWQLjHXdd5f-6h_klvKl87e1t4Kx0gU\n", - "To: /Users/alex/Documents/weissmanlab/assets/img/people/KatieYost.jpg\n", - "100%|██████████| 742k/742k [00:00<00:00, 10.5MB/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "JeffHussmann nan\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n" - ] - } - ], - "source": [ - "for id, url in survey_responses.set_index('id')['img'].items():\n", - " print(id, url)\n", - " if type(url) == str:\n", - " change_to = 'assets/img/people/'+id+'.jpg'\n", - " gdown.download(\"https://drive.google.com/uc?id={}\".format(url.split('id=')[-1]), change_to, quiet=False)" - ] - }, - { - "cell_type": "code", - "execution_count": 57, - "id": "74f66f3d-4a49-4d73-991e-e62c9416f419", - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "{'JeffHussmann',\n", - " 'JosephReplogle',\n", - " 'KaterinaPopova',\n", - " 'LakshmiMiller-Vedam',\n", - " 'MattJones',\n", - " 'ReubenSaunders',\n", - " 'RichardShe',\n", - " 'XiaojieQiu'}" - ] - }, - "execution_count": 57, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "set(people.id) & set(survey_responses.id)" - ] - }, - { - "cell_type": "code", - "execution_count": 58, - "id": "7d2f4403-4974-4908-8d1c-bacb7e100f52", - "metadata": {}, - "outputs": [], - "source": [ - "people = pd.concat((survey_responses, people)).drop_duplicates(subset=['id'], keep='first')" - ] - }, - { - "cell_type": "code", - "execution_count": 61, - "id": "d84fa7d0-7baa-415a-b106-0757dba17200", - "metadata": {}, - "outputs": [], - "source": [ - "people = people.drop('img', axis=1)" - ] - }, - { - "cell_type": "code", - "execution_count": 63, - "id": "14da890a-1c09-49d0-9bea-f88a671e4408", - "metadata": {}, - "outputs": [], - "source": [ - "people.to_csv('old_site_and_survey_people.csv', index=False)" - ] - }, - { - "cell_type": "code", - "execution_count": 64, - "id": "8cd15a5b-b5cd-47ed-b7ec-94b7343114c2", - "metadata": {}, - "outputs": [], - "source": [ - "pd.DataFrame(people).to_clipboard()" - ] - }, { "cell_type": "markdown", "id": "ce98febf-fc16-4529-b8d6-2630646bb4fe", @@ -6021,7 +5482,7 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 16, "id": "e6707396-53be-4d3c-a270-0077d0dae0d3", "metadata": {}, "outputs": [], @@ -6051,9 +5512,17 @@ "# id must be both the publication first/last, and the name of the image. Name is just the display name." ] }, + { + "cell_type": "markdown", + "id": "d4665bcf", + "metadata": {}, + "source": [ + "## Update people page" + ] + }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 17, "id": "006f6993-ac2b-4298-ad0f-ff149387735f", "metadata": {}, "outputs": [], @@ -6067,7 +5536,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 18, "id": "1898b1f0-9b78-48c5-bf38-ac1db5fb4158", "metadata": {}, "outputs": [], @@ -6088,7 +5557,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 19, "id": "02ddcce2-a14f-43f0-b507-2d1d86843a18", "metadata": {}, "outputs": [ @@ -6140,13 +5609,13 @@ "4 Maria Gould Admin Assistant mgould@wi.mit.edu MariaGould False NaN" ] }, - "execution_count": 5, + "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "people[ ~people.id.isin(old_people_data.id)]\n" + "people[ ~people.id.isin(old_people_data.id)]" ] }, { @@ -6159,7 +5628,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 20, "id": "368d3214-2842-403f-adfb-521f50a19f7c", "metadata": {}, "outputs": [ @@ -6195,23 +5664,23 @@ " \n", " \n", " \n", - " 47\n", - " Audrey Lim\n", - " Undergrad\n", - " alim@wi.mit.edu\n", - " AudreyLim\n", - " True\n", + " 116\n", + " Gene-Wei Li\n", + " Post-doc\n", " NaN\n", + " Gene-WeiLi\n", + " True\n", + " PI, Associate Professor of Biology & HHMI Inve...\n", " current\n", " \n", " \n", - " 46\n", - " Audrey Lim\n", - " Undergrad\n", - " alim@wi.mit.edu\n", - " AudreyLim\n", - " False\n", + " 116\n", + " Gene-Wei Li\n", + " Post-doc\n", " NaN\n", + " Gene-WeiLi\n", + " True\n", + " PI & Associate Professor of Biology | Massachu...\n", " previous\n", " \n", " \n", @@ -6219,12 +5688,16 @@ "" ], "text/plain": [ - " name pos email id alum now update\n", - "47 Audrey Lim Undergrad alim@wi.mit.edu AudreyLim True NaN current\n", - "46 Audrey Lim Undergrad alim@wi.mit.edu AudreyLim False NaN previous" + " name pos email id alum \\\n", + "116 Gene-Wei Li Post-doc NaN Gene-WeiLi True \n", + "116 Gene-Wei Li Post-doc NaN Gene-WeiLi True \n", + "\n", + " now update \n", + "116 PI, Associate Professor of Biology & HHMI Inve... current \n", + "116 PI & Associate Professor of Biology | Massachu... previous " ] }, - "execution_count": 6, + "execution_count": 20, "metadata": {}, "output_type": "execute_result" } @@ -6246,7 +5719,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 21, "id": "f1233203-5d3a-455d-8ced-5faa1da00d73", "metadata": {}, "outputs": [ @@ -6281,17 +5754,29 @@ " \n", " \n", " \n", + " \n", + " 42\n", + " Haarika Kathi\n", + " Technician\n", + " hkathi@wi.mit.edu\n", + " HaarikaKathi\n", + " False\n", + " NaN\n", + " previous\n", + " \n", " \n", "\n", "" ], "text/plain": [ - "Empty DataFrame\n", - "Columns: [name, pos, email, id, alum, now, update]\n", - "Index: []" + " name pos email id alum now \\\n", + "42 Haarika Kathi Technician hkathi@wi.mit.edu HaarikaKathi False NaN \n", + "\n", + " update \n", + "42 previous " ] }, - "execution_count": 7, + "execution_count": 21, "metadata": {}, "output_type": "execute_result" } @@ -6312,7 +5797,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 22, "id": "922ec1a1-b130-4595-a994-0ae9fe3d4f64", "metadata": {}, "outputs": [], @@ -6323,7 +5808,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 23, "id": "e43cf38b-3bf5-489e-912b-c081151b2fb9", "metadata": {}, "outputs": [], @@ -6340,17 +5825,17 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 24, "id": "b72f7d29-d480-4646-8afb-f7bb3f49a9aa", "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "20581" + "20657" ] }, - "execution_count": 10, + "execution_count": 24, "metadata": {}, "output_type": "execute_result" } @@ -6370,7 +5855,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3 (ipykernel)", + "display_name": "py-env", "language": "python", "name": "python3" },