test

README.md

 > E-mail：yaqing.liu@outlook.com
 >
 
+CNVkit is a Python library and command-line software toolkit to infer and visualize copy number from high-throughput DNA sequencing data. It is designed for use with hybrid capture, including both whole-exome and custom target panels, and short-read sequencing platforms such as Illumina and Ion Torrent.
+
+Official document: https://cnvkit.readthedocs.io/en/stable/index.html
 ## Install
 
 ```
 	"sample_id": "..."
 }
 ```
-#### Output
+## Output
 A segment file and some intermediate *.cnn/cns will be generated, and the segment file can be imported into IGV.

defaults

 {
-    "fasta": "GRCh38.d1.vd1.fa",
-    "ref_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/",
+    "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",
     "docker": "registry.cn-hangzhou.aliyuncs.com/pgx-docker-registry/cnvkit:0.9.7",
     "disk_size": "200",
     "cluster_config": "OnDemand bcs.a2.3xlarge img-ubuntu-vpc",

inputs

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

tasks/access.wdl

 task access {
-    File ref_dir
-    String fasta
+    File fasta
+    File fai
     String docker
 	String cluster_config
 	String disk_size
 
     command <<<
-		cnvkit.py access -s 5000 -o access-5kb-mappable.hg38.bed ${ref_dir}/${fasta}
+		cnvkit.py access -s 5000 -o access-5kb-mappable.hg38.bed ${fasta}
     >>>
    
     runtime {

tasks/batch.wdl

     Array[File] normal_bam
     Array[File] normal_bai
     File bed
-    File ref_dir
-    String fasta
+    File fasta
+    File fai
     File access_bed
     String docker
 	String cluster_config
 
         cnvkit.py batch ${sep=' ' tumor_bam} --normal ${sep=' ' normal_bam} \
         --targets ${bed} \
-        --fasta ${ref_dir}/${fasta} --access ${access_bed} \
+        --fasta ${fasta} --access ${access_bed} \
         --output-reference my_reference.cnn --output-dir ./results/ \
         --diagram --scatter
     >>>

workflow.wdl

     Array[File] normal_bam
     Array[File] normal_bai
     File bed
-    File ref_dir
-    String fasta
+    File fasta
+	File fai
 	String docker
     String cluster_config
     String disk_size