Merge pull request #1 from CancerCollaboratory/feature/cwl1

Feature/cwl1
CancerCollaboratory · Sep 14, 2016 · bf66d35 · bf66d35
2 parents 9c8fb9b + b0826c1
commit bf66d35
Show file tree

Hide file tree

Showing 2 changed files with 148 additions and 167 deletions.
diff --git a/Dockstore.cwl b/Dockstore.cwl
@@ -2,225 +2,204 @@
 
 class: CommandLineTool
 
-description: |
-  Move annotations from one assembly to another
-
-  usage:
-     liftOver oldFile map.chain newFile unMapped
-  oldFile and newFile are in bed format by default, but can be in GFF and
-  maybe eventually others with the appropriate flags below.
-  The map.chain file has the old genome as the target and the new genome
-  as the query.
-
-  ***********************************************************************
-  WARNING: liftOver was only designed to work between different
-           assemblies of the same organism. It may not do what you want
-           if you are lifting between different organisms. If there has
-           been a rearrangement in one of the species, the size of the
-           region being mapped may change dramatically after mapping.
-  ***********************************************************************
-
 dct:contributor:
   foaf:name: Andy Yang
-  foaf:mbox: "mailto:ayang@oicr.on.ca"
-
+  foaf:mbox: mailto:[email protected]
 dct:creator:
-  "@id": "http://orcid.org/0000-0001-9102-5681"
-  foaf:name: "Andrey Kartashov"
-  foaf:mbox: "mailto:Andrey.Kartashov@cchmc.org"
-
-dct:description: "Developed at Cincinnati Children’s Hospital Medical Center for the CWL consortium http://commonwl.org/ Original URL: https://github.com/common-workflow-language/workflows"
-
-cwlVersion: draft-3
+  '@id': http://orcid.org/0000-0001-9102-5681
+  foaf:name: Andrey Kartashov
+  foaf:mbox: mailto:[email protected]
+dct:description: 'Developed at Cincinnati Children’s Hospital Medical Center for the
+  CWL consortium http://commonwl.org/ Original URL: https://github.com/common-workflow-language/workflows'
+cwlVersion: v1.0
 
 requirements:
-  - class: DockerRequirement
-    dockerPull: "quay.io/cancercollaboratory/dockstore-tool-liftover"
-
+- class: DockerRequirement
+  dockerPull: quay.io/cancercollaboratory/dockstore-tool-liftover:1.0
 inputs:
-  - id: "#oldFile"
-    type: File
-    inputBinding:
-      position: 2
-
-  - id: "#mapChain"
-    type: File
-    description: |
-      The map.chain file has the old genome as the target and the new genome
-      as the query.
-    inputBinding:
-      position: 3
-
-  - id: "#newFile"
-    type: string
-    inputBinding:
-      position: 4
-
-  - id: "#unMapped"
-    type: string
-    inputBinding:
-      position: 5
-
-  - id: "#gff"
-    type: ["null",boolean]
-    description: |
-      File is in gff/gtf format.  Note that the gff lines are converted
-       separately.  It would be good to have a separate check after this
-       that the lines that make up a gene model still make a plausible gene
-       after liftOver
+  genePred:
+    type: boolean?
     inputBinding:
       position: 1
-      prefix: "-gff"
-
-  - id: "#genePred"
-    type: ["null",boolean]
-    description: |
+      prefix: -genePred
+    doc: |
       File is in genePred format
+  multiple:
+    type: boolean?
     inputBinding:
       position: 1
-      prefix: "-genePred"
-
-  - id: "#sample"
-    type: ["null",boolean]
-    description: |
-      File is in sample format
+      prefix: -multiple
+    doc: |
+      Allow multiple output regions
+  tab:
+    type: boolean?
     inputBinding:
       position: 1
-      prefix: "-sample"
-
-  - id: "#bedPlus"
-    type: ["null",int]
-    description: |
-      =N - File is bed N+ format
+      prefix: -tab
+  ends:
+    type: int?
     inputBinding:
       separate: false
       position: 1
-      prefix: "-bedPlus="
-
-  - id: "#positions"
-    type: ["null",boolean]
-    description: |
+      prefix: -ends=
+    doc: |
+      =N - Lift the first and last N bases of each record and combine the
+               result. This is useful for lifting large regions like BAC end pairs.
+  positions:
+    type: boolean?
+    inputBinding:
+      position: 1
+      prefix: -positions
+    doc: |
       File is in browser "position" format
+  chainTable:
+    type: string?
     inputBinding:
       position: 1
-      prefix: "-positions"
-
-  - id: "#hasBin"
-    type: ["null",boolean]
-    description: |
-      File has bin value (used only with -bedPlus)
+      prefix: -chainTable
+    doc: |
+      Min matching region size in query with -multiple.
+  fudgeThick:
+    type: boolean?
     inputBinding:
       position: 1
-      prefix: "-hasBin"
-
-  - id: "#minMatch"
-    type: ["null",int]
-    description: |
-      -minMatch=0.N Minimum ratio of bases that must remap. Default 0.95
+      prefix: -fudgeThick
+    doc: |
+      (bed 12 or 12+ only) If thickStart/thickEnd is not mapped,
+                    use the closest mapped base.  Recommended if using
+                    -minBlocks.
+  hasBin:
+    type: boolean?
     inputBinding:
-      separate: false
       position: 1
-      prefix: "-minMatch="
-
-  - id: "#tab"
-    type: ["null",boolean]
+      prefix: -hasBin
+    doc: |
+      File has bin value (used only with -bedPlus)
+  minChainQ:
+    type: int?
     inputBinding:
       position: 1
-      prefix: "-tab"
-
-  - id: "#pslT"
-    type: ["null",boolean]
-    description: |
-      File is in psl format, map target side only
+      prefix: -minChainQ
+    doc: |
+      Minimum chain size in target/query, when mapping
+                             to multiple output regions (default 0, 0)
+  sample:
+    type: boolean?
     inputBinding:
       position: 1
-      prefix: "-pslT"
-
-  - id: "#ends"
-    type: ["null",int]
-    description: |
-      =N - Lift the first and last N bases of each record and combine the
-               result. This is useful for lifting large regions like BAC end pairs.
+      prefix: -sample
+    doc: |
+      File is in sample format
+  minChainT:
+    type: int?
     inputBinding:
-      separate: false
       position: 1
-      prefix: "-ends="
-
-  - id: "#minBlocks"
-    type: ["null",int]
-    description: |
-      .N Minimum ratio of alignment blocks or exons that must map
-                    (default 1.00)
+      prefix: -minChainT
+    doc: |
+      Minimum chain size in target/query, when mapping
+                             to multiple output regions (default 0, 0)
+  minSizeQ:
+    type: int?
     inputBinding:
-      separate: false
       position: 1
-      prefix: "-minBlocks="
+      prefix: -minSizeQ
+    doc: |
+      Min matching region size in query with -multiple.
+  oldFile:
+    type: File
+    inputBinding:
+      position: 2
 
-  - id: "#fudgeThick"
-    type: ["null",boolean]
-    description: |
-      (bed 12 or 12+ only) If thickStart/thickEnd is not mapped,
-                    use the closest mapped base.  Recommended if using
-                    -minBlocks.
+  unMapped:
+    type: string
     inputBinding:
-      position: 1
-      prefix: "-fudgeThick"
+      position: 5
 
-  - id: "#multiple"
-    type: ["null",boolean]
-    description: |
-      Allow multiple output regions
+  mapChain:
+    type: File
     inputBinding:
-      position: 1
-      prefix: "-multiple"
+      position: 3
 
-  - id: "#minChainT"
-    type: ["null",int]
-    description: |
-      Minimum chain size in target/query, when mapping
-                             to multiple output regions (default 0, 0)
+    doc: |
+      The map.chain file has the old genome as the target and the new genome
+      as the query.
+  pslT:
+    type: boolean?
     inputBinding:
       position: 1
-      prefix: "-minChainT"
-
-  - id: "#minChainQ"
-    type: ["null",int]
-    description: |
-      Minimum chain size in target/query, when mapping
-                             to multiple output regions (default 0, 0)
+      prefix: -pslT
+    doc: |
+      File is in psl format, map target side only
+  minMatch:
+    type: int?
     inputBinding:
+      separate: false
       position: 1
-      prefix: "-minChainQ"
-
-  - id: "#minSizeQ"
-    type: ["null",int]
-    description: |
-      Min matching region size in query with -multiple.
+      prefix: -minMatch=
+    doc: |
+      -minMatch=0.N Minimum ratio of bases that must remap. Default 0.95
+  gff:
+    type: boolean?
     inputBinding:
       position: 1
-      prefix: "-minSizeQ"
-
-  - id: "#chainTable"
-    type: ["null",string]
-    description: |
-      Min matching region size in query with -multiple.
+      prefix: -gff
+    doc: |
+      File is in gff/gtf format.  Note that the gff lines are converted
+       separately.  It would be good to have a separate check after this
+       that the lines that make up a gene model still make a plausible gene
+       after liftOver
+  minBlocks:
+    type: int?
     inputBinding:
+      separate: false
       position: 1
-      prefix: "-chainTable"
-
+      prefix: -minBlocks=
+    doc: |
+      .N Minimum ratio of alignment blocks or exons that must map
+                    (default 1.00)
+  bedPlus:
+    type: int?
+    inputBinding:
+      separate: false
+      position: 1
+      prefix: -bedPlus=
+    doc: |
+      =N - File is bed N+ format
+  newFile:
+    type: string
+    inputBinding:
+      position: 4
 
 outputs:
-  - id: "#output"
+  output:
     type: File
-    description: "The sorted file"
     outputBinding:
       glob: $(inputs.newFile)
 
-  - id: "#unMappedFile"
+    doc: The sorted file
+  unMappedFile:
     type: File
-    description: "The sorted file"
     outputBinding:
       glob: $(inputs.unMapped)
 
 
-baseCommand: ["liftOver"]
+    doc: The sorted file
+baseCommand: [liftOver]
+doc: |
+  Move annotations from one assembly to another
+
+  usage:
+     liftOver oldFile map.chain newFile unMapped
+  oldFile and newFile are in bed format by default, but can be in GFF and
+  maybe eventually others with the appropriate flags below.
+  The map.chain file has the old genome as the target and the new genome
+  as the query.
+
+  ***********************************************************************
+  WARNING: liftOver was only designed to work between different
+           assemblies of the same organism. It may not do what you want
+           if you are lifting between different organisms. If there has
+           been a rearrangement in one of the species, the size of the
+           region being mapped may change dramatically after mapping.
+  ***********************************************************************
+
diff --git a/readme.md b/readme.md
@@ -12,3 +12,5 @@ cwltool (1.0.20160712154127)
 schema-salad (1.14.20160708181155)
 setuptools (25.1.6)
 ```
+
+Tested on Dockstore version 1.0-rc.2