colsum

codescripts/colsum.py

@@ -0,0 +1,22 @@
+import pandas as pd
+import sys, argparse, os
+
+
+# input arguments
+parser = argparse.ArgumentParser(description="This script is to get column sum of all variants in SV breakpoints flanking region")
+
+parser.add_argument('-file', '--file', type=str, help='The bed annotated file',  required=True)
+parser.add_argument('-prefix', '--prefix', type=str, help='The prefix of output file',  required=True)
+
+
+args = parser.parse_args()
+file = args.file
+prefix = args.prefix
+
+
+dat = pd.read_table(file,header=None)
+dat_sub = dat.iloc[:,5:]
+dat_sum = pd.DataFrame(dat_sub.sum())
+dat_sum.columns = [prefix]
+file_name = prefix + '.sum.txt'
+dat_sum.to_csv(file_name,index=0)

inputs

@@ -1,4 +1,5 @@
 {
+  "{{ project_name }}.colSum.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.4",
   "{{ project_name }}.disk_size": "200",
   "{{ project_name }}.bedAnnotation.docker": "registry-internal.cn-shanghai.aliyuncs.com/pgx-docker-registry/bedtools:v2.27.1",
   "{{ project_name }}.inputSamplesFile": "{{ inputSamplesFile }}",

tasks/colSum.wdl

@@ -0,0 +1,50 @@
+task colSum {
+	File filtered_bnd
+	File filtered_ins
+	File filtered_inv
+	File filtered_del
+	File filtered_dup
+	File voted_bnd
+	File voted_ins
+	File voted_inv
+	File voted_del
+	File voted_dup
+	String sample_name
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+
+		python /opt/colsum.py -file ${filtered_bnd} -prefix ${sample_name}.BND.filtered
+		python /opt/colsum.py -file ${filtered_ins} -prefix ${sample_name}.INS.filtered
+		python /opt/colsum.py -file ${filtered_inv} -prefix ${sample_name}.INV.filtered
+		python /opt/colsum.py -file ${filtered_del} -prefix ${sample_name}.DEL.filtered
+		python /opt/colsum.py -file ${filtered_dup} -prefix ${sample_name}.DUP.filtered
+		python /opt/colsum.py -file ${voted_bnd} -prefix ${sample_name}.BND.voted
+		python /opt/colsum.py -file ${voted_ins} -prefix ${sample_name}.INS.voted
+		python /opt/colsum.py -file ${voted_inv} -prefix ${sample_name}.INV.voted
+		python /opt/colsum.py -file ${voted_del} -prefix ${sample_name}.DEL.voted
+		python /opt/colsum.py -file ${voted_dup} -prefix ${sample_name}.DUP.voted
+
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File filtered_bnd_sum = "${sample_name}.BND.filtered.sum.txt"
+		File filtered_ins_sum = "${sample_name}.INS.filtered.sum.txt"
+		File filtered_inv_sum = "${sample_name}.INV.filtered.sum.txt"
+		File filtered_del_sum = "${sample_name}.DEL.filtered.sum.txt"
+		File filtered_dup_sum = "${sample_name}.DUP.filtered.sum.txt"
+		File voted_bnd_sum = "${sample_name}.BND.voted.sum.txt"
+		File voted_ins_sum = "${sample_name}.INS.voted.sum.txt"
+		File voted_inv_sum = "${sample_name}.INV.voted.sum.txt"
+		File voted_del_sum = "${sample_name}.DEL.voted.sum.txt"
+		File voted_dup_sum = "${sample_name}.DUP.voted.sum.txt"
+	}
+}

workflow.wdl

@@ -1,6 +1,7 @@
 import "./tasks/vcf2bed.wdl" as vcf2bed
 import "./tasks/mergeBed.wdl" as mergeBed
 import "./tasks/bedAnnotation.wdl" as bedAnnotation
+import "./tasks/colSum.wdl" as colSum
 
 workflow {{ project_name }} {
 	File inputSamplesFile
@@ -38,4 +39,20 @@ workflow {{ project_name }} {
 		cluster_config=cluster_config,
 		disk_size=disk_size
 	}
+	call colSum.colSum as colSum {
+		input:
+		filtered_bnd=bedAnnotation.filtered_bnd,
+		filtered_ins=bedAnnotation.filtered_ins,
+		filtered_inv=bedAnnotation.filtered_inv,
+		filtered_del=bedAnnotation.filtered_del,
+		filtered_dup=bedAnnotation.filtered_dup,
+		voted_bnd=bedAnnotation.voted_bnd,
+		voted_ins=bedAnnotation.voted_ins,
+		voted_inv=bedAnnotation.voted_inv,
+		voted_del=bedAnnotation.voted_del,
+		voted_dup=bedAnnotation.voted_dup,
+		sample_name=sample_name,
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
 }