count mendelian

codescripts/count_mendelian.py

+import pandas as pd
+import sys, argparse, os
+
+men = pd.read_table(sys.argv[1],header=None,low_memory=False)
+vote = pd.read_table(sys.argv[2],low_memory=False)
+men[1]=men[1].astype(str)
+merged_df = pd.merge(vote, men,  how='inner', left_on=['CHROM','POS'], right_on = [0,1])
+lcl5_dat = merged_df[(merged_df[5]!='./.') & (merged_df[5]!='0/0')]
+sub = lcl5_dat[['CHROM','POS','REF','ALT',4,5,6,7,8,'LCL5_consensus_calls', 'LCL5_detect_number','LCL5_same_diff',11]]
+sub['mendelian_state'] = 'MIE'
+sub.loc[sub[11]=='1:1:1','mendelian_state'] = 'MC'
+sub.columns=['CHROM','POS','REF','ALT','variant_type','LCL5','LCL6','LCL7','LCL8','LCL5_consensus_calls','LCL5_detect_number','LCL5_same_diff','mendelian_detail','mendelian_state']
+sub.to_csv(sys.argv[3],sep="\t",index=0)

codescripts/merge_mendelian_vot.py

-import pandas as pd
-import sys, argparse, os
-
-men = pd.read_table(sys.argv[1],header=None,low_memory=False)
-vote = pd.read_table(sys.argv[2],low_memory=False)
-men[1]=men[1].astype(str)
-merged_df = pd.merge(vote, men,  how='inner', left_on=['CHROM','POS'], right_on = [0,1])
-lcl5_dat = merged_df[(merged_df[5]!='./.') & (merged_df[5]!='0/0')]
-
-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']
-genotype_sub = pd.merge(sub, mut,  how='inner', left_on=["CHROM","POS"], right_on = [0,1])
-genotype_sub = genotype_sub[['CHROM','POS','detected_num','mendelian','detail',2,3]]
-genotype_sub.to_csv(sys.argv[4],header=0,sep="\t",index=0)

inputs

   "{{ project_name }}.fasta": "GRCh38.d1.vd1.fa",
   "{{ project_name }}.family_vcf": "{{ family_vcf }}",
   "{{ project_name }}.disk_size": "500",
+  "{{ project_name }}.vote_summary": "{{ vote_summary }}",
   "{{ project_name }}.SMALLcluster_config": "OnDemand bcs.ps.g.xlarge img-ubuntu-vpc",
   "{{ project_name }}.BIGcluster_config": "OnDemand bcs.a2.7xlarge img-ubuntu-vpc",
   "{{ project_name }}.MENDELIANdocker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/vbt:v1.1",
   "{{ project_name }}.DIYdocker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.4",
   "{{ project_name }}.ref_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/"
-}
+}

tasks/count_mendelian.wdl

+task count_mendelian {
+	File project_mendelian
+	File vote_summary
+	File family_vcf
+	String family_name = basename(family_vcf,".vcf")
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+
+		python /opt/count_mendelian.py ${project_mendelian} ${vote_summary} ${family_name}.mendelian.count.summary.txt
+
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File mendelian_summary = "${family_name}.mendelian.count.summary.txt"
+	}
+}

tasks/merge_mendelian.wdl

 	File D5_trio_vcf
 	File D6_trio_vcf
 	File family_vcf
-	String family_name = basename(family_vcf,".family.vcf")
+	String family_name = basename(family_vcf,".vcf")
 	String docker
 	String cluster_config
 	String disk_size

workflow.wdl

 import "./tasks/mendelian.wdl" as mendelian
 import "./tasks/merge_mendelian.wdl" as merge_mendelian
+import "./tasks/count_mendelian.wdl" as count_mendelian
 
 workflow {{ project_name }} {
 	File family_vcf
 	File ref_dir
+	File vote_summary
 	String fasta
 	String MENDELIANdocker
 	String DIYdocker
 		disk_size=disk_size
 	}
 
+	call count_mendelian.count_mendelian as count_mendelian {
+		input:
+		project_mendelian=merge_mendelian.project_mendelian,
+		vote_summary=vote_summary,
+		family_vcf=family_vcf,
+		docker=DIYdocker,
+		cluster_config=SMALLcluster_config,
+		disk_size=disk_size
+	}
 }