clean up assay suffix uses, fix help menu

Author: torres-alexis

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/main.nf

@@ -1,5 +1,4 @@
 // main.nf
-
 nextflow.enable.dsl=2
 
 def colorCodes = [
@@ -10,26 +9,18 @@ def colorCodes = [
     c_yellow: "\u001b[33;1m",
     c_reset: "\033[0m"
 ]
+// Command for: 'run main.nf --version'
 
-// Include the showHelp function from help.nf
-include { showHelp } from './modules/help.nf'
-// Only display the help message if --help parameter is specified
-if (params.help) {
-    showHelp(workflow)
-}
-
-if (params.version) {
-    println("${workflow.manifest.name} ${workflow.manifest.version}")
-    exit 0
-}
-
-// Print the pipeline version
+// Print the pipeline version on start
 println """
 ${colorCodes.c_bright_green}${colorCodes.c_line}
 ${workflow.manifest.name} ${workflow.manifest.version}
 ${colorCodes.c_line}${colorCodes.c_reset}
 """.stripIndent()
-
+if (params.version) {
+    println("${workflow.manifest.name} ${workflow.manifest.version}")
+    exit 0
+}
 // Debug warning
 println("${colorCodes.c_yellow}")
 if (params.limit_samples_to || params.truncate_to || params.force_single_end || params.genome_subsample) {
@@ -43,32 +34,9 @@ if (params.limit_samples_to || params.truncate_to || params.force_single_end ||
 }
 println("${colorCodes.c_reset}")
 
-// Check required parameters
-if ((params.accession) || params.runsheet_path || params.isa_archive_path) {
-    // Proceed
-} else {
-    log.error """
-        Missing Required Parameters: You must provide either --accession, or --runsheet_path, or --accession and--isa_archive_path.
-        Examples:
-          --accession [OSD-# or GLDS-#]
-          --runsheet_path /path/to/runsheet.csv
-          --accession [OSD-# or GLDS-#] --isa_archive_path /path/to/isa_archive.zip
-    """
-    exit 0
-}
-
 include { RNASEQ } from './workflows/rnaseq.nf'
 include { RNASEQ_MICROBES } from './workflows/rnaseq_microbes.nf'
 
-// Validate accession format. Must be OSD-# or GLDS-#
-if (params.accession && !params.accession.matches(/^(OSD|GLDS)-\d+$/)) {
-    log.error "Invalid accession format. Expected format: OSD-# or GLDS-#"
-    exit 1
-}
-
-// Set up channels. This will be used to pass in parameters from initialization 
-// into the entire workflow or subworkflows run independently (e.g. rerunning a 
-// specific step for reprocessing a dataset after metadata updates)
 ch_dp_tools_plugin = params.dp_tools_plugin ? 
     Channel.value(file(params.dp_tools_plugin)) : 
     Channel.value(file(params.mode == 'microbes' ? 
@@ -88,17 +56,15 @@ ch_force_single_end = Channel.value(params.force_single_end)
 ch_reference_store_path = Channel.value(params.reference_store_path)
 ch_derived_store_path = Channel.value(params.derived_store_path)
 
-// Set outdir based on the presence of an accession input.. currently not implemented as nextflow.config's outdir is only used for nextflow run info
-//  and ch_outdir is used for all processes' publishDir in order to set either ./results or ./{accession}
-ch_outdir = params.accession ? "$projectDir/${params.accession}" : "$projectDir/results"
-
-
 // set reference params
 ch_reference_source = params.reference_source ? Channel.value(params.reference_source) : null
 ch_reference_version = params.reference_version ? Channel.value(params.reference_version) : null
 ch_reference_fasta = params.reference_fasta ? Channel.fromPath(params.reference_fasta) : null
 ch_reference_gtf = params.reference_gtf ? Channel.fromPath(params.reference_gtf) : null
 
+// Set outdir based on the presence of an accession input.. currently not implemented as nextflow.config's outdir is only used for nextflow run info
+//  and ch_outdir is used for all processes' publishDir in order to set either ./results or ./{accession}
+ch_outdir = params.accession ? "$projectDir/${params.accession}" : "$projectDir/results"
 
 // Main workflows
 workflow {
@@ -137,4 +103,4 @@ workflow {
             ch_derived_store_path
         )
     }
-}
+}

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/add_gene_annotations.nf

@@ -11,11 +11,11 @@ process ADD_GENE_ANNOTATIONS {
         path(dge_no_annotations)
 
     output:
-        path("differential_expression${params.output_suffix}.csv"),  emit: annotated_dge_table
+        path("differential_expression${params.assay_suffix}.csv"),  emit: annotated_dge_table
         path("versions.txt"), emit: versions_txt
 
     script:
-        def output_filename_suffix = params.output_suffix ?: ""
+        def output_filename_suffix = params.assay_suffix ?: ""
         def annotations_rmd_file = "${projectDir}/bin/add_gene_annotations.Rmd"
 
         """

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/dge_deseq2.nf

@@ -11,18 +11,18 @@ process DGE_DESEQ2 {
         path(gene_counts)
 
     output:
-        tuple path("Normalized_Counts${params.output_suffix}.csv"),
-              path(params.mode == "microbes" ? "FeatureCounts_Unnormalized_Counts${params.output_suffix}.csv" : 
-                   "RSEM_Unnormalized_Counts${params.output_suffix}.csv"),                emit: norm_counts
-        path("contrasts${params.output_suffix}.csv"),                                     emit: contrasts
-        path("SampleTable${params.output_suffix}.csv"),                                   emit: sample_table      
-        path("differential_expression_no_annotations${params.output_suffix}.csv"),        emit: dge_table
-        path("VST_Normalized_Counts${params.output_suffix}.csv"),                         emit: vst_norm_counts
+        tuple path("Normalized_Counts${params.assay_suffix}.csv"),
+              path(params.mode == "microbes" ? "FeatureCounts_Unnormalized_Counts${params.assay_suffix}.csv" : 
+                   "RSEM_Unnormalized_Counts${params.assay_suffix}.csv"),                emit: norm_counts
+        path("contrasts${params.assay_suffix}.csv"),                                     emit: contrasts
+        path("SampleTable${params.assay_suffix}.csv"),                                   emit: sample_table      
+        path("differential_expression_no_annotations${params.assay_suffix}.csv"),        emit: dge_table
+        path("VST_Normalized_Counts${params.assay_suffix}.csv"),                         emit: vst_norm_counts
         path("summary.txt"),                                                              emit: summary
         path("versions2.txt"),                                                             emit: versions
 
     script:
-        def output_filename_suffix = params.output_suffix ?: ""
+        def output_filename_suffix = params.assay_suffix ?: ""
         def microbes = params.mode == 'microbes' ? 'TRUE' : 'FALSE'
         def dge_rmd_file = "${projectDir}/bin/dge_deseq2.Rmd"
         def debug_dummy_counts = params.use_dummy_gene_counts ? 'TRUE'  : 'FALSE'

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/extend_dge_table.nf

@@ -9,11 +9,11 @@ process EXTEND_DGE_TABLE {
         path(dge_table)
 
     output:
-        path("visualization_output_table${params.output_suffix}.csv"), emit: dge_visualization_table
+        path("visualization_output_table${params.assay_suffix}.csv"), emit: dge_visualization_table
         path("versions.txt"),    emit: versions_txt
 
     script:
-        def output_filename_suffix = params.output_suffix ?: ""
+        def output_filename_suffix = params.assay_suffix ?: ""
         def extend_rmd_file = "${projectDir}/bin/extend_dge_table.Rmd"
 
         """

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/featurecounts.nf

@@ -8,8 +8,8 @@ process FEATURECOUNTS {
     path(bam_files)
 
   output:
-    path("FeatureCounts_GLbulkRNAseq.tsv"),   emit: counts
-    path("FeatureCounts_GLbulkRNAseq.tsv.summary"), emit: summary
+    path("FeatureCounts${params.assay_suffix}.tsv"),   emit: counts
+    path("FeatureCounts${params.assay_suffix}.tsv.summary"), emit: summary
     path("versions.yml"),                           emit: versions
 
   script:
@@ -35,7 +35,7 @@ process FEATURECOUNTS {
       -a ${genomeGtf} \\
       -t "\${GTF_FEATURES}" \\
       -s ${strandOption} \\
-      -o "FeatureCounts_GLbulkRNAseq.tsv" \\
+      -o "FeatureCounts${params.assay_suffix}.tsv" \\
       \$bam_list
 
     echo '"${task.process}":' > versions.yml

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/generate_pca_table.nf

@@ -9,11 +9,11 @@ process GENERATE_PCA_TABLE {
         path(normalized_counts)
 
     output:
-        path("visualization_PCA_table${params.output_suffix}.csv"), emit: pca_table
+        path("visualization_PCA_table${params.assay_suffix}.csv"), emit: pca_table
         path("versions.txt"),    emit: versions_txt
 
     script:
-        def output_filename_suffix = params.output_suffix ?: ""
+        def output_filename_suffix = params.assay_suffix ?: ""
         def pca_rmd_file = "${projectDir}/bin/generate_pca_table.Rmd"
 
         """

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/help.nf

@@ -10,10 +10,10 @@ process MULTIQC {
 
     output:
     // path("${ mqc_label }_multiqc_GLbulkRNAseq_report.zip"), emit: zipped_report, to do: reimplement zip output w/ cleaned paths
-    path("${ mqc_label }_multiqc_GLbulkRNAseq_report"), emit: unzipped_report
-    path("${ mqc_label }_multiqc_GLbulkRNAseq_report.zip"), emit: zipped_report
-    path("${ mqc_label }_multiqc_GLbulkRNAseq_report/${ mqc_label }_multiqc_GLbulkRNAseq.html"), emit: html
-    path("${ mqc_label }_multiqc_GLbulkRNAseq_report/${ mqc_label }_multiqc_GLbulkRNAseq_data"), emit: data
+    path("${ mqc_label }_multiqc_${ params.assay_suffix }_report"), emit: unzipped_report
+    path("${ mqc_label }_multiqc_${ params.assay_suffix }_report.zip"), emit: zipped_report
+    path("${ mqc_label }_multiqc_${ params.assay_suffix }_report/${ mqc_label }_multiqc_${ params.assay_suffix }.html"), emit: html
+    path("${ mqc_label }_multiqc_${ params.assay_suffix }_report/${ mqc_label }_multiqc_${ params.assay_suffix }_data"), emit: data
     path("versions.yml"), emit: versions
 
     script:
@@ -22,11 +22,11 @@ process MULTIQC {
     multiqc \\
         --force \\
         --interactive \\
-        -o ${ mqc_label }_multiqc_GLbulkRNAseq_report \\
-        -n ${ mqc_label }_multiqc_GLbulkRNAseq \\
+        -o ${ mqc_label }_multiqc_${ params.assay_suffix }_report \\
+        -n ${ mqc_label }_multiqc_${ params.assay_suffix } \\
         ${ config_arg } \\
         .
-    zip -r '${ mqc_label }_multiqc_GLbulkRNAseq_report.zip' '${ mqc_label }_multiqc_GLbulkRNAseq_report'
+    zip -r '${ mqc_label }_multiqc_${ params.assay_suffix }_report.zip' '${ mqc_label }_multiqc_${ params.assay_suffix }_report'
 
     echo '"${task.process}":' > versions.yml
     echo "    multiqc: \$(multiqc --version | sed "s/multiqc, version //")" >> versions.yml