alter batch.wdl output, and defaults

defaults

@@ -1,8 +1,8 @@
 {
-    "fasta": "oss://pgx-reference-data/GRCh38.d1.vd1/GRCh38.d1.vd1.fa",
-    "fai": "oss://pgx-reference-data/GRCh38.d1.vd1/GRCh38.d1.vd1.fa.fai",
+    "fasta": "GRCh38.d1.vd1.fa",
+    "ref_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/",
     "docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/cnvkit:0.9.7",
-    "disk_size": "200",
-    "cluster_config": "OnDemand bcs.a2.3xlarge img-ubuntu-vpc",
+    "disk_size": "400",
+    "cluster_config": "OnDemand bcs.a2.7xlarge img-ubuntu-vpc",
     "bed": "oss://pgx-reference-data/reference/wes_bedfiles/agilent_v6/SureSelect_Human_All_Exon_V6_r2.bed"
 }

inputs

@@ -5,7 +5,7 @@
   "{{ project_name }}.tumor_bam": {{ tumor_bam | tojson }},
   "{{ project_name }}.tumor_bai": {{ tumor_bai | tojson }},
   "{{ project_name }}.fasta": "{{ fasta }}",
-  "{{ project_name }}.fai": "{{ fai }}",
+  "{{ project_name }}.ref_dir": "{{ ref_dir }}",
   "{{ project_name }}.docker": "{{ docker }}",
   "{{ project_name }}.bed": "{{ bed }}",
   "{{ project_name }}.disk_size": "{{ disk_size }}",

tasks/access.wdl

@@ -1,21 +1,21 @@
 task access {
-    File fasta
-    File fai
+	  File ref_dir
+	  String fasta
     String docker
-	String cluster_config
-	String disk_size
+    String cluster_config
+    String disk_size
 
     command <<<
-		cnvkit.py access -s 5000 -o access-5kb-mappable.hg38.bed ${fasta}
+        cnvkit.py access -s 5000 -o access-5kb-mappable.hg38.bed ${ref_dir}/${fasta}
     >>>
-   
+
     runtime {
-		docker: docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+        docker: docker
+        cluster: cluster_config
+        systemDisk: "cloud_ssd 40"
+        dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
     }
-
+    
     output {
         File access_bed = "access-5kb-mappable.hg38.bed"
     }

tasks/batch.wdl

@@ -5,37 +5,38 @@ task batch {
     Array[File] normal_bam
     Array[File] normal_bai
     File bed
-    File fasta
-    File fai
+    File ref_dir
+    String fasta
     File access_bed
     String docker
-	String cluster_config
-	String disk_size
+    String cluster_config
+    String disk_size
 
     command <<<
-	    set -o pipefail
+        set -o pipefail
         set -e
         mkdir -p /cromwell_root/tmp/cnvkit
-		cp ${sep=' ' normal_bai} /cromwell_root/tmp/cnvkit
+        cp ${sep=' ' normal_bai} /cromwell_root/tmp/cnvkit
         cp ${sep=' ' tumor_bai} /cromwell_root/tmp/cnvkit
-		cd /cromwell_root/tmp/cnvkit
-
+        cd /cromwell_root/tmp/cnvkit
+        
+        mkdir results
         cnvkit.py batch ${sep=' ' tumor_bam} --normal ${sep=' ' normal_bam} \
         --targets ${bed} \
-        --fasta ${fasta} --access ${access_bed} \
-        --output-reference my_reference.cnn --output-dir ./results/ \
+        --fasta ${ref_dir}/${fasta} --access ${access_bed} \
+        --output-reference ${sample_id}.reference.cnn --output-dir /cromwell_root/tmp/cnvkit/results/ \
         --diagram --scatter
     >>>
 
     runtime { 
-		docker: docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+        docker: docker
+        cluster: cluster_config
+        systemDisk: "cloud_ssd 40"
+        dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
     }
 
     output {
-        File reference_cnn = "my_reference.cnn"
-        Array[File] result = glob("result/*")
+        File reference_cnn = "${sample_id}.reference.cnn"
+        Array[File] results = glob("/cromwell_root/tmp/cnvkit/results/*")
     }
 }

tasks/export.wdl

@@ -1,25 +1,26 @@
 task export{
-    Array[File] result
+    String sample_id
+    Array[File] results
     String docker
     String cluster_config
     String disk_size
 
     command <<<
-		mkdir -p /cromwell_root/tmp/cnvkit
-		cp -r ${sep=" " result} /cromwell_root/tmp/cnvkit
-		cd /cromwell_root/tmp/cnvkit
-		# this version app just provides seg
-		cnvkit.py export seg ./results/*.cns -o samples.seg
+		    mkdir -p /cromwell_root/tmp/cnvkit
+		    cp -r ${sep=" " results} /cromwell_root/tmp/cnvkit
+		    cd /cromwell_root/tmp/cnvkit
+		    # this version app just provides seg
+		    cnvkit.py export seg *.cns -o ${sample_id}.seg
     >>>
    
     runtime { 
-		docker: docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+		    docker: docker
+		    cluster: cluster_config
+		    systemDisk: "cloud_ssd 40"
+		    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
     }
 
     output {
-        File seg = "samples.seg"
+        File seg = "${sample_id}.seg"
     }
 }

workflow.wdl

@@ -9,8 +9,8 @@ workflow {{ project_name }} {
     Array[File] normal_bam
     Array[File] normal_bai
     File bed
-    File fasta
-    File fai
+	File ref_dir
+	String fasta
     String docker
     String cluster_config
     String disk_size
@@ -18,7 +18,7 @@ workflow {{ project_name }} {
     call access.access as access {
         input: 
         fasta=fasta,
-        fai=fai,
+        ref_dir=ref_dir,
         docker = docker,
         cluster_config = cluster_config,
         disk_size = disk_size
@@ -28,7 +28,7 @@ workflow {{ project_name }} {
         input: 
         sample_id = sample_id,
         fasta=fasta,
-        fai=fai,
+        ref_dir=ref_dir,
         tumor_bam = tumor_bam,
         tumor_bai = tumor_bai,
         normal_bam = normal_bam,
@@ -42,7 +42,8 @@ workflow {{ project_name }} {
 
     call export.export as export {
         input:
-        result = batch.result,
+        sample_id = sample_id,
+        results = batch.results,
         docker = docker,
         cluster_config = cluster_config,
         disk_size = disk_size