first commit

codescripts/callable_bed_voting.py

+# import modules
+import sys, argparse, os
+import fileinput
+from operator import itemgetter   
+
+parser = argparse.ArgumentParser(description="this script is to vote callable bed region")
+
+parser.add_argument('-bed', '--multiSampleBED', type=str, help='The bed file to get high confidence region',  required=True)
+parser.add_argument('-prefix', '--prefix', type=str, help='The output file you want to name',  required=True)
+
+args = parser.parse_args()
+
+# Rename input:
+input_file = args.multiSampleBED
+prefix = args.prefix
+
+consensus_filename = prefix + '.27consensus.bed'
+outCONSENSUS = open(consensus_filename,'w')
+filter_filename = prefix + '.filtered.bed'
+outFiltered = open(filter_filename,'w')
+#initial
+#sequence_tech = ['chr','start','end','number','sample','SEQ2000','SEQ2000','SEQ2000','SEQT7','SEQT7','SEQT7','Nova','Nova','Nova','Nova','Nova','Nova','Nova','Nova','Nova','Nova','Nova','Nova','Nova','XTen','XTen','XTen','XTen','XTen','XTen','XTen','XTen','XTen']
+#sequence_site = ['chr','start','end','number','sample','BGI','BGI','BGI','WGE','WGE','WGE','ARD','ARD','ARD','ARD','ARD','ARD','BRG','BRG','BRG','WUX','WUX','WUX','ARD','ARD','ARD','NVG','NVG','NVG','WUX','WUX','WUX']
+
+def consensus_bed(oneLine):
+	line = oneLine.strip()
+	strings = line.split('\t')
+	# replicate
+	SEQ2000_BGI = 1 if strings[5:8].count('1') > 1 else 0
+	T7_WGE = 1 if strings[8:11].count('1') > 1 else 0 
+	Nova_ARD_1 = 1 if strings[11:14].count('1') > 1 else 0
+	Nova_ARD_2 = 1 if strings[14:17].count('1') > 1 else 0		
+	Nova_BRG = 1 if strings[17:20].count('1') > 1 else 0
+	Nova_WUX = 1 if strings[20:23].count('1') > 1 else 0
+	XTen_ARD = 1 if strings[23:26].count('1') >1 else 0
+	XTen_NVG = 1 if strings[26:29].count('1') > 1 else 0
+	XTen_WUX = 1 if strings[29:32].count('1') > 1 else 0
+	# library
+	pcr = 1 if [SEQ2000_BGI,Nova_WUX,XTen_ARD,XTen_WUX,XTen_NVG].count(1) > 3 else 0
+	pcr_free = 1 if [T7_WGE,Nova_ARD_1,Nova_ARD_2,Nova_BRG].count(1) > 2 else 0
+	voted = 1 if [pcr,pcr_free].count(1) > 1 else 0 
+	# get consensus bed and tech specific bed
+	if voted == 1:
+		outCONSENSUS.write(oneLine)
+	else:
+		outFiltered.write(oneLine)
+
+for oneLine in fileinput.input(input_file):
+	consensus_bed(oneLine)
+
+
+outCONSENSUS.close()
+outFiltered.close()
+
+

codescripts/count_bed.py

+import sys,getopt
+import fileinput
+
+def process(line):
+	strings = line.strip().split('\t')
+	pos2 = int(strings[2])
+	pos1 = int(strings[1])
+	c = pos2 - pos1
+	return c
+	
+
+result = 0
+
+for line in fileinput.input(sys.argv[1]):
+	C = process(line)
+	result = result + C
+
+print(result)

inputs

+{
+  "{{ project_name }}.LCL8_callable_bed": "oss://pgx-result/renluyao/manuscript_v3.0/benchmark_region/dat/LCL8.consensus.merged.bed",
+  "{{ project_name }}.LCL6_variants_bed": "oss://pgx-result/renluyao/manuscript_v3.0/benchmark_region/dat/LCL6.variants.bed",
+  "{{ project_name }}.LCL5_variants_bed": "oss://pgx-result/renluyao/manuscript_v3.0/benchmark_region/dat/LCL5.variants.bed",
+  "{{ project_name }}.LCL8_HR_bed": "oss://pgx-result/renluyao/manuscript_v3.0/benchmark_region/dat/LCL8.27.homo_ref.consensus.bed",
+  "{{ project_name }}.disk_size": "150",
+  "{{ project_name }}.LCL7_variants_bed": "oss://pgx-result/renluyao/manuscript_v3.0/benchmark_region/dat/LCL7.variants.bed",
+  "{{ project_name }}.LCL7_callable_bed": "oss://pgx-result/renluyao/manuscript_v3.0/benchmark_region/dat/LCL7.consensus.merged.bed",
+  "{{ project_name }}.docker": "registry-internal.cn-shanghai.aliyuncs.com/pgx-docker-registry/bedtools:v2.27.1",
+  "{{ project_name }}.LCL5_HR_bed": "oss://pgx-result/renluyao/manuscript_v3.0/benchmark_region/dat/LCL5.27.homo_ref.consensus.bed",
+  "{{ project_name }}.LCL7_HR_bed": "oss://pgx-result/renluyao/manuscript_v3.0/benchmark_region/dat/LCL7.27.homo_ref.consensus.bed",
+  "{{ project_name }}.LCL5_callable_bed": "oss://pgx-result/renluyao/manuscript_v3.0/benchmark_region/dat/LCL5.consensus.merged.bed",
+  "{{ project_name }}.LCL6_callable_bed": "oss://pgx-result/renluyao/manuscript_v3.0/benchmark_region/dat/LCL6.consensus.merged.bed",
+  "{{ project_name }}.LCL8_variants_bed": "oss://pgx-result/renluyao/manuscript_v3.0/benchmark_region/dat/LCL8.variants.bed",
+  "{{ project_name }}.cluster_config": "OnDemand bcs.a2.large img-ubuntu-vpc",
+  "{{ project_name }}.LCL6_HR_bed": "oss://pgx-result/renluyao/manuscript_v3.0/benchmark_region/dat/LCL6.27.homo_ref.consensus.bed"
+}

tasks/callable_loci.wdl

+task callable_loci {
+	
+	File LCL5_callable_bed
+	File LCL6_callable_bed
+	File LCL7_callable_bed
+	File LCL8_callable_bed
+	String docker
+	String disk_size
+	String cluster_config
+	
+
+	command <<<
+		
+		cat ${LCL5_callable_bed} | grep -w '^chr1\|^chr2\|^chr3\|^chr4\|^chr5\|^chr6\|^chr7\|^chr8\|^chr9\|^chr10\|^chr11\|^chr12\|^chr13\|^chr14\|^chr15\|^chr16\|^chr17\|^chr18\|^chr19\|^chr20\|^chr21\|^chr22\|^chrX' > LCL5_callable_bed.chr1-22.x.bed
+
+
+		cat ${LCL6_callable_bed} | grep -w '^chr1\|^chr2\|^chr3\|^chr4\|^chr5\|^chr6\|^chr7\|^chr8\|^chr9\|^chr10\|^chr11\|^chr12\|^chr13\|^chr14\|^chr15\|^chr16\|^chr17\|^chr18\|^chr19\|^chr20\|^chr21\|^chr22\|^chrX' > LCL6_callable_bed.chr1-22.x.bed
+
+		cat ${LCL7_callable_bed} | grep -w '^chr1\|^chr2\|^chr3\|^chr4\|^chr5\|^chr6\|^chr7\|^chr8\|^chr9\|^chr10\|^chr11\|^chr12\|^chr13\|^chr14\|^chr15\|^chr16\|^chr17\|^chr18\|^chr19\|^chr20\|^chr21\|^chr22\|^chrX' > LCL7_callable_bed.chr1-22.x.bed
+
+		cat ${LCL8_callable_bed} | grep -w '^chr1\|^chr2\|^chr3\|^chr4\|^chr5\|^chr6\|^chr7\|^chr8\|^chr9\|^chr10\|^chr11\|^chr12\|^chr13\|^chr14\|^chr15\|^chr16\|^chr17\|^chr18\|^chr19\|^chr20\|^chr21\|^chr22\|^chrX' > LCL8_callable_bed.chr1-22.x.bed
+
+
+		/opt/ccdg/bedtools-2.27.1/bin/bedtools multiinter -i LCL5_callable_bed.chr1-22.x.bed LCL6_callable_bed.chr1-22.x.bed LCL7_callable_bed.chr1-22.x.bed LCL8_callable_bed.chr1-22.x.bed > Quartet.callable.merged.bed
+
+		cat Quartet.callable.merged.bed | grep "1,2,3,4" | cut -f1-3 > Quartet.callable.merged.intersect.bed
+
+		>>>
+
+		runtime {
+		docker:docker
+    	cluster:cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File LCL5_callable_filtered_bed = "LCL5_callable_bed.chr1-22.x.bed"
+		File LCL6_callable_filtered_bed = "LCL6_callable_bed.chr1-22.x.bed"
+		File LCL7_callable_filtered_bed = "LCL7_callable_bed.chr1-22.x.bed"
+		File LCL8_callable_filtered_bed = "LCL8_callable_bed.chr1-22.x.bed"
+		File callable_merged_bed = "Quartet.callable.merged.bed"
+		File callable_merged_intersect_bed = "Quartet.callable.merged.intersect.bed"
+	}
+}
+
+
+
+

tasks/final_merge.wdl

+task final_merge {
+	
+	File callable_merged_intersect_bed
+	File HR_merged_intersect_bed
+	File variants_merged_bed
+	String docker
+	String disk_size
+	String cluster_config
+	
+
+	command <<<
+
+		/opt/ccdg/bedtools-2.27.1/bin/bedtools merge -i ${HR_merged_intersect_bed} ${variants_merged_bed} > variant_invariant.bed
+
+		/opt/ccdg/bedtools-2.27.1/bin/bedtools intersect -a variant_invariant.bed -b ${callable_merged_intersect_bed} > benchmark_regions.bed
+
+		>>>
+
+		runtime {
+		docker:docker
+    	cluster:cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File variant_invariant = "variant_invariant.bed"
+		File benchmark = "benchmark_regions.bed"
+	}
+}
+
+
+
+
+
+
+

tasks/homo_bed.wdl

+task homo_bed {
+	
+	File LCL5_HR_bed
+	File LCL6_HR_bed
+	File LCL7_HR_bed
+	File LCL8_HR_bed
+	String docker
+	String disk_size
+	String cluster_config
+	
+
+	command <<<
+		cat ${LCL5_HR_bed} | grep -w '^chr1\|^chr2\|^chr3\|^chr4\|^chr5\|^chr6\|^chr7\|^chr8\|^chr9\|^chr10\|^chr11\|^chr12\|^chr13\|^chr14\|^chr15\|^chr16\|^chr17\|^chr18\|^chr19\|^chr20\|^chr21\|^chr22\|^chrX' > LCL5_HR_bed.chr1-22.x.bed
+
+
+		cat ${LCL6_HR_bed} | grep -w '^chr1\|^chr2\|^chr3\|^chr4\|^chr5\|^chr6\|^chr7\|^chr8\|^chr9\|^chr10\|^chr11\|^chr12\|^chr13\|^chr14\|^chr15\|^chr16\|^chr17\|^chr18\|^chr19\|^chr20\|^chr21\|^chr22\|^chrX' > LCL6_HR_bed.chr1-22.x.bed
+
+		cat ${LCL7_HR_bed} | grep -w '^chr1\|^chr2\|^chr3\|^chr4\|^chr5\|^chr6\|^chr7\|^chr8\|^chr9\|^chr10\|^chr11\|^chr12\|^chr13\|^chr14\|^chr15\|^chr16\|^chr17\|^chr18\|^chr19\|^chr20\|^chr21\|^chr22\|^chrX' > LCL7_HR_bed.chr1-22.x.bed
+
+		cat ${LCL8_HR_bed} | grep -w '^chr1\|^chr2\|^chr3\|^chr4\|^chr5\|^chr6\|^chr7\|^chr8\|^chr9\|^chr10\|^chr11\|^chr12\|^chr13\|^chr14\|^chr15\|^chr16\|^chr17\|^chr18\|^chr19\|^chr20\|^chr21\|^chr22\|^chrX' > LCL8_HR_bed.chr1-22.x.bed
+
+
+		/opt/ccdg/bedtools-2.27.1/bin/bedtools multiinter -i LCL5_HR_bed.chr1-22.x.bed LCL6_HR_bed.chr1-22.x.bed LCL7_HR_bed.chr1-22.x.bed LCl8_HR_bed.chr1-22.x.bed > Quartet.HR.merged.bed
+
+		cat Quartet.HR.merged.bed | grep "1,2,3,4" | cut -f1-3 > Quartet.HR.merged.intersect.bed
+		>>>
+
+		runtime {
+		docker:docker
+    	cluster:cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File LCL5_HR_filtered_bed = "LCL5_HR_bed.chr1-22.x.bed"
+		File LCL6_HR_filtered_bed = "LCL6_HR_bed.chr1-22.x.bed"
+		File LCL7_HR_filtered_bed = "LCL7_HR_bed.chr1-22.x.bed"
+		File LCL8_HR_filtered_bed = "LCL8_HR_bed.chr1-22.x.bed"
+		File HR_merged_bed = "Quartet.HR.merged.bed"
+		File HR_merged_intersect_bed = "Quartet.HR.merged.intersect.bed"
+	}
+}
+
+
+
+

tasks/variant_bed.wdl

+task variant_bed {
+	
+	File LCL5_variants_bed
+	File LCL6_variants_bed
+	File LCL7_variants_bed
+	File LCL8_variants_bed
+	String docker
+	String disk_size
+	String cluster_config
+	
+
+	command <<<
+		cat ${LCL5_variants_bed} | cut -f1,11,12 > LCL5_variants_bed.chr1-22.x.bed
+		cat ${LCL6_variants_bed} | cut -f1,11,12 > LCL6_variants_bed.chr1-22.x.bed
+		cat ${LCL7_variants_bed} | cut -f1,11,12 > LCL7_variants_bed.chr1-22.x.bed
+		cat ${LCL8_variants_bed} | cut -f1,11,12 > LCL8_variants_bed.chr1-22.x.bed
+
+		cat LCL5_variants_bed.chr1-22.x.bed LCL6_variants_bed.chr1-22.x.bed LCL7_variants_bed.chr1-22.x.bed LCL8_variants_bed.chr1-22.x.bed | sort -k1,1 -k2,2n | /opt/ccdg/bedtools-2.27.1/bin/bedtools merge -i - > Quartet.variants.merged.union.bed
+
+		>>>
+
+		runtime {
+		docker:docker
+    	cluster:cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File variants_merged_bed = "Quartet.variants.merged.union.bed"
+	}
+}
+
+
+
+
+
+
+

workflow.wdl

+import "./tasks/callable_loci.wdl" as callable_loci
+import "./tasks/final_merge.wdl" as final_merge
+import "./tasks/homo_bed.wdl" as homo_bed
+import "./tasks/variant_bed.wdl" as variant_bed
+
+
+
+workflow {{ project_name }} {
+
+	File LCL5_callable_bed
+	File LCL6_callable_bed
+	File LCL7_callable_bed
+	File LCL8_callable_bed
+	File LCL5_HR_bed
+	File LCL6_HR_bed
+	File LCL7_HR_bed
+	File LCL8_HR_bed
+	File LCL5_variants_bed
+	File LCL6_variants_bed
+	File LCL7_variants_bed
+	File LCL8_variants_bed
+	String docker
+	String disk_size
+	String cluster_config
+	
+	call callable_loci.callable_loci as callable_loci {
+		input:
+		LCL5_callable_bed=LCL5_callable_bed,
+		LCL6_callable_bed=LCL6_callable_bed,
+		LCL7_callable_bed=LCL7_callable_bed,
+		LCL8_callable_bed=LCL8_callable_bed,
+		docker=docker,
+		disk_size=disk_size,
+		cluster_config=cluster_config
+	}
+
+	call homo_bed.homo_bed as homo_bed {
+		input:
+		LCL5_HR_bed=LCL5_HR_bed,
+		LCL6_HR_bed=LCL6_HR_bed,
+		LCL7_HR_bed=LCL7_HR_bed,
+		LCL8_HR_bed=LCL8_HR_bed,
+		docker=docker,
+		disk_size=disk_size,
+		cluster_config=cluster_config
+	}
+
+	call variant_bed.variant_bed as variant_bed {
+		input:
+		LCL5_variants_bed=LCL5_variants_bed,
+		LCL6_variants_bed=LCL6_variants_bed,
+		LCL7_variants_bed=LCL7_variants_bed,
+		LCL8_variants_bed=LCL8_variants_bed,
+		docker=docker,
+		disk_size=disk_size,
+		cluster_config=cluster_config
+	}
+
+	call final_merge.final_merge as final_merge {
+		input:
+		callable_merged_intersect_bed=callable_loci.callable_merged_intersect_bed,
+		HR_merged_intersect_bed=homo_bed.HR_merged_intersect_bed,
+		variants_merged_bed=variant_bed.variants_merged_bed,
+		docker=docker,
+		disk_size=disk_size,
+		cluster_config=cluster_config
+	}
+
+}
+