Merge pull request #41 from ctg-lund/fix-flex-mqc-yaml

Fix flex mqc yaml

bin/countmetric2mqc.py

@@ -0,0 +1,18 @@
+import sys
+
+# Check if input file name was provided
+if len(sys.argv) < 3:
+    print('Usage: python countmetric2mqc.py file.csv sample_name output_mqc.yaml')
+    sys.exit(1)
+
+# Get input file name from command-line argument
+input_file = sys.argv[1]
+sample_name = sys.argv[2]
+mqc_yaml = sys.argv[3]
+# Initialize dictionaries for each category
+with open(input_file, 'r') as file:
+    keys, values = file.readline().split(','), file.readline().split(',')
+    data = {k.strip():v.strip() for (k,v) in zip(keys,values)}
+# Appends to an already existing mqc.yaml file
+with open(mqc_yaml, 'a') as file:
+    file.write(f'  {sample_name}: {data}\n')

examples/CTG_SampleSheet.csv

@@ -1,13 +1,5 @@
 [Header],,,,,,,,
 IEMFileVersion,4,,,,,,,
-[Data],,,,,,,,
-Sample_ID,index,index2,Sample_Project,,,,,
-sample-1,SI-TT-A1,SI-TT-A1,project1,,,,,
-sample-2,SI-TT-A2,SI-TT-A2,project1,,,,,
-sample-3,SI-TT-A3,SI-TT-A3,project2,,,,,
-sample-4,SI-TT-A4,SI-TT-A4,project3,,,,,
-sample-5,SI-TT-A5,SI-TT-A5,project3,,,,,
-sample-6,SI-TT-A6,SI-TT-A6,project3,,,,,
 [10X_Data],,,,,,,,
 Sample_ID,Sample_Species,Sample_Project,force,agg,sample_pair,libtype,pipeline,cytaimage,darkimage,image,slide,slide_area
 sample-1,human,project1,n,n,n,gex,scrna-10x,n,n,n,n,n
@@ -31,6 +23,8 @@ sample-18,human,project10,n,n,n,gex,scvisium-10x,cytaimage,darkimage,image,slide
 sample-19,human,project7,n,n,5,gex,scmulti-10x,n,n,n,n,n
 sample-20,human,project7,n,n,5,tcr,scmulti-10x,n,n,n,n,n
 sample-21,human,project7,n,n,5,bcr,scmulti-10x,n,n,n,n,n
+sample-22,human,project9,n,n,6,atac,scarc-10x,n,n,n,n,n
+sample-23,human,project9,n,n,6,gex,scarc-10x,n,n,n,n,n
 [FlexConfig_Data],,,,,,,,
 sample_id,probe_barcode,Sample_Source,,,,,,
 sample1,BC001|BC002,sample_7,,,,,,

modules/cellranger/multi/main.nf

@@ -21,10 +21,14 @@ process MULTI {
 	"""
 	stub:
 	"""
-	sample_dir=$sample_id/outs/per_sample_outs/$sample_id
-	mkdir -p \$sample_dir
-	touch \$sample_dir/web_summary.html
-	touch \$sample_dir/cloupe.cloupe
+	sample_dir_1=$sample_id/outs/per_sample_outs/${sample_id}_1
+	sample_dir_2=$sample_id/outs/per_sample_outs/${sample_id}_2
+	mkdir -p \$sample_dir_1
+	mkdir -p \$sample_dir_2
+	touch \$sample_dir_1/web_summary.html
+	touch \$sample_dir_2/web_summary.html
+	touch \$sample_dir_1/cloupe.cloupe
+	touch \$sample_dir_2/cloupe.cloupe
 	echo \'\'\'Category,Library Type,Grouped By,Group Name,Metric Name,Metric Value
 Cells,Gene Expression,,,Cells,"5,727"
 Cells,Gene Expression,,,Confidently mapped reads in cells,84.20%
@@ -37,70 +41,37 @@ Cells,VDJ B,,,Cells with productive IGK contig,70.10%
 Cells,VDJ B,,,Cells with productive IGL contig,6.19%
 Cells,VDJ B,,,"Cells with productive V-J spanning (IGK, IGH) pair",49.31%
 Cells,VDJ B,,,"Cells with productive V-J spanning (IGL, IGH) pair",5.50%
-Cells,VDJ B,,,Cells with productive V-J spanning pair,54.47%
-Cells,VDJ B,,,Estimated number of cells,582
-Cells,VDJ B,,,Median IGH UMIs per Cell,9
-Cells,VDJ B,,,Median IGK UMIs per Cell,10
-Cells,VDJ B,,,Median IGL UMIs per Cell,0
-Cells,VDJ B,,,Number of cells with productive V-J spanning pair,317
 Cells,VDJ B,,,Paired clonotype diversity,72.28
 Cells,VDJ T,,,Cells with productive TRA contig,79.03%
 Cells,VDJ T,,,Cells with productive TRB contig,97.58%
 Cells,VDJ T,,,"Cells with productive V-J spanning (TRA, TRB) pair",76.61%
 Cells,VDJ T,,,Cells with productive V-J spanning pair,76.61%
-Cells,VDJ T,,,Estimated number of cells,124
-Cells,VDJ T,,,Median TRA UMIs per Cell,3
-Cells,VDJ T,,,Median TRB UMIs per Cell,7
-Cells,VDJ T,,,Number of cells with productive V-J spanning pair,95
-Cells,VDJ T,,,Paired clonotype diversity,35.11
 Library,Gene Expression,Fastq ID,1a_522_3wbm,Number of reads,"172,468,563"
 Library,Gene Expression,Fastq ID,1a_522_3wbm,Number of short reads skipped,0
 Library,Gene Expression,Fastq ID,1a_522_3wbm,Q30 RNA read,91.1%
-Library,Gene Expression,Fastq ID,1a_522_3wbm,Q30 UMI,94.8%
-Library,Gene Expression,Fastq ID,1a_522_3wbm,Q30 barcodes,95.8%
-Library,Gene Expression,Physical library ID,GEX_1,Confidently mapped antisense,2.56%
-Library,Gene Expression,Physical library ID,GEX_1,Confidently mapped reads in cells,84.20%
-Library,Gene Expression,Physical library ID,GEX_1,Confidently mapped to exonic regions,21.93%
-Library,Gene Expression,Physical library ID,GEX_1,Confidently mapped to genome,26.08%
-Library,Gene Expression,Physical library ID,GEX_1,Confidently mapped to intergenic regions,2.50%
-Library,Gene Expression,Physical library ID,GEX_1,Confidently mapped to intronic regions,1.65%
-Library,Gene Expression,Physical library ID,GEX_1,Confidently mapped to transcriptome,20.79%
-Library,Gene Expression,Physical library ID,GEX_1,Estimated number of cells,"5,727"
-Library,Gene Expression,Physical library ID,GEX_1,Mapped to genome,36.49%
-Library,Gene Expression,Physical library ID,GEX_1,Mean reads per cell,"30,115"
-Library,Gene Expression,Physical library ID,GEX_1,Number of reads,"172,468,563"
-Library,Gene Expression,Physical library ID,GEX_1,Number of reads in the library,"172,468,563"
-Library,Gene Expression,Physical library ID,GEX_1,Sequencing saturation,50.84%
-Library,Gene Expression,Physical library ID,GEX_1,Valid UMIs,99.85%
-Library,Gene Expression,Physical library ID,GEX_1,Valid barcodes,92.38%
-Library,VDJ B,Fastq ID,1a_522_3wbm_BCR,Number of reads,"30,607,267"
-Library,VDJ B,Fastq ID,1a_522_3wbm_BCR,Number of short reads skipped,0
-Library,VDJ B,Fastq ID,1a_522_3wbm_BCR,Q30 RNA read,92.7%
-Library,VDJ B,Fastq ID,1a_522_3wbm_BCR,Q30 UMI,94.5%
-Library,VDJ B,Fastq ID,1a_522_3wbm_BCR,Q30 barcodes,95.6%
-Library,VDJ B,Physical library ID,VDJB_1,Estimated number of cells,582
-Library,VDJ B,Physical library ID,VDJB_1,Fraction reads in cells,83.31%
-Library,VDJ B,Physical library ID,VDJB_1,Mean reads per cell,"52,590"
-Library,VDJ B,Physical library ID,VDJB_1,Mean used reads per cell,"9,638"
-Library,VDJ B,Physical library ID,VDJB_1,Number of reads,"30,607,267"
-Library,VDJ B,Physical library ID,VDJB_1,Reads mapped to IGH,22.57%
-Library,VDJ B,Physical library ID,VDJB_1,Reads mapped to IGK,50.50%
-Library,VDJ B,Physical library ID,VDJB_1,Reads mapped to IGL,14.06%
-Library,VDJ B,Physical library ID,VDJB_1,Reads mapped to any V(D)J gene,87.14%
-Library,VDJ B,Physical library ID,VDJB_1,Valid barcodes,95.44%
-Library,VDJ T,Fastq ID,1a_522_3wbm_TCR,Number of reads,"39,674,884"
-Library,VDJ T,Fastq ID,1a_522_3wbm_TCR,Number of short reads skipped,0
-Library,VDJ T,Fastq ID,1a_522_3wbm_TCR,Q30 RNA read,91.5%
-Library,VDJ T,Fastq ID,1a_522_3wbm_TCR,Q30 UMI,94.7%
-Library,VDJ T,Fastq ID,1a_522_3wbm_TCR,Q30 barcodes,95.4%
-Library,VDJ T,Physical library ID,VDJT_1,Estimated number of cells,124
-Library,VDJ T,Physical library ID,VDJT_1,Fraction reads in cells,15.60%
-Library,VDJ T,Physical library ID,VDJT_1,Mean reads per cell,"319,959"
-Library,VDJ T,Physical library ID,VDJT_1,Mean used reads per cell,"35,979"
-Library,VDJ T,Physical library ID,VDJT_1,Number of reads,"39,674,884"
-Library,VDJ T,Physical library ID,VDJT_1,Reads mapped to TRA,7.91%
-Library,VDJ T,Physical library ID,VDJT_1,Reads mapped to TRB,24.14%
-Library,VDJ T,Physical library ID,VDJT_1,Reads mapped to any V(D)J gene,32.31%
-Library,VDJ T,Physical library ID,VDJT_1,Valid barcodes,79.69%\'\'\' > \$sample_dir/metrics_summary.csv
+Library,Gene Expression,Fastq ID,1a_522_3wbm,Q30 UMI,94.8%\'\'\' > \$sample_dir_1/metrics_summary.csv
+
+echo \'\'\'Category,Library Type,Grouped By,Group Name,Metric Name,Metric Value
+Cells,Gene Expression,,,Cells,"5,727"
+Cells,Gene Expression,,,Confidently mapped reads in cells,84.20%
+Cells,Gene Expression,,,Median UMI counts per cell,"1,585"
+Cells,Gene Expression,,,Median genes per cell,744
+Cells,Gene Expression,,,Median reads per cell,"16,412"
+Cells,Gene Expression,,,Total genes detected,"14,371"
+Cells,VDJ B,,,Cells with productive IGH contig,78.52%
+Cells,VDJ B,,,Cells with productive IGK contig,70.10%
+Cells,VDJ B,,,Cells with productive IGL contig,6.19%
+Cells,VDJ B,,,"Cells with productive V-J spanning (IGK, IGH) pair",49.31%
+Cells,VDJ B,,,"Cells with productive V-J spanning (IGL, IGH) pair",5.50%
+Cells,VDJ B,,,Paired clonotype diversity,72.28
+Cells,VDJ T,,,Cells with productive TRA contig,79.03%
+Cells,VDJ T,,,Cells with productive TRB contig,97.58%
+Cells,VDJ T,,,"Cells with productive V-J spanning (TRA, TRB) pair",76.61%
+Cells,VDJ T,,,Cells with productive V-J spanning pair,76.61%
+Library,Gene Expression,Fastq ID,1a_522_3wbm,Number of reads,"172,468,563"
+Library,Gene Expression,Fastq ID,1a_522_3wbm,Number of short reads skipped,0
+Library,Gene Expression,Fastq ID,1a_522_3wbm,Q30 RNA read,91.1%
+Library,Gene Expression,Fastq ID,1a_522_3wbm,Q30 UMI,94.8%\'\'\' > \$sample_dir_2/metrics_summary.csv
+
 	"""
 }

modules/cellranger2multiqc/count/main.nf

@@ -22,10 +22,11 @@ process CELLRANGER_COUNT_TO_MULTIQC{
     IFS=', ' read -ra project_array <<< \"\$project_string\"
     # Checks if mqc_yaml exists, if not create it
     for i in {0..$number_of_samples}; do
+    echo \$i
     if ! [ -f \"$params.outdir/\${project_array[\$i]}/1_qc/multiqc/multiqc_mqc.yaml\" ]; then
       mkdir -p \"$params.outdir/\${project_array[\$i]}/1_qc/multiqc/\"
       echo \"\"\"id: \"single_cell_workflows_table\"
-section_name : \"Single Cell Workflows Stats\"
+section_name : \"Single Cell Workflows Count Stats\"
 description: \"This table consists of the data gathered from cellranger output \"
 plot_type: \"table\"
 pconfig:
@@ -34,7 +35,7 @@ pconfig:
 data:\"\"\" > \"$params.outdir/\${project_array[\$i]}/1_qc/multiqc/multiqc_mqc.yaml\"
     fi
     # Extends mqc_yaml file with sample information
-    echo \"  \${sample_array[\$i]}: \$(cat $params.outdir/\${project_array[\$i]}/2_count/\${sample_array[\$i]}/outs/$summary | python -c 'import csv, json, sys; print(json.dumps([dict(r) for r in csv.DictReader(sys.stdin)]))')\" | tr -d '[]' >> \"$params.outdir/\${project_array[\$i]}/1_qc/multiqc/multiqc_mqc.yaml\"
+    python $projectDir/bin/countmetric2mqc.py $params.outdir/\${project_array[\$i]}/2_count/\${sample_array[\$i]}/outs/$summary \${sample_array[\$i]} $params.outdir/\${project_array[\$i]}/1_qc/multiqc/multiqc_mqc.yaml
 done
     """
 }

modules/split_sheet/main.nf

@@ -5,7 +5,7 @@ process SPLITSHEET {
     output:
         path "10X_Data.csv", emit: data
         path "Data.csv", emit: pipe_data, optional: true
-        path "10X_Flex_Data.csv", emit: flex, optional: true
+        path "FlexConfig_Data.csv", emit: flex, optional: true
         path "FeatureReference_Data.csv", emit: feature_reference, optional: true
     shell:
     '''

subworkflows/finish.nf

@@ -24,5 +24,4 @@ workflow FINISH_PROJECTS {
             md5sum_ch = MD5SUM(publish_ch)
             deliver_auto_ch = DELIVER_PROJ(md5sum_ch.project_id)
         }
-        print params.ctg_mode
 }

templates/manifest.html

@@ -83,14 +83,14 @@
     <div class="main-block">
       <div class="block-item">
         <h1><b>Nextflow manifest</b></h1>
-        <p> <b>Pipeline release:</b> 1.4.1</p>
+        <p> <b>Pipeline release:</b> 1.4.2</p>
         <p> <b>Subworkflow:</b> xxSubWorkflowxx</p>
         <p> <b> Maintainer:</b> [email protected]</p>
         <p> <b>Description:</b> Your data has been processed by the nextflow pipeline singleCellWorkflows. If you want more information on how your data was processed, follow the link below and navigate to your release!</p>
         <a href="https://github.com/ctg-lund/singleCellWorkflows/tree/master">
             <button class="btn github" data-provider="github"><i class="fab fa-github"></i><span>GitHub</span></button>
         </a>
-        <a href="https://github.com/ctg-lund/singleCellWorkflows/archive/refs/tags/v1.4.0.tar.gz">
+        <a href="https://github.com/ctg-lund/singleCellWorkflows/archive/refs/tags/v1.4.2.tar.gz">
           <button class="btn twitter" data-provider="twitter"><i class="fab "></i><span>Download pipeline release</span></button>
       </a>
       </div>