update

cwl/workflows/workflow_RNAseq_NonSpliced.cwl

@@ -21,33 +21,32 @@ doc: |
       - kallisto (transcript [pseudo]counts)
 
 outputs:
-  files_to_folder_fastqc:
+  filtered_stats:
+    label: Filtered statistics
+    doc: Statistics on quality and preprocessing of the reads
     type: Directory
-    label: FASTQC
-    doc: Quality reporting by FASTQC
-    outputSource: quality/files_to_folder_fastqc
-  files_to_folder_filtered:
-    label: Filtered reads folder
-    doc: Output folder with filtered reads.
-    type: Directory
-    outputSource: quality/files_to_folder_filtered
-  files_to_folder_bowtie2:
+    outputSource: workflow_quality/reports_folder
+  bowtie2_output:
     type: Directory
     label: bowtie2 output
     doc: bowtie2 mapping results folder. Contains sorted bam file, metrics file and mapping statistics (stdout).
     outputSource: bowtie2_files_to_folder/results
-  files_to_folder_featurecounts:
+  featurecounts_output:
     type: Directory
     label: FeatureCounts output
     doc: FeatureCounts results folder. Contains readcounts, summary and mapping statistics (stdout).
     outputSource: featurecounts_files_to_folder/results
-  files_to_folder_kallisto:
+  kallisto_output:
     type: Directory
     label: kallisto output
     doc: kallisto results folder. Contains transcript abundances, run info and summary.
     outputSource: kallisto_files_to_folder/results
 
 inputs:
+  identifier:
+    type: string
+    doc: Identifier for this dataset used in this workflow
+    label: identifier used
   threads:
     type: int?
     doc: number of threads to use for computational processes
@@ -60,20 +59,15 @@ inputs:
     default: 4000
   filter_rrna:
     type: boolean
-    label: Filer rRNA
+    label: Filter rRNA
     doc: Filter rRNA from reads if true
     default: false
-  prefix_id:
-    type: string
-    label: Filename prefix
-    doc: Prefix of the output filenames.
-    default: out
   forward_reads:
-    type: File
+    type: string[]
     doc: forward sequence file locally
     label: forward reads
   reverse_reads:
-    type: File
+    type: string[]
     doc: reverse sequence file locally
     label: reverse reads
   bowtie2-indexfolder:
@@ -89,6 +83,11 @@ inputs:
     label: GTF file
     doc: GTF file location
 
+  contamination_references:
+    type: string[]
+    doc: bbmap reference fasta file for contamination filtering
+    label: contamination reference file
+
   destination:
     type: string?
     label: Output Destination
@@ -96,31 +95,34 @@ inputs:
 
 steps:
   #########################################
-  # Workflow for quality and filtering using fastqc, fastp and optionally bbduk
-  quality:
+  # Workflow for quality and filtering of raw reads
+  workflow_quality:
     label: Quality and filtering workflow
     doc: Quality assessment of illumina reads with rRNA filtering option
+    run: workflow_illumina_quality.cwl
     in:
-      filter_rrna: filter_rrna
-      prefix_id: prefix_id
       forward_reads: forward_reads
       reverse_reads: reverse_reads
-      threads: threads
+      filter_references: contamination_references
       memory: memory
-    run: workflow_illumina_quality.cwl
-    out: [files_to_folder_fastqc, files_to_folder_filtered, QC_forward_reads, QC_reverse_reads]
+      threads: threads
+      identifier: identifier
+      filter_rrna: filter_rrna
+      step: 
+        default: 1
+    out: [QC_reverse_reads, QC_forward_reads, reports_folder]
   #########################################
   # bowtie2 alignment
   bowtie2:
     label: bowtie2
     doc: runs bowtie2 alignment on the genome with the quality filtered reads.
+    run: ../bowtie2/bowtie2_align_simple.cwl
     in:
-      prefix: prefix_id
-      forward_reads: quality/QC_forward_reads
-      reverse_reads: quality/QC_reverse_reads
+      prefix: identifier
+      forward_reads: workflow_quality/QC_forward_reads
+      reverse_reads: workflow_quality/QC_reverse_reads
       indexfolder: bowtie2-indexfolder
       threads: threads
-    run: ../bowtie2/bowtie2_align_simple.cwl
     out:     
       [sam, metricsfile,bowtie2_stats]
   #########################################
@@ -128,13 +130,13 @@ steps:
   sam_to_sorted-bam:
     label: sam to sorted bam
     doc: Converts a SAM file to a sorted BAM file
+    run: ../samtools/sam_to_sorted-bam.cwl
     in:
-      prefix: 
-       source: prefix_id
+      identifier: 
+       source: identifier
        valueFrom: $(self+"_bowtie2")
       sam: bowtie2/sam
       threads: threads
-    run: ../samtools/sam_to_sorted-bam.cwl
     out: 
       [sortedbam]
   #########################################
@@ -142,13 +144,13 @@ steps:
   featurecounts:
     label: FeatureCounts
     doc: Calculates gene counts with bowtie2 mapped data and input GTF file with FeatureCounts.
+    run: ../RNAseq/featurecounts.cwl
     in:
-      prefix: prefix_id
+      prefix: identifier
       bam: sam_to_sorted-bam/sortedbam
       gtf: gtf
       threads: threads
     when: $(inputs.gtf != undefined)
-    run: ../RNAseq/featurecounts.cwl
     out: 
       [readcounts, summary, overview]
   #########################################
@@ -156,15 +158,15 @@ steps:
   kallisto:
     label: kallisto
     doc: Calculates transcript abundances
+    run: ../RNAseq/kallisto/kallisto_quant.cwl
     in:
       gtf: gtf
-      prefix: prefix_id
-      forward_reads: quality/QC_forward_reads
-      reverse_reads: quality/QC_reverse_reads
+      prefix: identifier
+      forward_reads: workflow_quality/QC_forward_reads
+      reverse_reads: workflow_quality/QC_reverse_reads
       indexfolder: kallisto-indexfolder
       threads: threads
     when: $(inputs.gtf != undefined)
-    run: ../RNAseq/kallisto/kallisto_quant.cwl
     out:
       [abundance.h5, abundance.tsv, run_info, summary]
 
@@ -173,6 +175,7 @@ steps:
   bowtie2_files_to_folder:
     label: bowtie2 output
     doc: Preparation of bowtie2 output files to a specific output folder
+    run: ../expressions/files_to_folder.cwl
     in:
       files: 
         source: [sam_to_sorted-bam/sortedbam, bowtie2/metricsfile, bowtie2/bowtie2_stats]
@@ -180,13 +183,13 @@ steps:
         pickValue: all_non_null
       destination: 
         default: "3_bowtie2-alignment"
-    run: ../expressions/files_to_folder.cwl
     out:
       [results]
 
   featurecounts_files_to_folder:
     label: FeatureCounts output
     doc: Preparation of FeatureCounts output files to a specific output folder
+    run: ../expressions/files_to_folder.cwl
     in:
       gtf: gtf
       files: 
@@ -196,13 +199,13 @@ steps:
       destination:
         default: "4_FeatureCounts"
     when: $(inputs.gtf != undefined)
-    run: ../expressions/files_to_folder.cwl
     out:
       [results]
       
   kallisto_files_to_folder:
     label: kallisto output
     doc: Preparation of kallisto output files to a specific output folder
+    run: ../expressions/files_to_folder.cwl
     in:
       gtf: gtf
       files: 
@@ -212,7 +215,6 @@ steps:
       destination: 
         default: "5_Kallisto"
     when: $(inputs.gtf != undefined)
-    run: ../expressions/files_to_folder.cwl
     out:
       [results]
 #############################################

cwl/workflows/workflow_RNAseq_Spliced.cwl

@@ -20,33 +20,32 @@ doc: |
       - kallisto (transcript [pseudo]counts)
 
 outputs:
-  files_to_folder_fastqc:
+  filtered_stats:
+    label: Filtered statistics
+    doc: Statistics on quality and preprocessing of the reads
     type: Directory
-    label: FASTQC
-    doc: Quality reporting by FASTQC
-    outputSource: quality/files_to_folder_fastqc
-  files_to_folder_filtered:
-    type: Directory
-    label: Filtered reads folder
-    doc: Output folder with filtered reads.
-    outputSource: quality/files_to_folder_filtered
-  files_to_folder_STAR:
+    outputSource: workflow_quality/reports_folder
+  STAR_output:
     type: Directory
     label: STAR output folder
     doc: STAR results folder. Contains logs, bam file, readcounts per gene and splice_junctions.
     outputSource: STAR_files_to_folder/results
-  files_to_folder_featurecounts:
+  featurecounts_output:
     type: Directory
     label: FeatureCounts output
     doc: FeatureCounts results folder. Contains readcounts, summary and mapping statistics (stdout).
     outputSource: featurecounts_files_to_folder/results
-  files_to_folder_kallisto:
+  kallisto_output:
     type: Directory
     label: kallisto output
     doc: kallisto results folder. Contains transcript abundances, run info and summary.
     outputSource: kallisto_files_to_folder/results
 
 inputs:
+  identifier:
+    type: string
+    doc: Identifier for this dataset used in this workflow
+    label: identifier used
   threads:
     type: int?
     doc: number of threads to use for computational processes
@@ -60,16 +59,12 @@ inputs:
   filter_rrna:
     type: boolean
     default: true
-  prefix_id:
-    type: string
-    doc: prefix of the filename outputs
-    default: out
   forward_reads:
-    type: File
+    type: string[]
     doc: forward sequence file locally
     label: forward reads
   reverse_reads:
-    type: File
+    type: string[]
     doc: reverse sequence file locally
     label: reverse reads
 
@@ -94,6 +89,11 @@ inputs:
         - GeneCounts
     doc: Run with get gene quantification
 
+  contamination_references:
+    type: string[]
+    doc: bbmap reference fasta file for contamination filtering
+    label: contamination reference file
+
   destination:
     type: string?
     label: Output Destination
@@ -101,30 +101,33 @@ inputs:
 
 steps:
   #########################################
-  # Workflow for quality and filtering using fastqc, fastp and optionally bbduk
-  quality:
+  # Workflow for quality and filtering of raw reads
+  workflow_quality:
     label: Quality and filtering workflow
     doc: Quality assessment of illumina reads with rRNA filtering option
+    run: workflow_illumina_quality.cwl
     in:
-      filter_rrna: filter_rrna
-      prefix_id: prefix_id
       forward_reads: forward_reads
       reverse_reads: reverse_reads
-      threads: threads
+      filter_references: contamination_references
       memory: memory
-    run: workflow_illumina_quality.cwl
-    out: [files_to_folder_fastqc, files_to_folder_filtered, QC_forward_reads, QC_reverse_reads]
+      threads: threads
+      identifier: identifier
+      filter_rrna: filter_rrna
+      step: 
+        default: 1
+    out: [QC_reverse_reads, QC_forward_reads, reports_folder]
   #########################################
   # STAR alignment
   STAR:
     label: STAR
     doc: runs STAR alignment on the genome with the quality filtered reads.
     in:
-      forward_reads: quality/QC_forward_reads
-      reverse_reads: quality/QC_reverse_reads
+      forward_reads: workflow_quality/QC_forward_reads
+      reverse_reads: workflow_quality/QC_reverse_reads
 
       OutFileNamePrefix:
-        source: prefix_id
+        source: identifier
         valueFrom: $(self+"_")
       genomeDir: STAR-indexfolder
       sjdbGTFfile: gtf
@@ -141,7 +144,7 @@ steps:
     label: FeatureCounts
     doc: Calculates gene counts with bowtie2 mapped data and input GTF file with FeatureCounts.
     in:
-      prefix: prefix_id
+      prefix: identifier
       bam: STAR/bam
       gtf: gtf
       threads: threads
@@ -154,9 +157,9 @@ steps:
     label: kallisto
     doc: Calculates transcript abundances
     in:
-      prefix: prefix_id
-      forward_reads: quality/QC_forward_reads
-      reverse_reads: quality/QC_reverse_reads
+      prefix: identifier
+      forward_reads: workflow_quality/QC_forward_reads
+      reverse_reads: workflow_quality/QC_reverse_reads
       indexfolder: kallisto-indexfolder
       threads: threads
     run: ../RNAseq/kallisto/kallisto_quant.cwl
@@ -169,7 +172,7 @@ steps:
     label: STAR output
     doc: Preparation of STAR output files to a specific output folder
     in:
-      files: 
+      files:
         source: [STAR/bam, STAR/log_file, STAR/final_log_file, STAR/reads_per_gene, STAR/splice_junctions]
         linkMerge: merge_flattened
         pickValue: all_non_null