Merge branch 'dev'

cwl/convert_TNMafPileupPair_to_MSIInputPair.cwl

@@ -0,0 +1,25 @@
+#!/usr/bin/env cwl-runner
+cwlVersion: v1.2
+class: ExpressionTool
+requirements:
+- $import: types.yml
+
+inputs:
+  pairs: "types.yml#TNMafPileupPair[]"
+
+outputs:
+  pairs: "types.yml#MSIInputPair[]"
+
+expression: |
+  ${
+    var pairs = [];
+    for ( var i in inputs.pairs ){
+      var pair = {
+        "tumor_id": inputs.pairs[i].tumor_id,
+        "normal_id": inputs.pairs[i].normal_id,
+        "pair_id": inputs.pairs[i].pair_id,
+      };
+      pairs.push(pair);
+    };
+    return {"pairs": pairs};
+  }

cwl/convert_TNMafPileupPair_to_TMBInputPair.cwl

@@ -0,0 +1,26 @@
+#!/usr/bin/env cwl-runner
+cwlVersion: v1.2
+class: ExpressionTool
+requirements:
+- $import: types.yml
+
+inputs:
+  pairs: "types.yml#TNMafPileupPair[]"
+
+outputs:
+  pairs: "types.yml#TMBInputPair[]"
+
+expression: |
+  ${
+    var pairs = [];
+    for ( var i in inputs.pairs ){
+      var pair = {
+        "tumor_id": inputs.pairs[i].tumor_id,
+        "normal_id": inputs.pairs[i].normal_id,
+        "pair_id": inputs.pairs[i].pair_id,
+        "pair_maf": inputs.pairs[i].pair_maf
+      };
+      pairs.push(pair);
+    };
+    return {"pairs": pairs};
+  }

cwl/facets-workflow.cwl

@@ -84,17 +84,7 @@ requirements:
   - $import: types.yml
 
 inputs:
-  pairs:
-    type:
-      type: array
-      items:
-        type: record
-        fields:
-          pair_maf: File
-          snp_pileup: File
-          pair_id: string
-          tumor_id: string
-          normal_id: string
+  pairs: "types.yml#TNMafPileupPair[]"
 
 steps:
   # run the facets suite wrapper set on each tumor normal pair

cwl/msi.cwl

@@ -1,18 +1,7 @@
 #!/usr/bin/env cwl-runner
-
-# example command;
-#    msisensor msi \
-#    -d msi_sites
-#    -n normal_bam
-#    -t tumor_bam
-#    -tumor_sample_name tumor_sample_name
-#    -normal_sample_name normal_sample_name
-#    -o ${ return inputs.tumor_sample_name +"."+inputs.normal_sample_name+".msi.txt" }
-#
-
 cwlVersion: v1.0
 class: CommandLineTool
-baseCommand: [ "msisensor", "msi", "-b", "8" ]
+baseCommand: [ "msisensor", "msi" ]
 
 requirements:
   DockerRequirement:
@@ -22,141 +11,110 @@ requirements:
     ramMin: 16000
     coresMin: 8
 
-doc: |
-  Run msisensor on tumor-normal bams to differentiate MSI (microsatellite instable) samples from MSS (microsatellite stable) ones
+doc: Run msisensor on tumor-normal bams to differentiate MSI (microsatellite instable) samples from MSS (microsatellite stable) ones
 
 # NOTE: next time use more verbose input labels, and only make input args for options we are using in the pipeline
 inputs:
-  d:
+  threads:
+    doc: threads number for parallel computing
+    type: string
+    default: "8"
+    # NOTE: no performance gains seen when using >8 threads
+    inputBinding:
+      prefix: -b
+
+  microsatellites_file:
     type:
     - string
     - File
     doc: homopolymer and microsatellites file
     inputBinding:
       prefix: -d
 
-  n:
+  normal_bam:
     type:
     - File
     doc: normal bam file
     secondaryFiles: ["^.bai"]
     inputBinding:
       prefix: -n
 
-  t:
+  tumor_bam:
     type:
     - File
     doc: tumor bam file
     secondaryFiles: ["^.bai"]
     inputBinding:
       prefix: -t
 
-  o:
+  output_filename:
     type: string
     doc: output distribution file
+    default: msi.txt
     inputBinding:
       prefix: -o
 
-#below are optional inputs
-  # e:
-  #   type: ['null', string]
-  #   doc: bed file, to select a few regions
-  #   inputBinding:
-  #     prefix: -e
-  #
-  # f:
-  #   type: ['null', double]
-  #   doc: FDR threshold for somatic sites detection
-  #   default: 0.05
-  #   inputBinding:
-  #     prefix: -f
-  #
-  # r:
-  #   type: ['null', string]
-  #   doc: choose one region, format 1:10000000-20000000
-  #   inputBinding:
-  #     prefix: -r
-  #
-  # l:
-  #   type: ['null', int]
-  #   default: 5
-  #   doc: minimal homopolymer size
-  #   inputBinding:
-  #     prefix: -l
-  #
-  # p:
-  #   type: ['null', int]
-  #   default: 10
-  #   doc: minimal homopolymer size for distribution analysis
-  #   inputBinding:
-  #     prefix: -p
-  #
-  # m:
-  #   type: ['null', int]
-  #   default: 50
-  #   doc: maximal homopolymer size for distribution analysis
-  #   inputBinding:
-  #     prefix: -m
-  #
-  # q:
-  #   type: ['null', int]
-  #   default: 3
-  #   doc: minimal microsatellites size
-  #   inputBinding:
-  #     prefix: -q
-  #
-  # s:
-  #   type: ['null', int]
-  #   default: 5
-  #   doc: minimal number of repeats in microsatellites for distribution analysis
-  #   inputBinding:
-  #     prefix: -s
-  #
-  # w:
-  #   type: ['null', int]
-  #   default: 40
-  #   doc: maximal microsatellites size for distribution analysis
-  #   inputBinding:
-  #     prefix: -w
-  #
-  # u:
-  #   type: ['null', int]
-  #   default: 500
-  #   doc: span size around window for extracting reads
-  #   inputBinding:
-  #     prefix: -u
-  #
-  # b:
-  #   type: ['null', int]
-  #   default: 2
-  #   doc: threads number for parallel computing
-  #   inputBinding:
-  #     prefix: -b
-  #
-  # x:
-  #   type: ['null', int]
-  #   default: 0
-  #   doc: output homopolymer only, 0 is no, 1 is yes
-  #   inputBinding:
-  #     prefix: -x
-  #
-  # y:
-  #   type: ['null', int]
-  #   default: 0
-  #   doc: output microsatellite only, 0 is no, 1 is yes
-  #   inputBinding:
-  #     prefix: -y
-
 outputs:
   output_file:
     type: File
     outputBinding:
-      glob: $(inputs.o)
+      glob: $(inputs.output_filename)
   dis_file:
     type: File
     outputBinding:
-      glob: $(inputs.o)_dis
+      glob: $(inputs.output_filename)_dis
   somatic_file:
     type: File
     outputBinding:
-      glob: $(inputs.o)_somatic
+      glob: $(inputs.output_filename)_somatic
+
+
+# example command;
+#    msisensor msi \
+#    -d msi_sites
+#    -n normal_bam
+#    -t tumor_bam
+#    -tumor_sample_name tumor_sample_name
+#    -normal_sample_name normal_sample_name
+#    -o ${ return inputs.tumor_sample_name +"."+inputs.normal_sample_name+".msi.txt" }
+#
+
+#
+# Program: msisensor (homopolymer and miscrosatelite analysis using bam files)
+# Version: v0.2
+# Author: Beifang Niu && Kai Ye
+#
+# Usage:   msisensor <command> [options]
+#
+# Key commands:
+#
+#  scan            scan homopolymers and miscrosatelites
+#  msi             msi scoring
+#
+#
+#
+# Singularity> msisensor msi
+#
+# Usage:  msisensor msi [options]
+#
+#        -d   <string>   homopolymer and microsates file
+#        -n   <string>   normal bam file
+#        -t   <string>   tumor  bam file
+#        -o   <string>   output distribution file
+#
+#        -e   <string>   bed file, optional
+#        -f   <double>   FDR threshold for somatic sites detection, default=0.05
+#        -c   <int>      coverage threshold for msi analysis, WXS: 20; WGS: 15, default=20
+#        -r   <string>   choose one region, format: 1:10000000-20000000
+#        -l   <int>      mininal homopolymer size, default=5
+#        -p   <int>      mininal homopolymer size for distribution analysis, default=10
+#        -m   <int>      maximal homopolymer size for distribution analysis, default=50
+#        -q   <int>      mininal microsates size, default=3
+#        -s   <int>      mininal microsates size for distribution analysis, default=5
+#        -w   <int>      maximal microstaes size for distribution analysis, default=40
+#        -u   <int>      span size around window for extracting reads, default=500
+#        -b   <int>      threads number for parallel computing, default=1
+#        -x   <int>      output homopolymer only, 0: no; 1: yes, default=0
+#        -y   <int>      output microsatellite only, 0: no; 1: yes, default=0
+#
+#        -h   help