Remove old sample output. Update sample output. Add Docker hints. Rem…

…ove ENTRYPOINT.
stjude · Nov 17, 2023 · ec820d6 · ec820d6
1 parent 560b8ec
commit ec820d6
Show file tree

Hide file tree

Showing 48 changed files with 217 additions and 146 deletions.
diff --git a/Dockerfile b/Dockerfile
@@ -99,6 +99,4 @@ COPY --chmod=755 --from=builder /opt/picard /opt/picard
 COPY --chmod=755 --from=builder /opt/xenocp /opt/xenocp
 COPY --chmod=755 --from=builder /opt/xenocp/bin/* /usr/local/bin/
 
-COPY --chmod=755  cwl /opt/xenocp/cwl
-
-ENTRYPOINT ["cwl-runner", "--parallel", "--outdir", "results", "--no-container", "/opt/xenocp/cwl/xenocp.cwl"]
+COPY --chmod=755  cwl /opt/xenocp/cwl
diff --git a/README.md b/README.md
@@ -186,8 +186,8 @@ $ docker build --tag xenocp .
 
 The Docker image uses `cwl-runner cwl/xenocp.cwl` as its entrypoint.
 
-The image assumes three working directories: `/data` for inputs, `/references` for
-reference files, and `/results` for outputs. `/data` and `/references` can be
+The image assumes three working directories: `/data` for inputs, `/reference` for
+reference files, and `/results` for outputs. `/data` and `/reference` can be
 read-only, where as `/results` needs write access.
 
 The paths given in the input parameters file must be from inside the
@@ -197,7 +197,10 @@ container, not the host, e.g.,
 bam:
   class: File
   path: /data/sample.bam
-ref_db_prefix: /reference/ref.fa
+ref_db_prefix: ref.fa
+index:
+  class: Directory
+  path: /reference
 aligner: "bwa aln"
 ```
 
@@ -213,6 +216,11 @@ $ docker run \
   --mount type=bind,source=/path/to/reference,target=/reference,readonly \
   --mount type=bind,source=$(pwd)/results,target=/results \
   xenocp \
+  cwl-runner \
+  --parallel \
+  --outdir results \
+  --no-container \
+  /opt/xenocp/cwl/xenocp.cwl \
   /data/inputs.yml
 ```
 

diff --git a/cwl/bwa_alignse_onlymapped.cwl b/cwl/bwa_alignse_onlymapped.cwl
@@ -11,12 +11,18 @@ hints:
         specs: ["bwa aln", "bwa samse"]
       tweak_sam:
         specs: ["java.sh org.stjude.compbio.sam.TweakSam"]
+  DockerRequirement:
+    dockerPull: "ghcr.io/stjude/xenocp:latest"
 
 inputs:
   ref_db_prefix: 
     type: string
     inputBinding:
         position: 1
+        valueFrom: |
+          ${
+            return inputs.index.path + "/" + self;
+          }
   input_fastq:
     type: File
     inputBinding:
@@ -26,6 +32,8 @@ inputs:
     label: Must be an output bam file name, not an absolute path
     inputBinding:
         position: 3
+  index:
+    type: Directory
 
 outputs:
     bam:

diff --git a/cwl/bwa_mem_onlymapped.cwl b/cwl/bwa_mem_onlymapped.cwl
@@ -11,6 +11,8 @@ hints:
         specs: ["bwa mem"]
       tweak_sam:
         specs: ["java.sh org.stjude.compbio.sam.TweakSam"]
+  DockerRequirement:
+    dockerPull: "ghcr.io/stjude/xenocp:latest"
 
 requirements:
   ResourceRequirement:
@@ -22,6 +24,10 @@ inputs:
     type: string
     inputBinding:
         position: 1
+        valueFrom: |
+          ${
+            return inputs.index.path + "/" + self;
+          }
   input_fastq:
     type: File
     inputBinding:
@@ -31,6 +37,8 @@ inputs:
     label: Must be an output bam file name, not an absolute path
     inputBinding:
         position: 3
+  index:
+    type: Directory
 
 outputs:
     bam:

diff --git a/cwl/cat.cwl b/cwl/cat.cwl
@@ -6,7 +6,11 @@ doc: |
   Merge a set of files into file using the cat utility.
 
 requirements:
- - class: InlineJavascriptRequirement
+  InlineJavascriptRequirement: {}
+
+hints:
+  DockerRequirement:
+    dockerPull: "ghcr.io/stjude/xenocp:latest"
 
 baseCommand: cat
 

diff --git a/cwl/create_contam_lists.cwl b/cwl/create_contam_lists.cwl
@@ -9,6 +9,8 @@ hints:
     packages:
       create_contam_list:
         specs: [ "java.sh org.stjude.compbio.xenocp.CreateContamLists" ]
+  DockerRequirement:
+    dockerPull: "ghcr.io/stjude/xenocp:latest"
 
 inputs:
   input_bam:

diff --git a/cwl/extract.cwl b/cwl/extract.cwl
@@ -37,6 +37,9 @@ steps:
     out: [out_bam]
     run: 
       class: CommandLineTool
+      hints:
+        DockerRequirement:
+          dockerPull: "ghcr.io/stjude/xenocp:latest"
       stdout: other.bam
       inputs: 
         bam: 
@@ -62,6 +65,9 @@ steps:
     scatter: chroms
     run:
       class: CommandLineTool
+      hints:
+        DockerRequirement:
+          dockerPull: "ghcr.io/stjude/xenocp:latest"
       inputs:
         chroms:
           type: string
@@ -88,6 +94,9 @@ steps:
    out: [unmapped_bam]
    run: 
      class: CommandLineTool
+     hints:
+        DockerRequirement:
+          dockerPull: "ghcr.io/stjude/xenocp:latest"
      stdout: unmapped.bam
      inputs: 
        bam: 

diff --git a/cwl/get_chroms.cwl b/cwl/get_chroms.cwl
@@ -7,6 +7,8 @@ hints:
     packages:
       bam_to_chr:
         specs: ["bam_to_chrs.sh"]
+  DockerRequirement:
+    dockerPull: "ghcr.io/stjude/xenocp:latest"
 
 baseCommand: bam_to_chrs.sh
 

diff --git a/cwl/merge_markdup_index.cwl b/cwl/merge_markdup_index.cwl
@@ -10,6 +10,10 @@ doc: |
 requirements:
  - class: InlineJavascriptRequirement
 
+hints:
+  DockerRequirement:
+    dockerPull: "ghcr.io/stjude/xenocp:latest"
+
 baseCommand: merge_markdup_index.sh
 
 inputs:

diff --git a/cwl/qc_bam.cwl b/cwl/qc_bam.cwl
@@ -10,6 +10,8 @@ hints:
     packages:
       qclib:
         specs: ["qclib.sh"]
+  DockerRequirement:
+    dockerPull: "ghcr.io/stjude/xenocp:latest"
 
 inputs:
   bam:

diff --git a/cwl/sort_flagstat.cwl b/cwl/sort_flagstat.cwl
@@ -18,6 +18,8 @@ hints:
       samtools:
         specs: ["samtools flagstat"]
         version: ["1.3.1"]
+  DockerRequirement:
+    dockerPull: "ghcr.io/stjude/xenocp:latest"
 
 inputs:
   input_bam:

diff --git a/cwl/split_sam.cwl b/cwl/split_sam.cwl
@@ -9,6 +9,8 @@ hints:
     packages:
       SplitSam:
         specs: [ "SplitSam.java" ]
+  DockerRequirement:
+    dockerPull: "ghcr.io/stjude/xenocp:latest"
 
 inputs:
   suffix_length:

diff --git a/cwl/star_onlymapped.cwl b/cwl/star_onlymapped.cwl
@@ -16,12 +16,14 @@ hints:
         specs: ["STAR"]
       tweak_sam:
         specs: ["java.sh org.stjude.compbio.sam.TweakSam"]
+  DockerRequirement:
+    dockerPull: "ghcr.io/stjude/xenocp:latest"
 
 inputs:
   ref_db_prefix: 
     type: string
     inputBinding:
-        position: 1
+        position: 4
   input_fastq:
     type: File
     inputBinding:
@@ -31,6 +33,10 @@ inputs:
     label: Must be an output bam file name, not an absolute path
     inputBinding:
         position: 3
+  index:
+    type: Directory
+    inputBinding:
+        position: 1
 
 outputs:
     bam:

diff --git a/cwl/tweak_sam.cwl b/cwl/tweak_sam.cwl
@@ -9,6 +9,8 @@ hints:
     packages:
       create_contam_list:
         specs: [ "java.sh org.stjude.compbio.sam.TweakSam" ]
+  DockerRequirement:
+    dockerPull: "ghcr.io/stjude/xenocp:latest"
 
 inputs:
   input_bam:

diff --git a/cwl/view_awk_picard.cwl b/cwl/view_awk_picard.cwl
@@ -15,6 +15,8 @@ hints:
       samtools:
         specs: ["samtools view"]
         version: ["1.3.1"]
+  DockerRequirement:
+    dockerPull: "ghcr.io/stjude/xenocp:latest"
 
 inputs:
   input_bam:

diff --git a/cwl/xenocp.cwl b/cwl/xenocp.cwl
@@ -23,6 +23,8 @@ inputs:
       type: enum
       symbols: ["bwa aln", "bwa mem", "star"]
       name: aligner
+  index:
+    type: Directory
   # See doc in split_sam.cwl for the meaning of the following arguments
   suffix_length:
     type: int?
@@ -84,6 +86,7 @@ steps:
     in:
       aligner: aligner
       ref_db_prefix: ref_db_prefix
+      index: index
       input_fastq: mapped-fastq/fastq
       output_bam:
         valueFrom: $(inputs.input_fastq.nameroot).contam.bam
@@ -101,6 +104,7 @@ steps:
     in:
       aligner: aligner
       ref_db_prefix: ref_db_prefix
+      index: index
       input_fastq: mapped-fastq/fastq
       output_bam:
         valueFrom: $(inputs.input_fastq.nameroot).contam.bam
@@ -118,6 +122,7 @@ steps:
     in:
       aligner: aligner
       ref_db_prefix: ref_db_prefix
+      index: index
       input_fastq: mapped-fastq/fastq
       output_bam:
         valueFrom: $(inputs.input_fastq.nameroot).contam.bam
@@ -160,7 +165,7 @@ steps:
     out: [cleaned_bam]
 
   # Step05b: sort tie BAMs prior to merge
-  sort-bams:
+  sort_tie_bams:
     run: bio-cwl-tools:picard/picard_SortSam.cwl
     in:
       alignments: contamination/output_tie_bam
@@ -190,7 +195,7 @@ steps:
     run: merge_markdup_index.cwl
     in:
       input_bams:
-        source: [cleanse/cleaned_bam, split/unmapped]
+        source: sort_tie_bams/sorted_alignments
         linkMerge: merge_flattened
       output_bam:
         source: bam

diff --git a/sample_data/input_data/inputs.yml b/sample_data/input_data/inputs.yml
@@ -1,5 +1,8 @@
 bam:
   class: File
   path: /data/SJRB001_X.subset.bam
-ref_db_prefix: /reference/MGSCv37/MGSCv37.fa
+ref_db_prefix: MGSCv37.fa
+index:
+  class: Directory
+  path: /reference/MGSCv37
 aligner: "bwa aln"
diff --git a/sample_data/input_data/inputs_local.yml b/sample_data/input_data/inputs_local.yml
@@ -1,5 +1,8 @@
 bam:
   class: File
   path: SJRB001_X.subset.bam
-ref_db_prefix: /path/to/reference
+ref_db_prefix: MGSCv37.fa
+index:
+  class: Directory
+  path: ../../reference/MGSCv37
 aligner: "bwa aln"