Merge pull request #4 from fjrmoreews/variation

Variation

Variation/job-variation_PE.yml

@@ -0,0 +1,67 @@
+#fastp
+reads_reverse:
+        - {class: File, path: ./data/SRR10903402/reverse.fastqsanger, format: http://edamontology.org/format_1931}
+reads_forward:
+        - {class: File, path: ./data/SRR10903402/forward.fastqsanger, format: http://edamontology.org/format_1931}
+min_length_required: 15
+disable_trim_poly_g: false
+force_polyg_tail_trimming: true
+#samtools_view_filter
+exclude_unmapped: false
+count: false 
+
+reference_in:
+        class: File
+        path: ./data/covid19.fa
+        format: http://edamontology.org/format_1929
+end_to_end_very_sensitive: true
+bankfile:
+        class: File
+        path: ./data/NC_045512.2
+genome_reference: covid19
+
+#picard_MarkDuplicates
+alignments_are_sorted: true
+remove_duplicates: true
+duplicate_scoring_strategy: SUM_OF_BASE_QUALITIES
+optical_duplicate_pixel_distance: 100
+
+#lofreq_call
+min_cov: 50
+max_depth: 1000000
+min_bq: 30
+min_alt_bq: 30
+min_mq: 20
+max_mq: 255
+min_jq: 0
+min_alt_jq: 0
+def_alt_jq: 0
+#pvalue_cutoff: 0.1
+#bonferroni: 'dynamic'
+threads: 1
+call_indels: true
+
+udLength: 0
+formatEff: true
+classic: true
+inputFormat: vcf
+outputFormat: vcf
+importGenome: true
+
+extractFields:
+  - "CHROM"
+  - "POS"
+  - "REF"
+  - "ALT"
+  - "DP"
+  - "AF"
+  - "SB"
+  - "DP4"
+  - "EFF[*].IMPACT"
+  - "EFF[*].FUNCLASS"
+  - "EFF[*].EFFECT"
+  - "EFF[*].GENE"
+  - "EFF[*].CODON"
+empty_text: "."
+
+IndexName: covid19.fa

Variation/tools/bwa-index.cwl

@@ -0,0 +1,49 @@
+#!/usr/bin/env cwl-runner
+cwlVersion: v1.0
+class: CommandLineTool
+
+requirements:
+  DockerRequirement:
+    dockerPull: "quay.io/biocontainers/bwa:0.7.17--ha92aebf_3"
+  InlineJavascriptRequirement: {}
+
+inputs:
+  InputFile:
+    type: File
+    format: edam:format_1929  # FASTA
+    inputBinding:
+      position: 200
+
+  IndexName:
+    type: string
+    inputBinding:
+      prefix: "-p"
+      #valueFrom: $(self + ".bwt")
+#Optional arguments
+  algoType:
+    type: 
+      - "null"
+      - type: enum
+        symbols:
+          - is
+          - bwtsw
+    inputBinding:
+      prefix: "-a"
+
+baseCommand: [bwa, index]
+
+outputs: 
+  index:
+    type: File
+    secondaryFiles: 
+   #   - $(inputs.IndexName).bwt.bwt
+      - $(inputs.IndexName).sa
+      - $(inputs.IndexName).pac
+      - $(inputs.IndexName).ann
+      - $(inputs.IndexName).amb
+    outputBinding:
+      glob: $(inputs.IndexName).bwt
+$namespaces:
+  edam: http://edamontology.org/
+$schemas:
+  - http://edamontology.org/EDAM_1.18.owl

Variation/tools/bwa-mem.cwl

@@ -0,0 +1,134 @@
+#!/usr/bin/env cwl-runner
+cwlVersion: v1.0
+class: CommandLineTool
+
+requirements:
+  DockerRequirement:
+    dockerPull: "quay.io/biocontainers/bwa:0.7.17--ha92aebf_3"
+
+inputs:
+  InputFile:
+    type: File[]
+    format:
+      - edam:format_1930 # FASTA
+      - edam:format_1931 # FASTQ
+    inputBinding:
+      position: 201
+
+  Index:
+    type: File
+    inputBinding:
+      position: 200
+    secondaryFiles:
+      - .fai
+      - .amb
+      - .ann
+      - .bwt
+      - .pac
+      - .sa
+
+#Optional arguments
+
+  Threads:
+    type: int?
+    inputBinding:
+      prefix: "-t"
+
+  MinSeedLen:
+    type: int?
+    inputBinding:
+      prefix: "-k"
+
+  BandWidth:
+    type: int?
+    inputBinding:
+      prefix: "-w"
+
+  ZDropoff:
+    type: int?
+    inputBinding:
+      prefix: "-d"
+
+  SeedSplitRatio:
+    type: float?
+    inputBinding:
+      prefix: "-r"
+
+  MaxOcc:
+    type: int?
+    inputBinding:
+      prefix: "-c"
+
+  MatchScore:
+    type: int?
+    inputBinding:
+      prefix: "-A"
+
+  MmPenalty:
+    type: int?
+    inputBinding:
+      prefix: "-B"
+
+  GapOpenPen:
+    type: int?
+    inputBinding:
+      prefix: "-O"
+
+  GapExtPen:
+    type: int?
+    inputBinding:
+      prefix: "-E"
+
+  ClipPen:
+    type: int?
+    inputBinding:
+      prefix: "-L"
+
+  UnpairPen:
+    type: int?
+    inputBinding:
+      prefix: "-U"
+
+  RgLine:
+    type: string?
+    inputBinding:
+      prefix: "-R"
+
+  VerboseLevel:
+    type: int?
+    inputBinding:
+      prefix: "-v"
+
+  isOutSecAlign:
+    type: boolean?
+    inputBinding:
+      prefix: "-a"
+
+  isMarkShortSplit:
+    type: boolean?
+    inputBinding:
+      prefix: "-M"
+
+  isUseHardClip:
+    type: boolean?
+    inputBinding:
+      prefix: "-H"
+
+  isMultiplexedPair:
+    type: boolean?
+    inputBinding:
+      prefix: "-p"
+
+
+baseCommand: [bwa, mem]
+
+stdout: unsorted_reads.sam
+
+outputs:
+  reads_stdout:
+    type: stdout
+    format: edam:format_2572 
+$namespaces:
+  edam: http://edamontology.org/
+$schemas:
+  - http://edamontology.org/EDAM_1.18.owl

Variation/tools/fastp.cwl

@@ -6,14 +6,15 @@ doc: |
   Modified from https://github.com/nigyta/bact_genome/blob/master/cwl/tool/fastp/fastp.cwl
 requirements:
     InlineJavascriptRequirement: {}
+hints:
     DockerRequirement:
         dockerPull: quay.io/biocontainers/fastp:0.20.0--hdbcaa40_0
 
 baseCommand: [fastp]
 
 arguments:
-    - -o
-    - $(inputs.fastq1.nameroot).fastp.fastq
+    - prefix: -o
+      valueFrom: $(inputs.fastq1.nameroot).fastp.fastq
     - |
       ${
         if (inputs.fastq2){
@@ -34,9 +35,15 @@ arguments:
 inputs:
     fastq1:
       type: File
+      format:
+        - edam:format_1930 # FASTA
+        - edam:format_1931 # FASTQ
       inputBinding:
         prefix: -i
     fastq2:
+      format:
+        - edam:format_1930 # FASTA
+        - edam:format_1931 # FASTQ
       type: File?
       inputBinding:
         prefix: -I
@@ -80,19 +87,14 @@ inputs:
 outputs:
     out_fastq1:
        type: File
+       format: $(inputs.fastq1.format)
        outputBinding:
            glob: $(inputs.fastq1.nameroot).fastp.fastq
     out_fastq2:
        type: File?
+       format: $(inputs.fastq2.format)
        outputBinding:
-           glob: |
-            ${
-             if (inputs.fastq2){
-                return inputs.fastq2.nameroot + ".fastp.fastq"
-             } else {
-                return 'no_file'
-              }
-             }
+           glob: $(inputs.fastq2.nameroot).fastp.fastq
     html_report:
       type: File
       outputBinding:
@@ -102,3 +104,7 @@ outputs:
       outputBinding:
         glob: fastp.json
 
+$namespaces:
+  edam: http://edamontology.org/
+$schemas:
+  - http://edamontology.org/EDAM_1.18.owl

Variation/tools/get_secondaryfiles.cwl

@@ -0,0 +1,35 @@
+class: CommandLineTool
+cwlVersion: v1.0
+requirements:
+  InlineJavascriptRequirement: {}
+  InitialWorkDirRequirement:
+    listing:
+      - $(inputs.sequence)
+      - $(inputs.bwa_index)
+baseCommand: [ls]
+inputs:
+  sequence:
+    type: File
+    secondaryFiles: .fai
+
+  bwa_index:
+    type: File
+    secondaryFiles:
+      - $(self.nameroot).ann 
+      - $(self.nameroot).amb
+      - $(self.nameroot).pac
+      - $(self.nameroot).sa
+
+outputs:
+  sequences_with_index: 
+    type: File
+    secondaryFiles: 
+      - $(inputs.bwa_index.nameroot).bwt
+      - $(inputs.bwa_index.nameroot).sa
+      - $(inputs.bwa_index.nameroot).pac
+      - $(inputs.bwa_index.nameroot).ann
+      - $(inputs.bwa_index.nameroot).amb
+      - $(inputs.sequence.basename).fai
+    outputBinding:
+      glob: $(inputs.sequence.basename)
+

Variation/tools/mergetab.cwl

@@ -0,0 +1,18 @@
+cwlVersion: v1.0
+class: CommandLineTool
+requirements:
+  InlineJavascriptRequirement: {}
+baseCommand: [ls]
+inputs:
+  out_fastq1: File
+  out_fastq2: File
+outputs:
+  tab:
+    type: File[]
+    outputBinding:
+      outputEval: |
+              ${var tab=[]
+                tab.push(inputs.out_fastq1)
+                tab.push(inputs.out_fastq2)
+                return tab;
+               }