Merge pull request #381 from BU-ISCIII/develop

Develop merge for 2.2.3 release
BU-ISCIII · Dec 23, 2024 · 6d9f0a2 · 6d9f0a2
2 parents 86556c4 + fd589bb
commit 6d9f0a2
Show file tree

Hide file tree

Showing 115 changed files with 373 additions and 327 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -4,18 +4,52 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [2.X.Xdev] - 2024-0X-XX : https://github.com/BU-ISCIII/buisciii-tools/releases/tag/2.X.X
+## [2.X.Xhot] - 2024-0X-0X : https://github.com/BU-ISCIII/buisciii-tools/releases/tag/2.X.3
 
 ### Credits
 
+Code contributions to the hotfix:
+
+### Template fixes and updates
+
+### Modules
+
+#### Added enhancements
+
+#### Fixes
+
+#### Changed
+
+#### Removed
+
+### Requirements
+
+## [2.2.3] - 2024-12-23 : https://github.com/BU-ISCIII/buisciii-tools/releases/tag/2.2.3
+
+### Credits
+
+Code contributions to the new version:
+
+- [Victor Lopez](https://github.com/victor5lm)
+- [Sarai Varona](https://github.com/svarona)
+
 ### Template fixes and updates
 
+- Updated sftp_user.json, added the locus-tag option for the PROKKA process in the bacass config file and changed new_service.py so that integrity is checked only for the samples of interest [#363](https://github.com/BU-ISCIII/buisciii-tools/pull/363).
+- Replaced /data/bi/ by /data/ucct/bi/ [#380](https://github.com/BU-ISCIII/buisciii-tools/pull/380).
+- Updated bacass version in all pertinent files [#380](https://github.com/BU-ISCIII/buisciii-tools/pull/380).
+- Updated read length variable definition when creating the mapping_illumina.tab file [#380](https://github.com/BU-ISCIII/buisciii-tools/pull/380).
+- Updated create_irma_stats.sh to include %mapped_reads [#380](https://github.com/BU-ISCIII/buisciii-tools/pull/380).
+- Changed "Buenas" by "Estimado/a" in email.j2 [#380](https://github.com/BU-ISCIII/buisciii-tools/pull/380).
+
 ### Modules
 
 #### Added enhancements
 
 #### Fixes
 
+- Fixed new-service to correctly handle when there are no samples in service [#372](https://github.com/BU-ISCIII/buisciii-tools/pull/372). Fixes issue [#371](https://github.com/BU-ISCIII/buisciii-tools/issues/371)
+
 #### Changed
 
 #### Removed

diff --git a/README.md b/README.md
@@ -202,13 +202,13 @@ Options:
   -a, --ask_path                  Please ask for service path.
   -t, --tmp_dir PATH              Directory to which the files will be
                                   transfered for execution. Default:
-                                  /data/bi/scratch_tmp/bi/
+                                  /data/ucct/bi/scratch_tmp/bi/
   -d, --direction [service_to_scratch|scratch_to_service|remove_scratch]
                                   Direction of the rsync command.
-                                  service_to_scratch from /data/bi/service to
-                                  /data/bi/scratch_tmp/bi/.scratch_to_service:
-                                  From /data/bi/scratch_tmp/bi/ to
-                                  /data/bi/service
+                                  service_to_scratch from /data/ucct/bi/service to
+                                  /data/ucct/bi/scratch_tmp/bi/.scratch_to_service:
+                                  From /data/ucct/bi/scratch_tmp/bi/ to
+                                  /data/ucct/bi/service
   --help                          Show this message and exit.
 ```
 

diff --git a/bu_isciii/__main__.py b/bu_isciii/__main__.py
@@ -57,7 +57,7 @@ def run_bu_isciii():
     )
 
     # stderr.print("[green]                                          `._,._,'\n", highlight=False)
-    __version__ = "2.2.2"
+    __version__ = "2.2.3"
     stderr.print(
         "[grey39]    BU-ISCIII-tools version {}".format(__version__), highlight=False
     )
@@ -252,8 +252,8 @@ def new_service(ctx, resolution, path, no_create_folder, ask_path):
     "-t",
     "--tmp_dir",
     type=click.Path(),
-    default="/data/bi/scratch_tmp/bi/",
-    help="Directory to which the files will be transfered for execution. Default: /data/bi/scratch_tmp/bi/",
+    default="/data/ucct/bi/scratch_tmp/bi/",
+    help="Directory to which the files will be transfered for execution. Default: /data/ucct/bi/scratch_tmp/bi/",
 )
 @click.option(
     "-d",
@@ -262,8 +262,8 @@ def new_service(ctx, resolution, path, no_create_folder, ask_path):
     multiple=False,
     help=(
         "Direction of the rsync command. service_to_scratch "
-        "from /data/bi/service to /data/bi/scratch_tmp/bi/."
-        "scratch_to_service: From /data/bi/scratch_tmp/bi/ to /data/bi/service"
+        "from /data/ucct/bi/service to /data/ucct/bi/scratch_tmp/bi/."
+        "scratch_to_service: From /data/ucct/bi/scratch_tmp/bi/ to /data/ucct/bi/service"
     ),
 )
 @click.pass_context
@@ -411,7 +411,7 @@ def copy_sftp(ctx, resolution, path, ask_path, sftp_folder):
     "-t",
     "--tmp_dir",
     type=click.Path(),
-    default="/data/bi/scratch_tmp/bi/",
+    default="/data/ucct/bi/scratch_tmp/bi/",
     help="Absolute path to the scratch directory containing the service.",
 )
 @click.pass_context

diff --git a/bu_isciii/bioinfo_doc.py b/bu_isciii/bioinfo_doc.py
@@ -222,7 +222,7 @@ def __init__(
     def load_versions(self):
         """Load and parse the versions.yml file."""
         result = subprocess.run(
-            f"find /data/bi/services_and_colaborations/*/*/{self.service_name} -name '*versions.yml'",
+            f"find /data/ucct/bi/services_and_colaborations/*/*/{self.service_name} -name '*versions.yml'",
             stdout=subprocess.PIPE,
             text=True,
             shell=True,

diff --git a/bu_isciii/conf/configuration.json b/bu_isciii/conf/configuration.json
@@ -1,6 +1,6 @@
 {
     "global": {
-        "data_path": "/data/bi",
+        "data_path": "/data/ucct/bi",
         "archived_path": "/archived/bi",
         "yaml_conf_path": "~/buisciii_config.yml",
         "permissions": {

diff --git a/bu_isciii/conf/configuration_dev.json b/bu_isciii/conf/configuration_dev.json
@@ -1,6 +1,6 @@
 {
     "global": {
-        "data_path": "tests/data/bi",
+        "data_path": "tests/data/ucct/bi",
         "archived_path": "tests/archived/bi",
         "yaml_conf_path": "~/buisciii_config.yml"
     },

diff --git a/bu_isciii/new_service.py b/bu_isciii/new_service.py
@@ -63,7 +63,7 @@ def __init__(
         self.services_requested = self.resolution_info["resolutions"][0][
             "available_services"
         ]
-        self.service_samples = self.resolution_info.get("samples", None)
+        self.service_samples = self.resolution_info.get("samples")
 
         if ask_path and path is None:
             stderr.print("Directory where you want to create the service folder.")
@@ -103,12 +103,19 @@ def check_md5(self):
         md5_dir = os.path.dirname(md5_file_path)
         os.chdir(md5_dir)
 
+        # Regex pattern to match sample names in .fastq.gz files
+        sample_names_pattern = "|".join(
+            [
+                f"{sample['sample_name']}.*\\.fastq\\.gz"
+                for sample in self.service_samples
+            ]
+        )
+
         # md5sum command
         stderr.print(f"[blue]Checking MD5 integrity for {md5_file_path}")
         try:
-            subprocess.run(
-                ["md5sum", "-c", os.path.basename(md5_file_path)], check=True
-            )
+            cmd = f"grep -E '{sample_names_pattern}' {md5_file_path} | md5sum -c"
+            subprocess.run(cmd, shell=True, check=True, executable="/bin/bash")
             stderr.print("[green]MD5 check passed!")
         except subprocess.CalledProcessError as e:
             stderr.print(f"[red]ERROR: MD5 check failed: {e.stderr}")
@@ -117,7 +124,6 @@ def check_md5(self):
             os.chdir(original_dir)
 
     def create_folder(self):
-        self.check_md5()
         if not self.no_create_folder:
             stderr.print(
                 "[blue]I will create the service folder for " + self.resolution_id + "!"
@@ -251,7 +257,8 @@ def samples_json(self):
         f.close()
 
     def create_new_service(self):
-        if self.service_samples is not None:
+        if len(self.service_samples) > 0:
+            self.check_md5()
             self.create_folder()
             self.copy_template()
             self.create_samples_id()
@@ -270,7 +277,9 @@ def create_new_service(self):
             stderr.print(
                 "[yellow]WARN: No samples recorded in service: " + self.resolution_id
             )
-            if bu_isciii.utils.prompt_yn_question("Do you want to proceed?: "):
+            if bu_isciii.utils.prompt_yn_question(
+                "Do you want to proceed?: ", dflt=True
+            ):
                 self.create_folder()
                 self.copy_template()
                 if self.resolution_info["service_state"] != "in_progress":

diff --git a/bu_isciii/schemas/deliver_automatization.json b/bu_isciii/schemas/deliver_automatization.json
@@ -4,7 +4,7 @@
   "type": "object",
   "properties": {
     "destination": {
-      "example": "/data/bi/sftp/Labvirusres",
+      "example": "/data/ucct/bi/sftp/Labvirusres",
       "description": "Folder at which the command will be executed",
       "type": "string"
     },
@@ -24,7 +24,7 @@
       "type": "string"
     },
     "source": {
-      "example": "/data/bi/services_and_colaborations/CNM/virologia/",
+      "example": "/data/ucct/bi/services_and_colaborations/CNM/virologia/",
       "description": "Folder from which the files are comming from",
       "type": "string"
     },

diff --git a/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/01-preproQC/lablog b/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/01-preproQC/lablog
@@ -4,4 +4,4 @@ mkdir logs
 
 scratch_dir=$(echo $PWD | sed "s/\/data\/bi\/scratch_tmp/\/scratch/g")
 
-cat ../samples_id.txt | while read in; do echo "mkdir $in; srun --partition short_idx --cpus-per-task 8 --time 01:00:00 --chdir $scratch_dir --output logs/FASTQC.${in}.%j.log singularity exec -B ${scratch_dir}/../../../ -B /srv/fastq_repo/ /data/bi/pipelines/singularity-images/fastqc:0.11.9--hdfd78af_1 fastqc -o ${scratch_dir}/$in --nogroup -t 8 -k 8 ${scratch_dir}/../00-reads/"$in"_R1.fastq.gz ${scratch_dir}/../00-reads/"$in"_R2.fastq.gz &"; done > _01_rawfastqc.sh
+cat ../samples_id.txt | while read in; do echo "mkdir $in; srun --partition short_idx --cpus-per-task 8 --time 01:00:00 --chdir $scratch_dir --output logs/FASTQC.${in}.%j.log singularity exec -B ${scratch_dir}/../../../ -B /srv/fastq_repo/ /data/ucct/bi/pipelines/singularity-images/fastqc:0.11.9--hdfd78af_1 fastqc -o ${scratch_dir}/$in --nogroup -t 8 -k 8 ${scratch_dir}/../00-reads/"$in"_R1.fastq.gz ${scratch_dir}/../00-reads/"$in"_R2.fastq.gz &"; done > _01_rawfastqc.sh
diff --git a/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/02-preprocessing/lablog b/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/02-preprocessing/lablog
@@ -1,4 +1,4 @@
 # module load singularity
 mkdir logs
-scratch_dir=$(echo $(pwd) | sed 's@/data/bi/scratch_tmp/@/scratch/@g')
-cat ../samples_id.txt | xargs -I @@ echo "mkdir @@; srun --chdir ${scratch_dir} --mem 10G --time 1:00:00 --job-name FP.@@ --output logs/FP.@@.%j.log --partition short_idx --cpus-per-task 5 singularity exec -B ${scratch_dir}/../../../ -B /srv/fastq_repo/ /data/bi/pipelines/singularity-images/fastp:0.20.0--hdbcaa40_0 fastp --in1 ${scratch_dir}/../00-reads/@@_R1.fastq.gz --in2 ${scratch_dir}/../00-reads/@@_R2.fastq.gz --thread 5 --cut_front --cut_tail --cut_mean_quality 15 --qualified_quality_phred 15 --trim_poly_x --length_required 50 --detect_adapter_for_pe --json ${scratch_dir}/@@/@@_fastp.json --html ${scratch_dir}/@@/@@_fastp.html --out1 ${scratch_dir}/@@/@@_R1_filtered.fastq.gz --out2 ${scratch_dir}/@@/@@_R2_filtered.fastq.gz --unpaired1 ${scratch_dir}/@@/@@_R1_unpaired.fastq.gz --unpaired2 ${scratch_dir}/@@/@@_R2_unpaired.fastq.gz &" > _01_fastp.sh
+scratch_dir=$(echo $(pwd) | sed 's@/data/ucct/bi/scratch_tmp/@/scratch/@g')
+cat ../samples_id.txt | xargs -I @@ echo "mkdir @@; srun --chdir ${scratch_dir} --mem 10G --time 1:00:00 --job-name FP.@@ --output logs/FP.@@.%j.log --partition short_idx --cpus-per-task 5 singularity exec -B ${scratch_dir}/../../../ -B /srv/fastq_repo/ /data/ucct/bi/pipelines/singularity-images/fastp:0.20.0--hdbcaa40_0 fastp --in1 ${scratch_dir}/../00-reads/@@_R1.fastq.gz --in2 ${scratch_dir}/../00-reads/@@_R2.fastq.gz --thread 5 --cut_front --cut_tail --cut_mean_quality 15 --qualified_quality_phred 15 --trim_poly_x --length_required 50 --detect_adapter_for_pe --json ${scratch_dir}/@@/@@_fastp.json --html ${scratch_dir}/@@/@@_fastp.html --out1 ${scratch_dir}/@@/@@_R1_filtered.fastq.gz --out2 ${scratch_dir}/@@/@@_R2_filtered.fastq.gz --unpaired1 ${scratch_dir}/@@/@@_R1_unpaired.fastq.gz --unpaired2 ${scratch_dir}/@@/@@_R2_unpaired.fastq.gz &" > _01_fastp.sh
diff --git a/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/03-procQC/lablog b/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/03-procQC/lablog
@@ -4,4 +4,4 @@ mkdir logs
 
 scratch_dir=$(echo $PWD | sed "s/\/data\/bi\/scratch_tmp/\/scratch/g")
 
-cat ../samples_id.txt | while read in; do echo "mkdir $in; srun --partition short_idx --chdir $scratch_dir --output logs/FASTQC.${in}.%j.log singularity exec -B ${scratch_dir}/../../../ /data/bi/pipelines/singularity-images/fastqc:0.11.9--hdfd78af_1 fastqc -o ${scratch_dir}/$in --nogroup -t 8 -k 8 ${scratch_dir}/../02-preprocessing/${in}/${in}_R1_filtered.fastq.gz ${scratch_dir}/../02-preprocessing/${in}/${in}_R2_filtered.fastq.gz &"; done > _01_rawfastqc.sh
+cat ../samples_id.txt | while read in; do echo "mkdir $in; srun --partition short_idx --chdir $scratch_dir --output logs/FASTQC.${in}.%j.log singularity exec -B ${scratch_dir}/../../../ /data/ucct/bi/pipelines/singularity-images/fastqc:0.11.9--hdfd78af_1 fastqc -o ${scratch_dir}/$in --nogroup -t 8 -k 8 ${scratch_dir}/../02-preprocessing/${in}/${in}_R1_filtered.fastq.gz ${scratch_dir}/../02-preprocessing/${in}/${in}_R2_filtered.fastq.gz &"; done > _01_rawfastqc.sh
diff --git a/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/create_irma_stats.sh b/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/create_irma_stats.sh
@@ -6,6 +6,7 @@ do
 SAMPLE_ID=$(echo ${in})
 TOTAL_READS=$(grep '1-initial' ${in}/tables/READ_COUNTS.txt | cut -f2)
 MAPPEDREADS=$(grep '3-match' ${in}/tables/READ_COUNTS.txt | cut -f2)
+PCTMAPPED=$(awk "BEGIN {printf \"%.2f\", ($MAPPEDREADS/$TOTAL_READS)*100}")
 FLU_TYPE=$(paste <(grep '4-[A-C]_MP' ${in}/tables/READ_COUNTS.txt | cut -f1 | cut -d '_' -f1 | cut -d '-' -f2) <(grep '4-[A-B]_HA' ${in}/tables/READ_COUNTS.txt | cut -f1 | cut -d '_' -f3 | cut -d '-' -f2) <(grep '4-[A-B]_NA' ${in}/tables/READ_COUNTS.txt | cut -f1 | cut -d '_' -f3) | tr '\t' '_')
 HA=$(grep '4-[A-C]_HA' ${in}/tables/READ_COUNTS.txt | cut -f2)
 MP=$(grep '4-[A-C]_MP' ${in}/tables/READ_COUNTS.txt | cut -f2)

diff --git a/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/lablog b/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/lablog
@@ -5,7 +5,7 @@ mkdir logs
 
 scratch_dir=$(echo $PWD | sed "s/\/data\/bi\/scratch_tmp/\/scratch/g")
 
-cat ../samples_id.txt | while read in; do echo "srun --partition short_idx --cpus-per-task 32 --mem 35000M --chdir $scratch_dir --time 01:00:00 --output logs/IRMA.${in}.%j.log /data/bi/pipelines/flu-amd/flu-amd-1.1.4/IRMA FLU_AD ../02-preprocessing/${in}/${in}_R1_filtered.fastq.gz ../02-preprocessing/${in}/${in}_R2_filtered.fastq.gz ${in} --external-config ../../../DOC/irma_config.sh &"; done > _01_irma.sh
+cat ../samples_id.txt | while read in; do echo "srun --partition short_idx --cpus-per-task 32 --mem 35000M --chdir $scratch_dir --time 01:00:00 --output logs/IRMA.${in}.%j.log /data/ucct/bi/pipelines/flu-amd/flu-amd-1.1.4/IRMA FLU_AD ../02-preprocessing/${in}/${in}_R1_filtered.fastq.gz ../02-preprocessing/${in}/${in}_R2_filtered.fastq.gz ${in} --external-config ../../../DOC/irma_config.sh &"; done > _01_irma.sh
 
 echo 'bash create_irma_stats.sh' > _02_create_stats.sh
 

diff --git a/bu_isciii/templates/assembly/ANALYSIS/ANALYSIS01_ASSEMBLY/lablog b/bu_isciii/templates/assembly/ANALYSIS/ANALYSIS01_ASSEMBLY/lablog
@@ -107,7 +107,7 @@ cat <<EOF > assembly.sbatch
 # module load Nextflow/23.10.0 singularity
 export NXF_OPTS="-Xms500M -Xmx8G"
 
-nextflow run /data/bi/pipelines/nf-core-bacass/nf-core-bacass-2.3.1/main.nf \\
+nextflow run /data/ucct/bi/pipelines/nf-core-bacass/nf-core-bacass-2.4.0/2_4_0/main.nf \\
         -c ../../DOC/hpc_slurm_assembly.config \\
         -profile singularity \\
         --input samplesheet.csv \\
@@ -119,8 +119,8 @@ nextflow run /data/bi/pipelines/nf-core-bacass/nf-core-bacass-2.3.1/main.nf \\
         --fastp_args '--qualified_quality_phred 20 --cut_mean_quality 20' \\
         --skip_kraken2 true \\
         --skip_kmerfinder false \\
-        --kmerfinderdb /data/bi/references/kmerfinder/latest/bacteria \\
-        --ncbi_assembly_metadata /data/bi/references/bacteria/20240626/assembly_summary_refseq.txt \\
+        --kmerfinderdb /data/ucct/bi/references/kmerfinder/latest/bacteria \\
+        --ncbi_assembly_metadata /data/ucct/bi/references/bacteria/20240626/assembly_summary_refseq.txt \\
         ${PROKKA_ARGS} \\
         -resume
 

diff --git a/bu_isciii/templates/assembly/DOC/hpc_slurm_assembly.config b/bu_isciii/templates/assembly/DOC/hpc_slurm_assembly.config
@@ -5,7 +5,7 @@
 singularity {
         enabled                 = true
         autoMounts              = true
-        singularity.cacheDir    = '/data/bi/pipelines/singularity-images'
+        singularity.cacheDir    = '/data/ucct/bi/pipelines/singularity-images'
 }
 
 process {
@@ -195,7 +195,8 @@ process {
         ext.args = {
             [
                 '--force',
-                params.prokka_args ? "${params.prokka_args}" : ''
+                params.prokka_args ? "${params.prokka_args}" : '',
+                "--locustag ${meta.id}"
             ].join(' ').trim()
         }
         publishDir = [

diff --git a/bu_isciii/templates/blast_nt/ANALYSIS/ANALYSIS02_BLAST/lablog b/bu_isciii/templates/blast_nt/ANALYSIS/ANALYSIS02_BLAST/lablog
@@ -6,8 +6,8 @@ mkdir logs
 # Location of assemblies to a variable so it only has to be changed here
 LOCATION=../*/*/assembly/*/*
 # Other databases: 
-# /data/bi/references/BLAST_dbs/nt_20211025/nt
-BLAST_DATABASE="/data/bi/references/virus/BLAST/all_virus.fasta"
+# /data/ucct/bi/references/BLAST_dbs/nt_20211025/nt
+BLAST_DATABASE="/data/ucct/bi/references/BLAST_dbs/viral_ncbi/viral_genomes_ncbi"
 
 # if there are scaffolds, uncompress the scaffolds in its dir (zcat for decompression)
 # if there contigs and no scaffolds, uncompress the contigs as scaffolds in its dir
@@ -27,7 +27,7 @@ cat ../samples_id.txt | while read in; do
 done 
 
 # NOTE3: change the -query flag to meet your requirements
-cat ../samples_id.txt | xargs -I %% echo "srun --chdir ${scratch_dir} --partition middle_idx --mem 200G --time 48:00:00 --cpus-per-task 10 --output logs/BLASTN_%%_%j.log --job-name BLASTN_%% singularity exec -B ${scratch_dir}/../../ -B /data/bi/references/virus/BLAST/ /data/bi/pipelines/singularity-images/blast:2.11.0--pl5262h3289130_1 blastn -num_threads 10 -db ${BLAST_DATABASE} -query ${scratch_dir}/%%/%%.scaffolds.fa -out ${scratch_dir}/%%/%%_blast.tsv -outfmt '6 qseqid stitle qaccver saccver pident length mismatch gaps qstart qend sstart send evalue bitscore slen qlen qcovs' &" > _01_blast.sh
+cat ../samples_id.txt | xargs -I %% echo "srun --chdir ${scratch_dir} --partition middle_idx --mem 200G --time 48:00:00 --cpus-per-task 10 --output logs/BLASTN_%%_%j.log --job-name BLASTN_%% singularity exec -B ${scratch_dir}/../../ -B /data/ucct/bi/references/BLAST_dbs/viral_ncbi/ /data/ucct/bi/pipelines/singularity-images/blast:2.11.0--pl5262h3289130_1 blastn -num_threads 10 -db ${BLAST_DATABASE} -query ${scratch_dir}/%%/%%.scaffolds.fa -out ${scratch_dir}/%%/%%_blast.tsv -outfmt '6 qseqid stitle qaccver saccver pident length mismatch gaps qstart qend sstart send evalue bitscore slen qlen qcovs' &" > _01_blast.sh
 
 # Filtering criteria:
     # %refCovered > 0.7
@@ -71,5 +71,5 @@ echo "rm header" >> _03_gather_results_add_header.sh
 # 20: %refCovered: length/slen
 
 # conda activate 2excel
-cat ../samples_id.txt | xargs -I %% echo "srun --chdir ${scratch_dir} --partition short_idx --mem 10G --time 1:00:00 --output logs/2excel_%%.log --job-name 2excel_%% python /data/bi/pipelines/utilities/export_excel_from_csv.py --input_file %%/%%_blast_filt.tsv --delimiter '\t' --output_filename %%/%%_blast_filt --it_has_index --it_has_header" > _04_to_excel.sh
-echo "srun --chdir ${scratch_dir} --partition short_idx --mem 10G --time 1:00:00 --output logs/2excel_all.log --job-name 2excel_all python /data/bi/pipelines/utilities/export_excel_from_csv.py --input_file all_samples_filtered_BLAST_results.tsv --delimiter '\t' --output_filename all_samples_filtered_BLAST_results --it_has_index --it_has_header" >> _04_to_excel.sh
+cat ../samples_id.txt | xargs -I %% echo "srun --chdir ${scratch_dir} --partition short_idx --mem 10G --time 1:00:00 --output logs/2excel_%%.log --job-name 2excel_%% python /data/ucct/bi/pipelines/utilities/export_excel_from_csv.py --input_file %%/%%_blast_filt.tsv --delimiter '\t' --output_filename %%/%%_blast_filt --it_has_index --it_has_header" > _04_to_excel.sh
+echo "srun --chdir ${scratch_dir} --partition short_idx --mem 10G --time 1:00:00 --output logs/2excel_all.log --job-name 2excel_all python /data/ucct/bi/pipelines/utilities/export_excel_from_csv.py --input_file all_samples_filtered_BLAST_results.tsv --delimiter '\t' --output_filename all_samples_filtered_BLAST_results --it_has_index --it_has_header" >> _04_to_excel.sh
Original file line number	Diff line number	Diff line change
Expand Up		@@ -4,4 +4,4 @@ mkdir logs

		scratch_dir=$(echo $PWD \| sed "s/\/data\/bi\/scratch_tmp/\/scratch/g")

		cat ../samples_id.txt \| while read in; do echo "mkdir $in; srun --partition short_idx --cpus-per-task 8 --time 01:00:00 --chdir $scratch_dir --output logs/FASTQC.${in}.%j.log singularity exec -B ${scratch_dir}/../../../ -B /srv/fastq_repo/ /data/bi/pipelines/singularity-images/fastqc:0.11.9--hdfd78af_1 fastqc -o ${scratch_dir}/$in --nogroup -t 8 -k 8 ${scratch_dir}/../00-reads/"$in"_R1.fastq.gz ${scratch_dir}/../00-reads/"$in"_R2.fastq.gz &"; done > _01_rawfastqc.sh
		cat ../samples_id.txt \| while read in; do echo "mkdir $in; srun --partition short_idx --cpus-per-task 8 --time 01:00:00 --chdir $scratch_dir --output logs/FASTQC.${in}.%j.log singularity exec -B ${scratch_dir}/../../../ -B /srv/fastq_repo/ /data/ucct/bi/pipelines/singularity-images/fastqc:0.11.9--hdfd78af_1 fastqc -o ${scratch_dir}/$in --nogroup -t 8 -k 8 ${scratch_dir}/../00-reads/"$in"_R1.fastq.gz ${scratch_dir}/../00-reads/"$in"_R2.fastq.gz &"; done > _01_rawfastqc.sh