summary numbers

codescripts/merge_mendelian_vot.py

@@ -3,10 +3,13 @@ import sys, argparse, os
 
 men = pd.read_table(sys.argv[1],header=None)
 vote = pd.read_table(sys.argv[2],low_memory=False)
+mut = pd.read_table(sys.argv[3],header=None)
 
 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)
+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

@@ -3,5 +3,6 @@
   "{{ 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"
-}
+  "{{ project_name }}.cluster_config": "OnDemand bcs.a2.xlarge img-ubuntu-vpc",
+  "{{ project_name }}.mut_file": "{{ mut_file }}",
+}

tasks/merge_chromo.wdl

@@ -1,5 +1,6 @@
 task merge_chromo {
-	Array[File] mendelian_vote_summary
+	Array[File] mendelian_vote_snv
+	Array[File] mendelian_vote_indel
 	String sample_name
 	String docker
 	String cluster_config
@@ -7,9 +8,13 @@ task merge_chromo {
 	
 	command <<<
 
-		paste ${sep=" " mendelian_vote_summary} > ${sample_name}.all_chromo.mendelian.vote.txt
+		cat ${sep=" " mendelian_vote_snv} > ${sample_name}.snv.txt
 
-		paste ${sep=" " mendelian_vote_summary} > ${sample_name}.colnames 
+		cat ${sep=" " mendelian_vote_indel} > ${sample_name}.indel
+
+		cat ${sample_name}.snv |  cut -f3,4 | sort | uniq -c > ${sample_name}.snv.summary.txt
+
+		cat ${sample_name}.indel |  cut -f3,4 | sort | uniq -c > ${sample_name}.indel.summary.txt
 
 	>>>
 
@@ -20,7 +25,9 @@ task merge_chromo {
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File mendelian_vote_summary_all_chromo = "${sample_name}.all_chromo.mendelian.vote.txt"
-		File colnames = "${sample_name}.colnames"
+		File mendelian_vote_summary_snv = "${sample_name}.snv.summary.txt"
+		File mendelian_vote_summary_indel = "${sample_name}.indel.summary.txt"
+		File mendelian_vote_summary_snv_detail = "${sample_name}.snv.txt"
+		File mendelian_vote_summary_indel_detail = "${sample_name}.indel.txt"
 	}
 }

tasks/merge_mendelian_vote.wdl

@@ -1,6 +1,7 @@
 task merge_mendelian_vote {
 	File vote_file
 	File mendelian_file
+	File mut_file
 	String output_prefix
 	String docker
 	String cluster_config
@@ -8,7 +9,11 @@ task merge_mendelian_vote {
 	
 	command <<<
 
-		python /opt/merge_mendelian_vote.py ${mendelian_file} ${vote_file} ${output_prefix}.mendelian.vote.txt
+		python /opt/merge_mendelian_vote.py ${mendelian_file} ${vote_file} ${mut_file} ${output_prefix}.mendelian.vote.txt
+
+		${output_prefix}.mendelian.vote.txt | awk '{ if ((length($6) < 51) || (length($7) < 51)) { print } }' > ${output_prefix}.snv
+
+		${output_prefix}.mendelian.vote.txt | awk '{ if ((length($6) > 50) || (length($7) > 50)) { print } }' > ${output_prefix}.indel		
 
 	>>>
 
@@ -20,5 +25,7 @@ task merge_mendelian_vote {
 	}
 	output {
 		File mendelian_vote = "${output_prefix}.mendelian.vote.txt"
+		File mendelian_vote_snv = "${output_prefix}.snv"
+		File mendelian_vote_indel = "${output_prefix}.indel"
 	}
 }

tasks/summary_mendelian.wdl

@@ -1,23 +0,0 @@
-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

@@ -1,10 +1,10 @@
 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)
+	File mut_file
 	String docker
 	String sample_name
 	String cluster_config
@@ -16,14 +16,7 @@ workflow {{ project_name }} {
 			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],
+			mut_file=mut_file,
 			docker=docker,
 			cluster_config=cluster_config,
 			disk_size=disk_size
@@ -31,10 +24,11 @@ workflow {{ project_name }} {
 	}
 	call merge_chromo.merge_chromo as merge_chromo {
 		input:
-		mendelian_vote_summary=summary_mendelian.mendelian_vote_summary,
+		mendelian_vote_snv=merge_mendelian_vote.mendelian_vote_snv,
+		mendelian_vote_indel=merge_mendelian_vote.mendelian_vote_indel,
 		sample_name=sample_name,
 		docker=docker,
 		cluster_config=cluster_config,
 		disk_size=disk_size
 	}
-}
+}