vcf2maf

README.md

@@ -0,0 +1,26 @@
+### VEP (Variant Effect Predictor)
+VEP predicts the functional effects of genomic variants. The annotated VCF will be converted into MAF based on vcf2maf.
+
+### Getting Started
+
+We recommend using choppy system and Aliyun OSS service. The command will look like this:
+
+```
+# Activate the choppy environment
+$ open-choppy-env
+
+# Install the APP
+$ choppy install YaqingLiu/VEP [-f]
+
+# List the parameters
+$ choppy samples YaqingLiu/VEP-latest [--no-default]
+
+# Submit you task with the `samples.csv file` and `project name`
+$ choppy batch YaqingLiu/VEP-latest samples.csv -p Project [-l project:Label]
+
+# Query the status of all tasks in the project
+$ choppy query -L project:Label | grep "status"
+```
+### Output
+
+There are two files: .vep.vcf and .maf

defaults

@@ -0,0 +1,11 @@
+{
+  "vep_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/vep:v104.0",
+  "fasta": "GRCh38.d1.vd1.fa",
+  "ref_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/",
+  "cache": "oss://pgx-reference-data/ensembl_vep/cache/",
+  "vep_path": "/opt/vep/ensembl-vep",
+  "species": "homo_sapiens_merged",
+  "ncbi_build": "GRCh38",
+  "disk_size": "200",
+  "cluster_config": "OnDemand bcs.a2.3xlarge img-ubuntu-vpc"
+}

inputs

@@ -0,0 +1,15 @@
+{
+  "{{ project_name }}.vcf": "{{ vcf }}",
+  "{{ project_name }}.sample_id": "{{ sample_id }}",
+  "{{ project_name }}.tumor_id": "{{ tumor_id }}",
+  "{{ project_name }}.normal_id": "{{ normal_id }}",
+  "{{ project_name }}.ref_dir": "{{ ref_dir }}",
+  "{{ project_name }}.fasta": "{{ fasta }}",
+  "{{ project_name }}.vep_path": "{{ vep_path }}",
+  "{{ project_name }}.cache": "{{ cache }}",
+  "{{ project_name }}.ncbi_build": "{{ ncbi_build }}",
+  "{{ project_name }}.species": "{{ species }}",
+  "{{ project_name }}.vep_docker": "{{ vep_docker }}",
+  "{{ project_name }}.disk_size": "{{ disk_size }}",
+  "{{ project_name }}.cluster_config": "{{ cluster_config }}"
+}

tasks/vcf2maf.wdl

@@ -0,0 +1,44 @@
+task vcf2maf {
+
+  File vcf
+  String basename = basename(vcf,".vcf")
+  String tumor_id
+  String normal_id
+	File ref_dir
+	String fasta
+  String vep_path
+  File cache
+  String ncbi_build
+  String species
+  String docker
+  String cluster_config
+  String disk_size
+
+
+  command <<<
+    set -o pipefail
+    set -e
+    nt=$(nproc)    
+    perl /opt/mskcc-vcf2maf/vcf2maf.pl \
+    --input-vcf ${vcf} --output-maf ${basename}.maf \
+    --tumor-id ${tumor_id} --normal-id ${normal_id} \
+    --ref-fasta ${ref_dir}/${fasta} \
+    --vep-path ${vep_path} \
+    --vep-data ${cache} \
+    --ncbi-build ${ncbi_build} \
+    --species ${species} \
+    --vep-fork $nt
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+
+  output {
+    File vep_vcf = "${basename}.vep.vcf"
+    File maf = "${basename}.maf"
+  }
+}

workflow.wdl

@@ -0,0 +1,34 @@
+import "./tasks/vcf2maf.wdl" as vcf2maf
+
+workflow {{ project_name }} {
+	
+  File vcf
+  String sample_id
+  String tumor_id
+  String normal_id
+	File ref_dir
+	String fasta
+  String vep_path
+  File cache
+  String ncbi_build
+  String species
+  String vep_docker
+  String cluster_config
+  String disk_size
+
+	call vcf2maf.vcf2maf as vcf2maf {
+		input: 
+		vcf=vcf,
+    tumor_id=tumor_id,
+    normal_id=normal_id,
+    ref_dir=ref_dir,
+    fasta=fasta,
+    vep_path=vep_path,
+    cache=cache,
+    ncbi_build=ncbi_build,
+    species=species,
+		docker=vep_docker,
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+}