first commit

codescripts/merge_mendelian_vot.py

@@ -0,0 +1,12 @@
+import pandas as pd
+import sys, argparse, os
+
+men = pd.read_table(sys.argv[1],header=None)
+vote = pd.read_table(sys.argv[2],low_memory=False)
+
+merged_df = pd.merge(vote, men,  how='inner', left_on=['CHROM','POS'], right_on = [0,1])
+merged_df['mendelian_check'] = 'MIE'
+merged_df.loc[merged_df[2]=='1:1:1','mendelian_check'] = 'MP'
+sub = merged_df[['CHROM','POS','LCL5_detected_num','mendelian_check',2]]
+sub.columns=['CHROM','POS','detected_num','mendelian','detail']
+sub.to_csv(sys.argv[3],header=0,sep="\t",index=0)

inputs

@@ -0,0 +1,7 @@
+{
+  "{{ project_name }}.disk_size": "100",
+  "{{ project_name }}.inputSamplesFile": "{{ inputSamplesFile }}",
+  "{{ project_name }}.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.4",
+  "{{ project_name }}.sample_name": "{{ sample_name }}",
+  "{{ project_name }}.cluster_config": "OnDemand bcs.a2.xlarge img-ubuntu-vpc"
+}

tasks/merge_chromo.wdl

@@ -0,0 +1,23 @@
+task merge_chromo {
+	Array[File] mendelian_vote_summary
+	String sample_name
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+
+		cat ${sep=" " mendelian_vote_summary} > ${sample_name}.all_chromo.mendelian.vote.txt
+
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File mendelian_vote_summary_all_chromo = "${sample_name}.all_chromo.mendelian.vote.txt"
+	}
+}

tasks/merge_mendelian_vote.wdl

@@ -0,0 +1,24 @@
+task merge_mendelian_vote {
+	File vote_file
+	File mendelian_file
+	String output_prefix
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+
+		python /opt/merge_mendelian_vote.py ${mendelian_file} ${vote_file} ${output_prefix}.mendelian.vote.txt
+
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File mendelian_vote = "${output_prefix}.mendelian.vote.txt"
+	}
+}

tasks/summary_mendelian.wdl

@@ -0,0 +1,23 @@
+task summary_mendelian {
+	File mendelian_vote
+	String output_prefix
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+
+		cat ${mendelian_vote} | cut -f3,4 | sort | uniq -c > ${output_prefix}.summary.txt
+
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File mendelian_vote_summary = "${output_prefix}.summary.txt"
+	}
+}

workflow.wdl

@@ -0,0 +1,40 @@
+import "./tasks/merge_mendelian_vote.wdl" as merge_mendelian_vote
+import "./tasks/summary_mendelian.wdl" as summary_mendelian
+import "./tasks/merge_chromo.wdl" as merge_chromo
+
+workflow {{ project_name }} {
+	File inputSamplesFile
+	Array[Array[File]] inputSamples = read_tsv(inputSamplesFile)
+	String docker
+	String sample_name
+	String cluster_config
+	String disk_size
+
+	scatter (sample in inputSamples){
+		call merge_mendelian_vote.merge_mendelian_vote as merge_mendelian_vote {
+			input:
+			vote_file=sample[0],
+			mendelian_file=sample[1],
+			output_prefix=sample[2],
+			docker=docker,
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call summary_mendelian.summary_mendelian as summary_mendelian {
+			input:
+			mendelian_vote=merge_mendelian_vote.mendelian_vote,
+			output_prefix=sample[2],
+			docker=docker,
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+	}
+	call merge_chromo.merge_chromo as merge_chromo {
+		input:
+		mendelian_vote_summary=summary_mendelian.mendelian_vote_summary,
+		sample_name=sample_name,
+		docker=docker,
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+}