Merge branch 'cwl' into 'main'

Cwl

See merge request !14

.gitattributes

@@ -32,4 +32,16 @@ runs/kallisto_sleuth/sleuth_dge.csv filter=lfs diff=lfs merge=lfs -text
 studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa filter=lfs diff=lfs merge=lfs -text
 runs/sleuth/kallisto_sleuthObject.RData filter=lfs diff=lfs merge=lfs -text
 runs/sleuth/out/kallisto_sleuthObject.RData filter=lfs diff=lfs merge=lfs -text
-runs/kallisto/kallisto_results/** filter=lfs diff=lfs merge=lfs -text
\ No newline at end of file
+runs/kallisto/kallisto_results/** filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_097_CAMMD_CAGATC_L001_R1_001_fastqc.zip filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_163_reC3MD_GTGAAA_L001_R1_001_fastqc.html filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_097_CAMMD_CAGATC_L001_R1_001_fastqc.html filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_099_CAMMD_CTTGTA_L001_R1_001_fastqc.html filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_099_CAMMD_CTTGTA_L001_R1_001_fastqc.zip filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_103_CAMMD_AGTCAA_L001_R1_001_fastqc.html filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_103_CAMMD_AGTCAA_L001_R1_001_fastqc.zip filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_161_reC3MD_GTCCGC_L001_R1_001_fastqc.html filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_161_reC3MD_GTCCGC_L001_R1_001_fastqc.zip filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_163_reC3MD_GTGAAA_L001_R1_001_fastqc.zip filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_165_re-C3MD_GTGAAA_L002_R1_001_fastqc.html filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_165_re-C3MD_GTGAAA_L002_R1_001_fastqc.zip filter=lfs diff=lfs merge=lfs -text

runs/fastqc/run.cwl

+cwlVersion: v1.2
+class: Workflow
+
+requirements:
+  SubworkflowFeatureRequirement: {}
+  ScatterFeatureRequirement: {}
+  MultipleInputFeatureRequirement: {}
+
+inputs:
+  fastq: File[]
+  finaloutdir: string
+
+steps:
+  fastqc:
+    run: ../../workflows/fastqc/workflow.cwl
+    in:
+      fastq: fastq
+      finaloutdir: finaloutdir
+    out: [outdir]
+
+outputs:
+  outdir:
+    type: Directory
+    outputSource: fastqc/outdir
\ No newline at end of file

runs/fastqc/run.yml

+finaloutdir: "results"
+fastq:
+  - class: File
+    path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_097_CAMMD_CAGATC_L001_R1_001.fastq.gz
+  - class: File
+    path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_099_CAMMD_CTTGTA_L001_R1_001.fastq.gz
+  - class: File
+    path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_103_CAMMD_AGTCAA_L001_R1_001.fastq.gz
+  - class: File
+    path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_161_reC3MD_GTCCGC_L001_R1_001.fastq.gz
+  - class: File
+    path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_163_reC3MD_GTGAAA_L001_R1_001.fastq.gz
+  - class: File
+    path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_165_re-C3MD_GTGAAA_L002_R1_001.fastq.gz
\ No newline at end of file

runs/kallisto/run.cwl

@@ -4,16 +4,20 @@ class: Workflow
 
 requirements:
   SubworkflowFeatureRequirement: {}
+  MultipleInputFeatureRequirement: {}
 
 inputs:
   IndexInput: File[]
-  InputReadsMultipleSamples:
-    type: 
+  sampleRecord:
+    type:
       type: array
-      items: 
-        type: array
-        items: File
-  numUnderscoresFileName: int
+      items:
+        type: record
+        fields:
+          readsOfOneSample:
+            type: File[]
+          sampleName:
+            type: string?
   isSingle: boolean
   FragmentLength: double?  
   StandardDeviation: double?
@@ -25,8 +29,7 @@ steps:
     run:  ../../workflows/kallisto/workflow.cwl
     in:
       IndexInput: IndexInput
-      InputReadsMultipleSamples: InputReadsMultipleSamples
-      numUnderscoresFileName: numUnderscoresFileName
+      sampleRecord: sampleRecord
       isSingle: isSingle
       FragmentLength: FragmentLength
       StandardDeviation: StandardDeviation

runs/kallisto/run.yml

@@ -5,44 +5,47 @@ IndexInput:
     format: edam:format_1929 # FASTA
 
 ## Fastq files to be mapped
-# The `InputReadsMultipleSamples` looks more complicated than needed
-# It's an array of File arrays to generically allow multiple fastq files per sample
+# The `readsOfOneSample` looks more complicated than needed
+# It's an array of records (each with one or mupltiple files and a sample name) to generically allow multiple fastq files per sample
 
-InputReadsMultipleSamples:
-  - 
+sampleRecord:
+  - readsOfOneSample:
     - class: File
       path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_097_CAMMD_CAGATC_L001_R1_001.fastq.gz
-      format: edam:format_1930 # FASTQ
-  - 
+      format: edam:format_1930
+    sampleName: 'DB_097'
+  - readsOfOneSample:  
+    - class: File
+      path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_163_reC3MD_GTGAAA_L001_R1_001.fastq.gz
+      format: edam:format_1930
+    sampleName: 'DB_163'
+  - readsOfOneSample:
     - class: File
       path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_099_CAMMD_CTTGTA_L001_R1_001.fastq.gz
-      format: edam:format_1930 # FASTQ
-  # - 
-  #   - class: File
-  #     path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_103_CAMMD_AGTCAA_L001_R1_001.fastq.gz
-  #     format: edam:format_1930 # FASTQ
-  # - 
-  #   - class: File
-  #     path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_161_reC3MD_GTCCGC_L001_R1_001.fastq.gz
-  #     format: edam:format_1930 # FASTQ
-  # - 
-  #   - class: File
-  #     path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_163_reC3MD_GTGAAA_L001_R1_001.fastq.gz
-  #     format: edam:format_1930 # FASTQ
-  # - 
-  #   - class: File
-  #     path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_165_re-C3MD_GTGAAA_L002_R1_001.fastq.gz
-  #     format: edam:format_1930 # FASTQ
-
-numUnderscoresFileName: 2
+      format: edam:format_1930
+    sampleName: 'DB_099'
+  - readsOfOneSample:
+    - class: File
+      path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_103_CAMMD_AGTCAA_L001_R1_001.fastq.gz
+      format: edam:format_1930
+    sampleName: 'DB_103'
+  - readsOfOneSample:
+    - class: File
+      path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_161_reC3MD_GTCCGC_L001_R1_001.fastq.gz
+      format: edam:format_1930
+    sampleName: 'DB_161'
+  - readsOfOneSample:
+    - class: File
+      path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_165_re-C3MD_GTGAAA_L002_R1_001.fastq.gz
+      format: edam:format_1930
+    sampleName: 'DB_165'
 
 ### Kallisto quant Parameters
 isSingle: true
 FragmentLength: 200
 StandardDeviation: 20
 BootstrapSamples: 30
-
-resultsFolder: test
+resultsFolder: kallisto_results
 
 $namespaces:
   edam: https://edamontology.org/
\ No newline at end of file

workflows/fastqc/collectFilesInDir.cwl

+cwlVersion: v1.2
+class: ExpressionTool
+label: Collect files in a directory
+doc: |
+  Takes Files (e.g. from a workflow step) and yields them in a desired directory.
+requirements:
+  - class: InlineJavascriptRequirement
+inputs:
+  files: File[]
+  destination: string
+expression: |
+  ${
+    return {"outDir": {
+      "class": "Directory", 
+      "basename": inputs.destination,
+      "listing": inputs.files
+    } };
+  }
+outputs:
+  outDir: Directory
\ No newline at end of file

workflows/fastqc/fastqc.cwl

+#!/usr/bin/env cwl-runner
+cwlVersion: v1.2
+class: CommandLineTool
+
+label: Run fastqc on raw reads in FASTQ format (single or paired end) or aligned reads in BAM.
+
+doc: |
+  simplified from: https://github.com/common-workflow-library/bio-cwl-tools/blob/66f620da5b0a11e934a6da83272205a2516bcd91/fastqc/fastqc_1.cwl
+  
+  Run fastqc on raw reads in FASTQ format (single or paired end) or aligned reads in BAM.
+
+hints:
+  ResourceRequirement:
+    coresMin: 1
+    ramMin: 5000
+  DockerRequirement:
+    dockerPull: quay.io/biocontainers/fastqc:0.11.9--hdfd78af_1
+  SoftwareRequirement:
+    packages:
+      fastqc:
+        specs: [ https://identifiers.org/biotools/fastqc ]
+        version: [ "0.11.9" ]
+
+
+baseCommand: "fastqc"
+arguments: 
+  - valueFrom: $(runtime.outdir)
+    prefix: "-o"
+  - valueFrom: "--noextract"
+
+inputs:
+  fastq:
+    type: File
+    inputBinding:
+      position: 1
+ 
+outputs:
+  fastqc_zip:
+    doc: all data e.g. figures
+    type: File
+    outputBinding:
+      glob: "*_fastqc.zip"
+  fastqc_html:
+    doc: html report showing results from zip
+    type: File
+    outputBinding:
+      glob: "*_fastqc.html"
+