multiqc enhancement

dakehero · Jun 5, 2020 · 03e306b · 03e306b
1 parent 07b3b7c
commit 03e306b
Show file tree

Hide file tree

Showing 3 changed files with 56 additions and 4 deletions.
diff --git a/assets/multiqc_config.yaml b/assets/multiqc_config.yaml
@@ -0,0 +1,13 @@
+module_order:    
+    - fastqc:
+        name: 'FastQC (raw)'
+        path_filters_exclude:
+            - '*.trimmed_fastqc.zip'
+    - fastp
+    - fastqc:
+        name: 'FastQC (trimmed)'
+        path_filters:
+            - '*.trimmed_fastqc.zip'   
+    - sortmerna   
+    - hisat2
+    - featureCounts
diff --git a/main.nf b/main.nf
@@ -176,6 +176,11 @@ deseq2_script_refactor_reportingtools_table = Channel.fromPath( workflow.project
 deseq2_script_improve_deseq_table = Channel.fromPath( workflow.projectDir + '/bin/improve_deseq_table.rb', checkIfExists: true )
 deseq2_script_csv2xlsx = Channel.fromPath( workflow.projectDir + '/bin/csv_to_excel.py', checkIfExists: true )
 
+/*
+* MultiQC config
+*/
+multiqc_config = Channel.fromPath( workflow.projectDir + '/assets/multiqc_config.yaml', checkIfExists: true )
+
 //if (params.index) {
 //  index_ch = Channel.fromPath("${params.index}.*", checkIfExists: true)
 //}
@@ -215,7 +220,7 @@ include featurecounts from './modules/featurecounts'
 include tpm_filter from './modules/tpm_filter'
 include deseq2 from './modules/deseq2'
 include { fastqc as fastqcPre; fastqc as fastqcPost } from './modules/fastqc'
-include multiqc from './modules/multiqc'
+include { multiqc; multiqc_sample_names } from './modules/multiqc'
 
 // helpers
 include {format_annotation; format_annotation_gene_rows} from './modules/prepare_annotation'
@@ -289,6 +294,7 @@ workflow analysis_reference_based {
         deseq2_script_refactor_reportingtools_table
         deseq2_script_improve_deseq_table
         deseq2_script_csv2xlsx
+        multiqc_config
 
     main:
         // initial QC of raw reads
@@ -352,7 +358,10 @@ workflow analysis_reference_based {
         deseq2(tpm_filter.out.filtered_counts, annotated_sample.condition.collect(), annotated_sample.col_label.collect(), deseq2_comparisons, format_annotation.out, format_annotation_gene_rows.out, annotated_sample.patient.collect(), deseq2_script, deseq2_script_refactor_reportingtools_table, deseq2_script_improve_deseq_table, deseq2_script_csv2xlsx)
 
         // run MultiQC
-        multiqc(fastp.out.json_report.collect(), 
+        multiqc_sample_names(annotated_reads.map{ row -> row[0..-3]}.collect())
+        multiqc(multiqc_config, 
+                multiqc_sample_names.out,
+                fastp.out.json_report.collect(), 
                 sortmerna.out.log.collect(), 
                 hisat2.out.log.collect(), 
                 featurecounts.out.log.collect(), 
@@ -392,7 +401,7 @@ workflow {
     sortmerna_db = download_sortmerna.out
 
     // start reference-based analysis
-    analysis_reference_based(illumina_input_ch, reference, annotation, sortmerna_db, dge_comparisons_input_ch, deseq2_script, deseq2_script_refactor_reportingtools_table, deseq2_script_improve_deseq_table, deseq2_script_csv2xlsx)
+    analysis_reference_based(illumina_input_ch, reference, annotation, sortmerna_db, dge_comparisons_input_ch, deseq2_script, deseq2_script_refactor_reportingtools_table, deseq2_script_improve_deseq_table, deseq2_script_csv2xlsx, multiqc_config)
 }
 
 

diff --git a/modules/multiqc.nf b/modules/multiqc.nf
@@ -9,6 +9,8 @@ process multiqc {
     else { publishDir "${params.output}/${params.multiqc_dir}" }
 
     input:
+    path(config)
+    path(sample_names)
     path(fastp)
     path(sortmerna)
     path(hisat2)
@@ -22,6 +24,34 @@ process multiqc {
 
     script:
     """
-    multiqc .    
+    multiqc . -c ${config} --sample-names ${sample_names}
     """
 }
+
+process multiqc_sample_names {
+    label 'smallTask'
+
+    input:
+    val(list)
+
+    output:
+    path('multiqc_sample_names.tsv')
+
+    script:
+    def tbl = ''
+    if (params.mode == 'single') {
+        for( int i=0; i<list.size()-1; i=i+2 ){
+            tbl += "${list[i+1].baseName.tokenize('.')[0]}\t${list[i]}\n"
+        }
+    }
+    else {
+        for( int i=0; i<list.size()-2; i=i+3 ){
+            tbl += "${list[i+1].baseName.tokenize('.')[0]}\t${list[i]}.R1\n"
+            tbl += "${list[i+2].baseName.tokenize('.')[0]}\t${list[i]}.R2\n"
+        }
+    }
+    """
+    echo "Read File Names\tSample Names" > multiqc_sample_names.tsv
+    echo "${tbl}" >> multiqc_sample_names.tsv
+    """
+}