towards combining everything in one arc.cwl

arc-job.yml

+################################################################################
+### runs/kallisto
+################################################################################
+
+## Genome file to build kallisto Index
+kallisto_IndexInput:
+  - class: File
+    path: ../../studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa
+    format: edam:format_1929 # FASTA
+
+## Fastq files to be mapped
+# 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
+
+kallisto_sampleRecord:
+  - readsOfOneSample:
+    - class: File
+      path: ../../assays/RNASeq/dataset/DB_097_CAMMD_CAGATC_L001_R1_001.fastq.gz
+      format: edam:format_1930
+    sampleName: 'DB_097'
+  - readsOfOneSample:  
+    - class: File
+      path: ../../assays/RNASeq/dataset/DB_163_reC3MD_GTGAAA_L001_R1_001.fastq.gz
+      format: edam:format_1930
+    sampleName: 'DB_163'
+  - readsOfOneSample:
+    - class: File
+      path: ../../assays/RNASeq/dataset/DB_099_CAMMD_CTTGTA_L001_R1_001.fastq.gz
+      format: edam:format_1930
+    sampleName: 'DB_099'
+  - readsOfOneSample:
+    - class: File
+      path: ../../assays/RNASeq/dataset/DB_103_CAMMD_AGTCAA_L001_R1_001.fastq.gz
+      format: edam:format_1930
+    sampleName: 'DB_103'
+  - readsOfOneSample:
+    - class: File
+      path: ../../assays/RNASeq/dataset/DB_161_reC3MD_GTCCGC_L001_R1_001.fastq.gz
+      format: edam:format_1930
+    sampleName: 'DB_161'
+  - readsOfOneSample:
+    - class: File
+      path: ../../assays/RNASeq/dataset/DB_165_re-C3MD_GTGAAA_L002_R1_001.fastq.gz
+      format: edam:format_1930
+    sampleName: 'DB_165'
+
+### Kallisto quant Parameters
+kallisto_isSingle: true
+kallisto_FragmentLength: 200
+kallisto_StandardDeviation: 20
+kallisto_BootstrapSamples: 30
+kallisto_resultsFolder: kallisto_results
+
+$namespaces:
+  edam: https://edamontology.org/
+
+################################################################################
+### runs/isaSampleToRawDataSeq
+################################################################################
+
+isaSampleToRawDataSeq_arcPath: 
+  class: Directory
+  path: ../../
+isaSampleToRawDataSeq_assayName: "RNASeq"
+isaSampleToRawDataSeq_outName: rnaseq-samples
+isaSampleToRawDataSeq_startingNodeNum: 0

arc.cwl

+cwlVersion: v1.2
+class: Workflow
+
+requirements:
+  SubworkflowFeatureRequirement: {}
+  ScatterFeatureRequirement: {}
+  MultipleInputFeatureRequirement: {}
+
+inputs:
+  #### runs/kallisto
+  kallisto_IndexInput: File[]
+  kallisto_sampleRecord:
+    type:
+      type: array
+      items:
+        type: record
+        fields:
+          readsOfOneSample:
+            type: File[]
+          sampleName:
+            type: string?
+  kallisto_isSingle: boolean
+  kallisto_FragmentLength: double?  
+  kallisto_StandardDeviation: double?
+  kallisto_BootstrapSamples: int?
+  kallisto_resultsFolder: string
+
+  #### runs/isaSampleToRawDataSeq
+  isaSampleToRawDataSeq_arcPath: Directory 
+  isaSampleToRawDataSeq_assayName: string
+  isaSampleToRawDataSeq_startingNodeNum: int
+  isaSampleToRawDataSeq_outName: string
+
+  #### runs/sleuth
+#   sleuth_inKallistoResults: Directory
+#   sleuth_inMetadataFile: File
+  sleuth_inMetadataSample: string
+  sleuth_inMetadataFactorList: string[]
+  sleuth_inMetadataDataCol: string
+  sleuth_outFolder: string
+
+steps:
+    kallisto:
+        run: runs/kallisto/run.cwl
+        in:
+            IndexInput:         kallisto_IndexInput
+            sampleRecord:       kallisto_sampleRecord
+            isSingle:           kallisto_isSingle
+            FragmentLength:     kallisto_FragmentLength
+            StandardDeviation:  kallisto_StandardDeviation
+            BootstrapSamples:   kallisto_BootstrapSamples
+            resultsFolder:      kallisto_resultsFolder
+        out: [finalOut]
+
+
+    isaSampleToRawDataSeq:
+        run: runs/isaSampleToRawDataSeq/run.cwl
+        in:
+          arcPath:          isaSampleToRawDataSeq_arcPath
+          assayName:        isaSampleToRawDataSeq_assayName
+          startingNodeNum:  isaSampleToRawDataSeq_startingNodeNum
+          outName:          isaSampleToRawDataSeq_outName
+        out: [output]
+
+    sleuth:
+        run: runs/sleuth/run.cwl
+        in:
+            inKallistoResults:      kallisto/finalOut
+            inMetadataFile:         isaSampleToRawDataSeq/output
+            inMetadataSample:       sleuth_inMetadataSample
+            inMetadataFactorList:   sleuth_inMetadataFactorList
+            inMetadataDataCol:      sleuth_inMetadataDataCol
+            outFolder:              sleuth_outFolder
+        out: [outdir]
+
+outputs:
+
+  outdir:
+    type: Directory[]
+    outputSource: sleuth/outdir
\ No newline at end of file

runs/sleuth/run.cwl

@@ -12,7 +12,7 @@ inputs:
   outFolder: string
 
 steps: 
-  collectResults:
+  sleuth:
     run: ../../workflows/sleuth/workflow.cwl
     in:
       inKallistoResults: inKallistoResults
@@ -26,4 +26,4 @@ steps:
 outputs:
  outdir:
     type: Directory[]
-    outputSource: collectResults/outdir
+    outputSource: sleuth/outdir