mendelian concordence

README.md

-#高置信位点整合Part2——从VCF和BAM文件中提取突变位点的信息
+#高置信突变位点的整合
 
 > Author： Run Luyao
 >
 > E-mail：18110700050@fudan.edu.cn
 >
-> Git: http://choppy.3steps.cn/renluyao/HCC_Extract_Info.git
+> Git：http://choppy.3steps.cn/renluyao/high_confidence_calls_intergration.git
 >
-> Last Updates: 11/9/2019
+> Last Updates: 12/6/2019
 
 ## 安装指南
 
 # 激活choppy环境
 source activate choppy
 # 安装app
-choppy install renluyao/HCC_Extract_Info
+choppy install renluyao/high_confidence_calls_intergration
 ```
 
 ## App概述
 
-当我们拿到测序结果的时候，没有办法判断哪些是真的突变位点，哪些是假阳性
+中华家系1号全基因组高置信small variants（SNVs和Indels）的整合流程。
 
-## 流程与参数
+Quartet家系的四个样本的DNA标准物质被送往多加测序公司，用PCRfree或者PCR的建库方法建立3个技术重复，用多个测序平台（Illumina XTen、Illumina Novaseq、BGISEQ-500、BGISEQ-2000和BGISEQ-T7）进行测序。获得的原始数据用多个分析流程进行分析（比对软件：BWA-mem、Novoalign、Bowtie2，突变检出软件：HaplotyperCaller、Strelka2、FreeBayes）。
+
+经过以上各种因素的组合每个样本得到216个VCF文件，本APP的目的是整合这些VCF文件的结果得到一组可信度较高的突变。
 
-两个问题：
+## 流程与参数
 
-1. MNP
-2. merge之后的pos相同，但是ref和alt不同
 
-是不是gatk的问题，尝试用bcftools norm
 
 ## App输入变量与输入文件
 
+
+
 ## App输出文件
 
+
+
 ## 结果展示与解读
 
+
+
 ## CHANGELOG
 
+
+
 ## FAQ
 

codescripts/high_confidence_call_vote.py

+# import modules
+import sys, argparse, os
+import fileinput
+import re
+import pandas as pd
+from operator import itemgetter
+from collections import Counter
+from itertools import islice  
+
+# input arguments
+parser = argparse.ArgumentParser(description="this script is to count voting number")
+
+parser.add_argument('-vcf', '--multi_sample_vcf', type=str, help='The VCF file you want to count the voting number',  required=True)
+parser.add_argument('-dup', '--dup_list', type=str, help='Duplication list',  required=True)
+parser.add_argument('-sample', '--sample_name', type=str, help='which sample of quartet',  required=True)
+parser.add_argument('-prefix', '--prefix', type=str, help='Prefix of output file name',  required=True)
+
+args = parser.parse_args()
+multi_sample_vcf = args.multi_sample_vcf
+dup_list = args.dup_list
+prefix = args.prefix
+sample_name = args.sample_name
+
+vcf_header = '''##fileformat=VCFv4.2
+##fileDate=20191224
+##source=high_confidence_calls_intergration(choppy app)
+##reference=GRCh38.d1.vd1
+##INFO=<ID=PCT,Number=1,Type=Float,Description="Percentage of votes">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=TWINS,Number=0,Type=Flag,Description="0 for sister consistent, 1 for sister inconsistent">
+##FORMAT=<ID=TRIO5,Number=0,Type=Flag,Description="0 for trio consistent, 1 for trio inconsistent">
+##FORMAT=<ID=TRIO6,Number=0,Type=Flag,Description="0 for trio consistent, 1 for trio inconsistent">
+##contig=<ID=chr1,length=248956422>
+##contig=<ID=chr2,length=242193529>
+##contig=<ID=chr3,length=198295559>
+##contig=<ID=chr4,length=190214555>
+##contig=<ID=chr5,length=181538259>
+##contig=<ID=chr6,length=170805979>
+##contig=<ID=chr7,length=159345973>
+##contig=<ID=chr8,length=145138636>
+##contig=<ID=chr9,length=138394717>
+##contig=<ID=chr10,length=133797422>
+##contig=<ID=chr11,length=135086622>
+##contig=<ID=chr12,length=133275309>
+##contig=<ID=chr13,length=114364328>
+##contig=<ID=chr14,length=107043718>
+##contig=<ID=chr15,length=101991189>
+##contig=<ID=chr16,length=90338345>
+##contig=<ID=chr17,length=83257441>
+##contig=<ID=chr18,length=80373285>
+##contig=<ID=chr19,length=58617616>
+##contig=<ID=chr20,length=64444167>
+##contig=<ID=chr21,length=46709983>
+##contig=<ID=chr22,length=50818468>
+##contig=<ID=chrX,length=156040895>
+'''
+
+# read in duplication list
+dup = pd.read_table(dup_list,header=None)
+var_dup = dup[0].tolist()
+
+# output file
+file_name = prefix + '_annotated.vcf'
+outfile = open(file_name,'w')
+
+# write VCF
+outputcolumn = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tQuartet_DNA_BGI_SEQ2000_BGI_1_20180518_LCL5\tQuartet_DNA_BGI_SEQ2000_BGI_2_20180530_LCL5\tQuartet_DNA_BGI_SEQ2000_BGI_3_20180530_LCL5\tQuartet_DNA_BGI_SEQ2000_WGE_1_20190402_LCL5\tQuartet_DNA_BGI_SEQ2000_WGE_2_20190402_LCL5\tQuartet_DNA_BGI_SEQ500_BGI_1_20180328_LCL5 \tQuartet_DNA_BGI_SEQ500_BGI_2_20180328_LCL5\tQuartet_DNA_BGI_SEQ500_BGI_3_20180328_LCL5\tQuartet_DNA_ILM_Nova_ARD_1_20181108_LCL5\tQuartet_DNA_ILM_Nova_ARD_2_20181108_LCL5\tQuartet_DNA_ILM_Nova_ARD_3_20181108_LCL5\tQuartet_DNA_ILM_Nova_ARD_4_20190111_LCL5\tQuartet_DNA_ILM_Nova_ARD_5_20190111_LCL5\tQuartet_DNA_ILM_Nova_ARD_6_20190111_LCL5\tQuartet_DNA_ILM_Nova_BRG_1_20171024_LCL5\tQuartet_DNA_ILM_Nova_BRG_1_20180930_LCL5\tQuartet_DNA_ILM_Nova_BRG_2_20180930_LCL5\tQuartet_DNA_ILM_Nova_BRG_3_20180930_LCL5\tQuartet_DNA_ILM_Nova_GAC_1_20171025_LCL5\tQuartet_DNA_ILM_Nova_NVG_1_20171024_LCL5\tQuartet_DNA_ILM_Nova_WUX_1_20171024_LCL5\tQuartet_DNA_ILM_XTen_ARD_1_20170403_LCL5\tQuartet_DNA_ILM_XTen_ARD_2_20170403_LCL5\tQuartet_DNA_ILM_XTen_ARD_3_20170403_LCL5\tQuartet_DNA_ILM_XTen_NVG_1_20170329_LCL5\tQuartet_DNA_ILM_XTen_NVG_2_20170329_LCL5\tQuartet_DNA_ILM_XTen_NVG_3_20170329_LCL5\tQuartet_DNA_ILM_XTen_WUX_1_20170216_LCL5\tQuartet_DNA_ILM_XTen_WUX_2_20170216_LCL5\tQuartet_DNA_ILM_XTen_WUX_3_20170216_LCL5\tQuartet_DNA_ILM_XTen_WUX_4_20180703_LCL5\tQuartet_DNA_ILM_XTen_WUX_5_20180703_LCL5\tQuartet_DNA_ILM_XTen_WUX_6_20180703_LCL5' +'\t'+ sample_name+'_pcr'+'\t' + sample_name+'_pcr-free'+ '\t'+ sample_name +'consensus' + '\n'
+outfile.write(vcf_header)
+outfile.write(outputcolumn)
+
+#function
+def vote_percentage(strings):
+	strings = [x.replace('0/0','.') for x in strings]
+	gt = [x.split(':')[0] for x in strings]
+	percentage = round((33 - gt.count('.'))/33,4)
+	return(str(percentage))
+
+def decide_by_rep(strings):
+	consensus_rep = ''
+	mendelian = [x[-5:] for x in strings]
+	strings = [x.replace('.','0/0') for x in strings]
+	gt = [x.split(':')[0] for x in strings]
+	# mendelian consistent?
+	mendelian_dict = Counter(mendelian)
+	highest_mendelian = mendelian_dict.most_common(1)
+	candidate_mendelian = highest_mendelian[0][0]
+	freq_mendelian = highest_mendelian[0][1]
+	if (candidate_mendelian == '1:1:1') and (freq_mendelian >= 2):
+		gt_num_dict = Counter(gt)
+		highest_gt = gt_num_dict.most_common(1)
+		candidate_gt = highest_gt[0][0]
+		freq_gt = highest_gt[0][1]
+		if (candidate_gt != '0/0') and (freq_gt >= 2):
+			consensus_rep = candidate_gt
+		elif (candidate_gt == '0/0') and (freq_gt >= 2):
+			consensus_rep = '0/0'
+		else:
+			consensus_rep = 'inconGT'
+	elif (candidate_mendelian == '.') and (freq_mendelian >= 2):
+		consensus_rep = 'noInfo'
+	else:
+		consensus_rep = 'inconMen'
+	return consensus_rep
+
+
+def main():
+	for line in fileinput.input(multi_sample_vcf):
+		headline = re.match('^\#',line)
+		if headline is not None:
+			pass
+		else:
+			line = line.strip()
+			strings = line.split('\t')
+			variant_id = '_'.join([strings[0],strings[1]])
+			# check if the variants location is duplicated
+			if variant_id in var_dup:
+				outLine = '\t'.join(strings) + '\t' + '.' +'\t' + '.' + '\t' + 'dupVar' + '\n'
+				outfile.write(outLine)
+			else:
+				# pre-define
+				pcr_consensus = ''
+				pcr_free_consensus = ''
+				consensus_call = ''
+				# pcr 
+				pcr = itemgetter(*[9,10,11,12,14,15,16,23,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41])(strings)
+				SEQ2000 = decide_by_rep(pcr[0:4])
+				SEQ500 = decide_by_rep(pcr[4:7])
+				Nova = decide_by_rep(pcr[7:11])
+				XTen_ARD = decide_by_rep(pcr[11:14])
+				XTen_NVG = decide_by_rep(pcr[14:17])
+				XTen_WUX_1 = decide_by_rep(pcr[17:20])
+				XTen_WUX_2 = decide_by_rep(pcr[20:23])
+				sequence_site = [SEQ2000,SEQ500,Nova,XTen_ARD,XTen_NVG,XTen_WUX_1,XTen_WUX_2]
+				sequence_dict = Counter(sequence_site)
+				highest_sequence = sequence_dict.most_common(1)
+				candidate_sequence = highest_sequence[0][0]
+				freq_sequence = highest_sequence[0][1]
+				if freq_sequence > 4:
+					pcr_consensus = candidate_sequence
+				else:
+					pcr_consensus = 'inconSequenceSite'
+				# pcr-free
+				pcr_free = itemgetter(*[13,17,18,19,20,21,22,24,25,26])(strings)
+				SEQ2000 = decide_by_rep(pcr_free[0])
+				Nova_ARD_1 = decide_by_rep(pcr_free[1:4])
+				Nova_ARD_2 = decide_by_rep(pcr_free[4:7])
+				Nova_BRG = decide_by_rep(pcr_free[7:10])
+				sequence_site = [SEQ2000,Nova_ARD_1,Nova_ARD_2,Nova_BRG]
+				highest_sequence = sequence_dict.most_common(1)
+				candidate_sequence = highest_sequence[0][0]
+				freq_sequence = highest_sequence[0][1]
+				if freq_sequence > 2:
+					pcr_free_consensus = candidate_sequence
+				else:
+					pcr_free_consensus = 'inconSequenceSite'
+				# pcr and pcr-free
+				tag = ['inconGT','noInfo','inconMen','inconSequenceSite']
+				if (pcr_consensus == pcr_free_consensus) and (pcr_consensus not in tag) and (pcr_consensus != '0/0'):
+					consensus_call = pcr_consensus
+					strings[6] = 'reproducible'
+				elif (pcr_consensus in tag) or (pcr_free_consensus in tag):
+					consensus_call = 'filtered'
+					strings[6] = '.'
+				elif (pcr_consensus == '0/0') and (pcr_free_consensus not in tag) and (pcr_free_consensus != '0/0'):
+					consensus_call = 'pcr-free-speicifc'
+					strings[6] = '.'
+				elif (pcr_consensus != '0/0') and (pcr_consensus not in tag) and (pcr_free_consensus == '0/0'):
+					consensus_call = 'pcr-speicifc'
+					strings[6] = '.'
+				elif (pcr_consensus == '0/0') and (pcr_free_consensus == '0/0'):
+					consensus_call = 'confirm for parents'
+					strings[6] = '.'					
+				else:
+					consensus_call = 'filtered'
+					strings[6] = '.'
+				# percentage
+				percentage = vote_percentage(strings[9:])
+				strings[7] = 'PCT=' + percentage
+				# output 
+				outLine = '\t'.join(strings) + '\t' + pcr_consensus +'\t' + pcr_free_consensus + '\t' + consensus_call + '\n'
+				outfile.write(outLine)
+
+
+if __name__ == '__main__':
+	main()
+
+
+
+
+
+
+
+
+
+
+
+

codescripts/reformVCF.py

+# import modules
+import sys, argparse, os
+import fileinput
+import re
+
+parser = argparse.ArgumentParser(description="This script is to split samples in VCF files and rewrite to the right style")
+
+parser.add_argument('-vcf', '--familyVCF', type=str, help='VCF with sister and mendelian infomation',  required=True)
+parser.add_argument('-name', '--familyName', type=str, help='Family name of the VCF file',  required=True)
+
+args = parser.parse_args()
+
+# Rename input:
+inputFile = args.familyVCF
+family_name = args.familyName
+
+# output filename
+LCL5_name = family_name + '.LCL5.vcf'
+LCL5file = open(LCL5_name,'w')
+LCL6_name = family_name + '.LCL6.vcf'
+LCL6file = open(LCL6_name,'w')
+LCL7_name = family_name + '.LCL7.vcf'
+LCL7file = open(LCL7_name,'w')
+LCL8_name = family_name + '.LCL8.vcf'
+LCL8file = open(LCL8_name,'w')
+family_filename = family_name + '.vcf'
+familyfile = open(family_filename,'w')
+
+# default columns, which will be included in the included in the calssifier
+vcfheader = '''##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="the same genotype between twin sister and mendelian consistent in 578 and 678">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=TWINS,Number=0,Type=Flag,Description="0 for sister consistent, 1 for sister inconsistent">
+##FORMAT=<ID=TRIO5,Number=0,Type=Flag,Description="0 for trio consistent, 1 for trio inconsistent">
+##FORMAT=<ID=TRIO6,Number=0,Type=Flag,Description="0 for trio consistent, 1 for trio inconsistent">
+##contig=<ID=chr1,length=248956422>
+##contig=<ID=chr2,length=242193529>
+##contig=<ID=chr3,length=198295559>
+##contig=<ID=chr4,length=190214555>
+##contig=<ID=chr5,length=181538259>
+##contig=<ID=chr6,length=170805979>
+##contig=<ID=chr7,length=159345973>
+##contig=<ID=chr8,length=145138636>
+##contig=<ID=chr9,length=138394717>
+##contig=<ID=chr10,length=133797422>
+##contig=<ID=chr11,length=135086622>
+##contig=<ID=chr12,length=133275309>
+##contig=<ID=chr13,length=114364328>
+##contig=<ID=chr14,length=107043718>
+##contig=<ID=chr15,length=101991189>
+##contig=<ID=chr16,length=90338345>
+##contig=<ID=chr17,length=83257441>
+##contig=<ID=chr18,length=80373285>
+##contig=<ID=chr19,length=58617616>
+##contig=<ID=chr20,length=64444167>
+##contig=<ID=chr21,length=46709983>
+##contig=<ID=chr22,length=50818468>
+##contig=<ID=chrX,length=156040895>
+'''
+# write VCF
+LCL5colname = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t'+family_name+'_LCL5'+'\n'
+LCL5file.write(vcfheader)
+LCL5file.write(LCL5colname)
+
+LCL6colname = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t'+family_name+'_LCL6'+'\n'
+LCL6file.write(vcfheader)
+LCL6file.write(LCL6colname)
+
+LCL7colname = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t'+family_name+'_LCL7'+'\n'
+LCL7file.write(vcfheader)
+LCL7file.write(LCL7colname)
+
+LCL8colname = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t'+family_name+'_LCL8'+'\n'
+LCL8file.write(vcfheader)
+LCL8file.write(LCL8colname)
+
+familycolname = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t'+'LCL5\t'+'LCL6\t'+'LCL7\t'+'LCL8'+'\n'
+familyfile.write(vcfheader)
+familyfile.write(familycolname)
+
+# reform VCF
+def process(oneLine):
+	line = oneLine.rstrip()
+	strings = line.strip().split('\t')
+	# replace .
+	# LCL5 uniq
+	if strings[11] == '.':
+		strings[11] = '0/0'
+		strings[9] = strings[12]
+		strings[10] = strings[13]
+	else:
+		pass
+	# LCL6 uniq
+	if strings[14] == '.':
+		strings[14] = '0/0'
+		strings[12] = strings[9]
+		strings[13] = strings[10]
+	else:
+		pass
+	# sister
+	if strings[11] == strings[14]:
+		add_format = ":1"
+	else:
+		add_format = ":0"
+	# trioLCL5
+	if strings[15] == 'MD=1':
+		add_format = add_format + ":1"
+	else:
+		add_format = add_format + ":0"
+	# trioLCL6
+	if strings[7] == 'MD=1':
+		add_format = add_format + ":1"
+	else:
+		add_format = add_format + ":0"
+	# filter
+	if (strings[11] == strings[14]) and (strings[15] == 'MD=1') and (strings[7] == 'MD=1'):
+		strings[6] = 'PASS'
+	else:
+		strings[6] = '.'
+	# output LCL5
+	LCL5outLine = strings[0]+'\t'+strings[1]+'\t'+strings[2]+'\t'+strings[3]+'\t'+strings[4]+'\t'+'.'+'\t'+strings[6]+'\t'+ '.' +'\t'+ 'GT:TWINS:TRIO5:TRIO6' + '\t' + strings[14] + add_format + '\n'
+	LCL5file.write(LCL5outLine)
+	# output LCL6
+	LCL6outLine = strings[0]+'\t'+strings[1]+'\t'+strings[2]+'\t'+strings[3]+'\t'+strings[4]+'\t'+'.'+'\t'+strings[6]+'\t'+ '.' +'\t'+ 'GT:TWINS:TRIO5:TRIO6' + '\t' + strings[11] + add_format + '\n'
+	LCL6file.write(LCL6outLine)
+	# output LCL7
+	LCL7outLine = strings[0]+'\t'+strings[1]+'\t'+strings[2]+'\t'+strings[3]+'\t'+strings[4]+'\t'+'.'+'\t'+strings[6]+'\t'+ '.' +'\t'+ 'GT:TWINS:TRIO5:TRIO6' + '\t' + strings[10] + add_format + '\n'
+	LCL7file.write(LCL7outLine)
+	# output LCL8
+	LCL8outLine = strings[0]+'\t'+strings[1]+'\t'+strings[2]+'\t'+strings[3]+'\t'+strings[4]+'\t'+'.'+'\t'+strings[6]+'\t'+ '.' +'\t'+ 'GT:TWINS:TRIO5:TRIO6' + '\t' + strings[9] + add_format + '\n'
+	LCL8file.write(LCL8outLine)
+	# output family
+	familyoutLine = strings[0]+'\t'+strings[1]+'\t'+strings[2]+'\t'+strings[3]+'\t'+strings[4]+'\t'+ '.'+'\t'+strings[6]+'\t'+ '.' +'\t'+ 'GT:TWINS:TRIO5:TRIO6' + '\t' + strings[14] + add_format +'\t' + strings[11] + add_format + '\t' + strings[10] + add_format +'\t' + strings[9] + add_format + '\n'
+	familyfile.write(familyoutLine)
+
+
+for line in fileinput.input(inputFile):
+	m = re.match('^\#',line)
+	if m is not None:
+		pass
+	else:
+		process(line)
+		
+

family.tsv

-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL8_1_20180518.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL7_1_20180518.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL5_1_20180518.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL6_1_20180518.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL8_1_20180518.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL7_1_20180518.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL5_1_20180518.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL6_1_20180518.normed.callable.vcf.gz.tbi	Quartet_DNA_BGI_SEQ2000_BGI_LCL8_1_20180518	Quartet_DNA_BGI_SEQ2000_BGI_LCL7_1_20180518	Quartet_DNA_BGI_SEQ2000_BGI_LCL5_1_20180518	BGI_SEQ2000_BGI_1
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL8_2_20180530.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL7_2_20180530.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL5_2_20180530.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL6_2_20180530.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL8_2_20180530.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL7_2_20180530.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL5_2_20180530.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL6_2_20180530.normed.callable.vcf.gz.tbi	Quartet_DNA_BGI_SEQ2000_BGI_LCL8_2_20180530	Quartet_DNA_BGI_SEQ2000_BGI_LCL7_2_20180530	Quartet_DNA_BGI_SEQ2000_BGI_LCL5_2_20180530	BGI_SEQ2000_BGI_2
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL8_3_20180530.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL7_3_20180530.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL5_3_20180530.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL6_3_20180530.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL8_3_20180530.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL7_3_20180530.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL5_3_20180530.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_BGI_LCL6_3_20180530.normed.callable.vcf.gz.tbi	Quartet_DNA_BGI_SEQ2000_BGI_LCL8_3_20180530	Quartet_DNA_BGI_SEQ2000_BGI_LCL7_3_20180530	Quartet_DNA_BGI_SEQ2000_BGI_LCL5_3_20180530	BGI_SEQ2000_BGI_3
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL8_1_20190402.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL7_1_20190402.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL5_1_20190402.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL6_1_20190402.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL8_1_20190402.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL7_1_20190402.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL5_1_20190402.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL6_1_20190402.normed.callable.vcf.gz.tbi	Normal_DNA_M8	Normal_DNA_F7	Normal_DNA_D5	BGI_SEQ2000_WGE_1
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL8_2_20190402.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL7_2_20190402.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL5_2_20190402.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL6_2_20190402.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL8_2_20190402.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL7_2_20190402.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL5_2_20190402.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ2000_WGE_LCL6_2_20190402.normed.callable.vcf.gz.tbi	PCRFree_DNA_M8	PCRFree_DNA_F7	PCRFree_DNA_D5	BGI_SEQ2000_WGE_2
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL8_1_20180328.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL7_1_20180328.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL5_1_20180328.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL6_1_20180328.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL8_1_20180328.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL7_1_20180328.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL5_1_20180328.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL6_1_20180328.normed.callable.vcf.gz.tbi	Quartet_DNA_BGI_SEQ500_BGI_LCL8_1_20180328	Quartet_DNA_BGI_SEQ500_BGI_LCL7_1_20180328	Quartet_DNA_BGI_SEQ500_BGI_LCL5_1_20180328	BGI_SEQ500_BGI_1
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL8_2_20180328.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL7_2_20180328.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL5_2_20180328.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL6_2_20180328.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL8_2_20180328.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL7_2_20180328.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL5_2_20180328.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL6_2_20180328.normed.callable.vcf.gz.tbi	Quartet_DNA_BGI_SEQ500_BGI_LCL8_2_20180328	Quartet_DNA_BGI_SEQ500_BGI_LCL7_2_20180328	Quartet_DNA_BGI_SEQ500_BGI_LCL5_2_20180328	BGI_SEQ500_BGI_2
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL8_3_20180328.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL7_3_20180328.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL5_3_20180328.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL6_3_20180328.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL8_3_20180328.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL7_3_20180328.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL5_3_20180328.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_BGI_SEQ500_BGI_LCL6_3_20180328.normed.callable.vcf.gz.tbi	Quartet_DNA_BGI_SEQ500_BGI_LCL8_3_20180328	Quartet_DNA_BGI_SEQ500_BGI_LCL7_3_20180328	Quartet_DNA_BGI_SEQ500_BGI_LCL5_3_20180328	BGI_SEQ500_BGI_3
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL8_1_20181108.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL7_1_20181108.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL5_1_20181108.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL6_1_20181108.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL8_1_20181108.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL7_1_20181108.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL5_1_20181108.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL6_1_20181108.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_Nova_ARD_LCL8_1_20181108	Quartet_DNA_ILM_Nova_ARD_LCL7_1_20181108	Quartet_DNA_ILM_Nova_ARD_LCL5_1_20181108	ILM_Nova_ARD_1
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL8_2_20181108.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL7_2_20181108.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL5_2_20181108.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL6_2_20181108.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL8_2_20181108.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL7_2_20181108.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL5_2_20181108.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL6_2_20181108.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_Nova_ARD_LCL8_2_20181108	Quartet_DNA_ILM_Nova_ARD_LCL7_2_20181108	Quartet_DNA_ILM_Nova_ARD_LCL5_2_20181108	ILM_Nova_ARD_2
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL8_3_20181108.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL7_3_20181108.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL5_3_20181108.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL6_3_20181108.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL8_3_20181108.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL7_3_20181108.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL5_3_20181108.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL6_3_20181108.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_Nova_ARD_LCL8_3_20181108	Quartet_DNA_ILM_Nova_ARD_LCL7_3_20181108	Quartet_DNA_ILM_Nova_ARD_LCL5_3_20181108	ILM_Nova_ARD_3
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL8_4_20190111.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL7_4_20190111.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL5_4_20190111.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL6_4_20190111.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL8_4_20190111.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL7_4_20190111.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL5_4_20190111.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL6_4_20190111.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_Nova_ARD_LCL8_4_20190111	Quartet_DNA_ILM_Nova_ARD_LCL7_4_20190111	Quartet_DNA_ILM_Nova_ARD_LCL5_4_20190111	ILM_Nova_ARD_4
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL8_5_20190111.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL7_5_20190111.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL5_5_20190111.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL6_5_20190111.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL8_5_20190111.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL7_5_20190111.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL5_5_20190111.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL6_5_20190111.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_Nova_ARD_LCL8_5_20190111	Quartet_DNA_ILM_Nova_ARD_LCL7_5_20190111	Quartet_DNA_ILM_Nova_ARD_LCL5_5_20190111	ILM_Nova_ARD_5
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL8_6_20190111.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL7_6_20190111.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL5_6_20190111.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL6_6_20190111.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL8_6_20190111.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL7_6_20190111.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL5_6_20190111.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_ARD_LCL6_6_20190111.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_Nova_ARD_LCL8_6_20190111	Quartet_DNA_ILM_Nova_ARD_LCL7_6_20190111	Quartet_DNA_ILM_Nova_ARD_LCL5_6_20190111	ILM_Nova_ARD_6
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL8_1_20171024.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL7_1_20171024.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL5_1_20171024.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL6_1_20171024.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL8_1_20171024.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL7_1_20171024.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL5_1_20171024.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL6_1_20171024.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_Nova_BRG_LCL8_1_20171024	Quartet_DNA_ILM_Nova_BRG_LCL7_1_20171024	Quartet_DNA_ILM_Nova_BRG_LCL5_1_20171024	ILM_Nova_BRG_1
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL8_1_20180930.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL7_1_20180930.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL5_1_20180930.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL6_1_20180930.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL8_1_20180930.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL7_1_20180930.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL5_1_20180930.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL6_1_20180930.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_Nova_BRG_LCL8_1_20180930	Quartet_DNA_ILM_Nova_BRG_LCL7_1_20180930	Quartet_DNA_ILM_Nova_BRG_LCL5_1_20180930	ILM_Nova_BRG_2
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL8_2_20180930.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL7_2_20180930.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL5_2_20180930.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL6_2_20180930.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL8_2_20180930.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL7_2_20180930.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL5_2_20180930.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL6_2_20180930.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_Nova_BRG_LCL8_2_20180930	Quartet_DNA_ILM_Nova_BRG_LCL7_2_20180930	Quartet_DNA_ILM_Nova_BRG_LCL5_2_20180930	ILM_Nova_BRG_3
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL8_3_20180930.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL7_3_20180930.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL5_3_20180930.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL6_3_20180930.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL8_3_20180930.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL7_3_20180930.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL5_3_20180930.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_BRG_LCL6_3_20180930.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_Nova_BRG_LCL8_3_20180930	Quartet_DNA_ILM_Nova_BRG_LCL7_3_20180930	Quartet_DNA_ILM_Nova_BRG_LCL5_3_20180930	ILM_Nova_BRG_4
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_GAC_LCL8_1_20171025.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_GAC_LCL7_1_20171025.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_GAC_LCL5_1_20171025.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_GAC_LCL6_1_20171025.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_GAC_LCL8_1_20171025.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_GAC_LCL7_1_20171025.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_GAC_LCL5_1_20171025.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_GAC_LCL6_1_20171025.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_Nova_GAC_LCL8_1_20171025	Quartet_DNA_ILM_Nova_GAC_LCL7_1_20171025	Quartet_DNA_ILM_Nova_GAC_LCL5_1_20171025	ILM_Nova_GAC_1
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_NVG_LCL8_1_20171024.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_NVG_LCL7_1_20171024.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_NVG_LCL5_1_20171024.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_NVG_LCL6_1_20171024.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_NVG_LCL8_1_20171024.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_NVG_LCL7_1_20171024.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_NVG_LCL5_1_20171024.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_NVG_LCL6_1_20171024.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_Nova_NVG_LCL8_1_20171024	Quartet_DNA_ILM_Nova_NVG_LCL7_1_20171024	Quartet_DNA_ILM_Nova_NVG_LCL5_1_20171024	ILM_Nova_NVG_1
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_WUX_LCL8_1_20171024.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_WUX_LCL7_1_20171024.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_WUX_LCL5_1_20171024.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_WUX_LCL6_1_20171024.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_WUX_LCL8_1_20171024.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_WUX_LCL7_1_20171024.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_WUX_LCL5_1_20171024.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_Nova_WUX_LCL6_1_20171024.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_Nova_WUX_LCL8_1_20171024	Quartet_DNA_ILM_Nova_WUX_LCL7_1_20171024	Quartet_DNA_ILM_Nova_WUX_LCL5_1_20171024	ILM_Nova_WUX_1
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL8_1_20170403.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL7_1_20170403.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL5_1_20170403.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL6_1_20170403.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL8_1_20170403.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL7_1_20170403.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL5_1_20170403.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL6_1_20170403.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_XTen_ARD_LCL8_1_20170403	Quartet_DNA_ILM_XTen_ARD_LCL7_1_20170403	Quartet_DNA_ILM_XTen_ARD_LCL5_1_20170403	ILM_XTen_ARD_1
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL8_2_20170403.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL7_2_20170403.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL5_2_20170403.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL6_2_20170403.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL8_2_20170403.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL7_2_20170403.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL5_2_20170403.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL6_2_20170403.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_XTen_ARD_LCL8_2_20170403	Quartet_DNA_ILM_XTen_ARD_LCL7_2_20170403	Quartet_DNA_ILM_XTen_ARD_LCL5_2_20170403	ILM_XTen_ARD_2
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL8_3_20170403.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL7_3_20170403.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL5_3_20170403.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL6_3_20170403.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL8_3_20170403.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL7_3_20170403.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL5_3_20170403.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_ARD_LCL6_3_20170403.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_XTen_ARD_LCL8_3_20170403	Quartet_DNA_ILM_XTen_ARD_LCL7_3_20170403	Quartet_DNA_ILM_XTen_ARD_LCL5_3_20170403	ILM_XTen_ARD_3
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL8_1_20170329.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL7_1_20170329.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL5_1_20170329.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL6_1_20170329.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL8_1_20170329.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL7_1_20170329.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL5_1_20170329.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL6_1_20170329.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_XTen_NVG_LCL8_1_20170329	Quartet_DNA_ILM_XTen_NVG_LCL7_1_20170329	Quartet_DNA_ILM_XTen_NVG_LCL5_1_20170329	ILM_XTen_NVG_1
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL8_2_20170329.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL7_2_20170329.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL5_2_20170329.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL6_2_20170329.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL8_2_20170329.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL7_2_20170329.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL5_2_20170329.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL6_2_20170329.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_XTen_NVG_LCL8_2_20170329	Quartet_DNA_ILM_XTen_NVG_LCL7_2_20170329	Quartet_DNA_ILM_XTen_NVG_LCL5_2_20170329	ILM_XTen_NVG_2
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL8_3_20170329.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL7_3_20170329.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL5_3_20170329.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL6_3_20170329.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL8_3_20170329.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL7_3_20170329.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL5_3_20170329.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_NVG_LCL6_3_20170329.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_XTen_NVG_LCL8_3_20170329	Quartet_DNA_ILM_XTen_NVG_LCL7_3_20170329	Quartet_DNA_ILM_XTen_NVG_LCL5_3_20170329	ILM_XTen_NVG_3
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL8_1_20170216.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL7_1_20170216.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL5_1_20170216.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL6_1_20170216.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL8_1_20170216.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL7_1_20170216.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL5_1_20170216.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL6_1_20170216.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_XTen_WUX_LCL8_1_20170216	Quartet_DNA_ILM_XTen_WUX_LCL7_1_20170216	Quartet_DNA_ILM_XTen_WUX_LCL5_1_20170216	ILM_XTen_WUX_1
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL8_2_20170216.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL7_2_20170216.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL5_2_20170216.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL6_2_20170216.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL8_2_20170216.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL7_2_20170216.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL5_2_20170216.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL6_2_20170216.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_XTen_WUX_LCL8_2_20170216	Quartet_DNA_ILM_XTen_WUX_LCL7_2_20170216	Quartet_DNA_ILM_XTen_WUX_LCL5_2_20170216	ILM_XTen_WUX_2
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL8_3_20170216.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL7_3_20170216.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL5_3_20170216.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL6_3_20170216.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL8_3_20170216.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL7_3_20170216.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL5_3_20170216.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL6_3_20170216.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_XTen_WUX_LCL8_3_20170216	Quartet_DNA_ILM_XTen_WUX_LCL7_3_20170216	Quartet_DNA_ILM_XTen_WUX_LCL5_3_20170216	ILM_XTen_WUX_3
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL8_4_20180703.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL7_4_20180703.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL5_4_20180703.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL6_4_20180703.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL8_4_20180703.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL7_4_20180703.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL5_4_20180703.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL6_4_20180703.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_XTen_WUX_LCL8_4_20180703	Quartet_DNA_ILM_XTen_WUX_LCL7_4_20180703	Quartet_DNA_ILM_XTen_WUX_LCL5_4_20180703	ILM_XTen_WUX_4
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL8_5_20180703.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL7_5_20180703.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL5_5_20180703.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL6_5_20180703.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL8_5_20180703.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL7_5_20180703.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL5_5_20180703.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL6_5_20180703.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_XTen_WUX_LCL8_5_20180703	Quartet_DNA_ILM_XTen_WUX_LCL7_5_20180703	Quartet_DNA_ILM_XTen_WUX_LCL5_5_20180703	ILM_XTen_WUX_5
-oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL8_6_20180703.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL7_6_20180703.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL5_6_20180703.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL6_6_20180703.normed.callable.vcf.gz	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL8_6_20180703.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL7_6_20180703.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL5_6_20180703.normed.callable.vcf.gz.tbi	oss://pgx-result/renluyao/high_confidence_call/normed_vcf/Quartet_DNA_ILM_XTen_WUX_LCL6_6_20180703.normed.callable.vcf.gz.tbi	Quartet_DNA_ILM_XTen_WUX_LCL8_6_20180703	Quartet_DNA_ILM_XTen_WUX_LCL7_6_20180703	Quartet_DNA_ILM_XTen_WUX_LCL5_6_20180703	ILM_XTen_WUX_6
+#LCL5vcf	LCL6vcf	LCL7vcf	LCL8vcf	LCL5name	LCL6name	LCL7name	LCL8name	familyname

inputs

 {
-  "{{ project_name }}.sister.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.mendelian.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.disk_size": "100",
-  "{{ project_name }}.merge.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.fasta": "GRCh38.d1.vd1.fa",
+  "{{ project_name }}.LCL6mendelian.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/vbt:v1.1",
+  "{{ project_name }}.LCL5mendelian.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/vbt:v1.1",
+  "{{ project_name }}.disk_size": "150",
   "{{ project_name }}.inputSamplesFile": "{{ inputSamplesFile }}",
-  "{{ project_name }}.sdf": "oss://chinese-quartet/quartet-storage-data/reference_data/GRCh38.d1.vd1.sdf/",
-  "{{ project_name }}.cluster_config": "OnDemand bcs.a2.large img-ubuntu-vpc",
-  "{{ project_name }}.merge.sample_name": "{{ sample_name }}"
-  }
+  "{{ project_name }}.LCL6variantsNorm.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9"",
+  "{{ project_name }}.cluster_config": "OnDemand bcs.a2.xlarge img-ubuntu-vpc",
+  "{{ project_name }}.LCL7variantsNorm.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9"",
+  "{{ project_name }}.LCL5variantsNorm.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9"",
+  "{{ project_name }}.LCL8variantsNorm.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9"",
+  "{{ project_name }}.ref_dir": "oss://chinese-quartet/quartet-storage-data/reference_data/"
+}

tasks/ExtractVCFinfo.wdl

-task ExtractVCFinfo {
-	File snv_train
-	File snv_test
-	File indel_train
-	File indel_test
-	String snv_train_sampleName = basename(snv_train,".vcf")
-	String snv_test_sampleName = basename(snv_test,".vcf")
-	String indel_train_sampleName = basename(indel_train,".vcf")
-	String indel_test_sampleName = basename(indel_test,".vcf")	
-	String docker
-	String cluster_config
-	String disk_size
-	
-	command <<<
-		python /opt/extract_vcf_information.py -i ${snv_train} -o ${snv_train_sampleName}.txt
-		python /opt/extract_vcf_information.py -i ${snv_test} -o ${snv_test_sampleName}.txt
-		python /opt/extract_vcf_information.py -i ${indel_train} -o ${indel_train_sampleName}.txt
-		python /opt/extract_vcf_information.py -i ${indel_test} -o ${indel_test_sampleName}.txt
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-
-	output {
-		File snv_train_vcf = "${snv_train_sampleName}.txt"
-		File snv_test_vcf = "${snv_test_sampleName}.txt"
-		File indel_train_vcf = "${indel_train_sampleName}.txt"
-		File indel_test_vcf = "${indel_test_sampleName}.txt"
-	}
-}

tasks/KeepVar.wdl

-task KeepVar {
-	File violation_merged_vcf
-	File consistent_merged_vcf
-	String docker
-	String cluster_config
-	String disk_size
-	
-	command <<<
-		python /opt/select_small_variants_supported_by_all_callsets.py -i ${violation_merged_vcf} -o violation.all.selected
-
-		python /opt/select_small_variants_supported_by_all_callsets.py -i ${consistent_merged_vcf} -o consistent.all.selected
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-	output {
-		File violation_keeped_vcf = "violation.all.selected.vcf"
-		File violation_outlier_vcf = "violation.all.selected_outlier.vcf"
-		File consistent_keeped_vcf = "consistent.all.selected.vcf"
-		File consistent_outlier_vcf = "consistent.all.selected_outlier.vcf"
-	}
-}
-

tasks/SepSnvIndel.wdl

-task SepSnvIndel {
-	File vcf
-	String sampleName = basename(vcf,".normed.vcf")
-	File keeped_vcf
-	String docker
-	String cluster_config
-	String disk_size
-	
-	command <<<
-
-		cat ${vcf} | grep '#' > header
-		cat ${vcf} | sed '/^#/d' | awk '$5!~/,/' > removed.body
-		cat ${vcf} | sed '/^#/d' | awk '$5~/,/' > MNP.body
-		cat header removed.body > ${sampleName}.MNPremoved.vcf
-		cat header MNP.body > ${sampleName}.MNP.vcf
-
-		rtg bgzip ${sampleName}.MNPremoved.vcf
-		rtg index -f vcf ${sampleName}.MNPremoved.vcf.gz
-
-
-		rtg bgzip ${keeped_vcf} -c > all.selected.vcf.gz
-		rtg index -f vcf all.selected.vcf.gz
-
-		rtg vcffilter -i ${sampleName}.MNPremoved.vcf.gz -o ${sampleName}.normed.snv.train.vcf.gz --include-vcf=all.selected.vcf.gz --snps-only 
-
-		rtg vcffilter -i ${sampleName}.MNPremoved.vcf.gz -o ${sampleName}.normed.snv.test.vcf.gz --exclude-vcf=all.selected.vcf.gz --snps-only 
-
-		rtg vcffilter -i ${sampleName}.MNPremoved.vcf.gz -o ${sampleName}.normed.indel.train.vcf.gz --include-vcf=all.selected.vcf.gz --non-snps-only
-
-		rtg vcffilter -i ${sampleName}.MNPremoved.vcf.gz -o ${sampleName}.normed.indel.test.vcf.gz --exclude-vcf=all.selected.vcf.gz --non-snps-only
-
-		rtg vcffilter -i ${sampleName}.MNPremoved.vcf.gz -o ${sampleName}.normed.snv.vcf.gz --snps-only 
-
-		rtg vcffilter -i ${sampleName}.MNPremoved.vcf.gz -o ${sampleName}.normed.indel.vcf.gz --non-snps-only
-	
-
-		gzip -d ${sampleName}.normed.snv.train.vcf.gz -c > ${sampleName}.normed.snv.train.vcf
-		gzip -d ${sampleName}.normed.snv.test.vcf.gz -c > ${sampleName}.normed.snv.test.vcf
-		gzip -d ${sampleName}.normed.indel.train.vcf.gz -c > ${sampleName}.normed.indel.train.vcf
-		gzip -d ${sampleName}.normed.indel.test.vcf.gz -c > ${sampleName}.normed.indel.test.vcf
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-
-	output {
-		File MNP="${sampleName}.MNP.vcf"
-		File snv_gz = "${sampleName}.normed.snv.vcf.gz"
-		File snv_idx = "${sampleName}.normed.snv.vcf.gz.tbi"
-		File indel_gz = "${sampleName}.normed.indel.vcf.gz"
-		File indel_idx = "${sampleName}.normed.indel.vcf.gz.tbi"
-		File snv_train = "${sampleName}.normed.snv.train.vcf"
-		File snv_test = "${sampleName}.normed.snv.test.vcf"
-		File indel_train = "${sampleName}.normed.indel.train.vcf"
-		File indel_test = "${sampleName}.normed.indel.test.vcf"
-		File snv_train_gz = "${sampleName}.normed.snv.train.vcf.gz"
-		File snv_test_gz = "${sampleName}.normed.snv.test.vcf.gz"
-		File indel_train_gz = "${sampleName}.normed.indel.train.vcf.gz"
-		File indel_test_gz = "${sampleName}.normed.indel.test.vcf.gz"
-		File snv_train_idx = "${sampleName}.normed.snv.train.vcf.gz.tbi"
-		File snv_test_idx = "${sampleName}.normed.snv.test.vcf.gz.tbi"
-		File indel_train_idx = "${sampleName}.normed.indel.train.vcf.gz.tbi"
-		File indel_test_idx = "${sampleName}.normed.indel.test.vcf.gz.tbi"		
-	}
-}

tasks/SepTrueFalse.wdl

-task SepTrueFalse {
-	File snv_true_bed
-	File snv_false_bed
-	File indel_true_bed
-	File indel_false_bed
-	File snv_padding
-	File indel_padding
-
-	File snv_gz
-	File indel_gz
-	File snv_idx
-	File indel_idx
-	File snv_test_gz
-	File indel_test_gz
-	File snv_test_idx
-	File indel_test_idx	
-
-	String sampleName = basename(snv_gz,".normed.snv.vcf.gz")
-	String docker
-	String cluster_config
-	String disk_size
-
-	command <<<
-
-	rtg vcffilter -i ${snv_test_gz} -o ${sampleName}.true.snv.vcf.gz --include-bed=${snv_true_bed}
-
-	rtg vcffilter -i ${snv_test_gz} -o ${sampleName}.false.snv.vcf.gz --include-bed=${snv_false_bed}
-
-	rtg vcffilter -i ${snv_gz} -o ${sampleName}.remain.snv.vcf.gz --exclude-bed=${snv_false_bed}
-
-	rtg vcffilter -i ${snv_gz} -o ${sampleName}.padding.snv.vcf.gz --include-bed=${snv_padding}
-
-	
-	rtg vcffilter -i ${indel_test_gz} -o ${sampleName}.true.indel.vcf.gz --include-bed=${indel_true_bed}
-
-	rtg vcffilter -i ${indel_test_gz} -o ${sampleName}.false.indel.vcf.gz --include-bed=${indel_false_bed}
-
-	rtg vcffilter -i ${indel_gz} -o ${sampleName}.remain.indel.vcf.gz --exclude-bed=${indel_false_bed}
-
-	rtg vcffilter -i ${indel_gz} -o ${sampleName}.padding.indel.vcf.gz --include-bed=${indel_padding}
-
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-
-	output {
-		File snv_true_vcf = "${sampleName}.true.snv.vcf.gz"
-		File snv_true_vcf_index = "${sampleName}.true.snv.vcf.gz.tbi"
-		File snv_false_vcf = "${sampleName}.false.snv.vcf.gz"
-		File snv_false_vcf_index = "${sampleName}.false.snv.vcf.gz.tbi"
-		File snv_remain_vcf = "${sampleName}.remain.snv.vcf.gz"
-		File snv_remain_vcf_index = "${sampleName}.remain.snv.vcf.gz.tbi"
-		File snv_padding_vcf = "${sampleName}.padding.snv.vcf.gz"
-		File snv_padding_vcf_index = "${sampleName}.padding.snv.vcf.gz.tbi"
-
-		File indel_true_vcf = "${sampleName}.true.indel.vcf.gz"
-		File indel_true_vcf_index = "${sampleName}.true.indel.vcf.gz.tbi"
-		File indel_false_vcf = "${sampleName}.false.indel.vcf.gz"
-		File indel_false_vcf_index = "${sampleName}.false.indel.vcf.gz.tbi"
-		File indel_remain_vcf = "${sampleName}.remain.indel.vcf.gz"
-		File indel_remain_vcf_index = "${sampleName}.remain.indel.vcf.gz.tbi"
-		File indel_padding_vcf = "${sampleName}.padding.indel.vcf.gz"
-		File indel_padding_vcf_index = "${sampleName}.padding.indel.vcf.gz.tbi"
-	}
-}
-

tasks/VCFrename.wdl

+task VCFrename {
+	File trio_vcf_gz
+	File trio_vcf_idx
+	String mother_name
+	String father_name
+	String child_name
+	String family_name
+	String child
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+		echo "MOTHER ${mother_name}.${child}
+		FATHER ${father_name}.${child}
+		CHILD ${child_name}" > rename.txt
+
+		rtg vcfannotate -i ${trio_vcf_gz} -o ${family_name}.${child}.rename.vcf.gz --relabel=rename.txt
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File rename_trio_vcf_gz = "${family_name}.${child}.rename.vcf.gz"
+		File rename_trio_vcf_idx = "${family_name}.${child}.rename.vcf.gz.tbi"
+	}
+}

tasks/indelNorm.wdl

 
 		cat ${vcf} | grep '#' > header
 		cat ${vcf} | grep -v '#' > body
-		cat body | 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\|^chrY\|^chrM' > body.filtered
+		cat body | 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\' > body.filtered
 		cat header body.filtered > ${sampleName}.filtered.vcf
 
 		/opt/hall-lab/bcftools-1.9/bin/bcftools norm -f ${ref_dir}/${fasta} ${sampleName}.filtered.vcf > ${sampleName}.normed.vcf
+
 	>>>
 
 	runtime {

tasks/mendelian.wdl

 task mendelian {
-	File mother_vcf_gz
-	File father_vcf_gz
-	File child_vcf_gz
-	File mother_vcf_idx
-	File father_vcf_idx
-	File child_vcf_idx
-	String mother_name
-	String father_name
+	File child_vcf
+	File LCL7_vcf
+	File LCL8_vcf
+	String LCL7_name
+	String LCL8_name
 	String child_name
-	String family_name
-	File sdf
+	File ref_dir
+	String fasta
 	String docker
 	String cluster_config
 	String disk_size
 	
 	command <<<
-		rtg vcfmerge -o family.vcf.gz ${child_vcf_gz} ${mother_vcf_gz} ${father_vcf_gz}
+		export LD_LIBRARY_PATH=/opt/htslib-1.9
+		nt=$(nproc)
+		mkdir VBT
 
-		rtg vcfannotate -i family.vcf.gz -o family.anno.vcf.gz \
-		--add-header "##SAMPLE=<ID=${mother_name},Sex=FEMALE>" \
-		--add-header "##SAMPLE=<ID=${father_name},Sex=MALE>" \
-		--add-header "##SAMPLE=<ID=${child_name},Sex=FEMALE>" \
-		--add-header "##PEDIGREE=<Child=${child_name},Mother=${mother_name},Father=${father_name}>"
-
-		rtg mendelian -i family.anno.vcf.gz -t ${sdf} -o ${family_name}.family.anno.mendelian.vcf.gz --lenient
-
-		zcat ${family_name}.family.anno.mendelian.vcf.gz | grep '#' > header
-		zcat ${family_name}.family.anno.mendelian.vcf.gz | grep -v '#'| grep 'MCU\|MCV' | cat header -  > ${family_name}.violation.vcf
-		zcat ${family_name}.family.anno.mendelian.vcf.gz | grep -v '#'| grep -v 'MCV' | grep -v 'MCU' | cat header - > ${family_name}.consistent.vcf
-
-		rtg bgzip ${family_name}.violation.vcf 
-		rtg index -f vcf ${family_name}.violation.vcf.gz
-
-		rtg bgzip ${family_name}.consistent.vcf
-		rtg index -f vcf ${family_name}.consistent.vcf.gz
-
-		zcat ${child_vcf_gz} | grep '##' > child_header
-		zcat ${family_name}.violation.vcf.gz | grep -v '##' | cut -f1-10 | awk '$10!~/\./' | cat child_header - > ${child_name}.violation.vcf		
-		zcat ${family_name}.consistent.vcf.gz | grep -v '##' | cut -f1-10 | awk '$10!~/\./' | cat child_header - > ${child_name}.consistent.vcf
-
-		rtg bgzip ${child_name}.violation.vcf
-		rtg index -f vcf ${child_name}.violation.vcf.gz
-
-		rtg bgzip ${child_name}.consistent.vcf
-		rtg index -f vcf ${child_name}.consistent.vcf.gz
+		/opt/VBT-TrioAnalysis/vbt mendelian -ref ${ref_dir}/${fasta} -mother ${LCL8_vcf} -father ${LCL7_vcf} -child ${child_vcf} -outDir VBT -out-prefix ${child_name}.family --output-violation-regions -thread-count $nt
 
+		cat VBT/${child_name}.family_trio.vcf > ${child_name}.family.vcf
 	>>>
 
 	runtime {
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File family_vcf_gz = "${family_name}.family.anno.mendelian.vcf.gz"
-		File family_vcf_index = "${family_name}.family.anno.mendelian.vcf.gz.tbi"
-		File family_violation_vcf_gz = "${family_name}.violation.vcf.gz"
-		File family_violation_vcf_idx = "${family_name}.violation.vcf.gz.tbi"
-		File family_consistent_vcf_gz = "${family_name}.consistent.vcf.gz"
-		File family_consistent_vcf_idx = "${family_name}.consistent.vcf.gz.tbi"
-		File violation_vcf_gz = "${child_name}.violation.vcf.gz"
-		File violation_vcf_idx = "${child_name}.violation.vcf.gz.tbi"
-		File consistent_vcf_gz = "${child_name}.consistent.vcf.gz"
-		File consistent_vcf_idx = "${child_name}.consistent.vcf.gz.tbi"
+		Array[File] vbt_mendelian = glob("VBT/*")
+		File trio_vcf = "${child_name}.family.vcf"
 	}
 }

tasks/merge.wdl

 task merge {
-	Array[File] child_violation_sister
-	Array[File] child_violation_sister_idx
-	Array[File] child_violation_nonsister
-	Array[File] child_violation_nonsister_idx
-	Array[File] child_consistent_sister
-	Array[File] child_consistent_sister_idx
-	Array[File] child_consistent_nonsister
-	Array[File] child_consistent_nonsister_idx
-	String sample_name
+	Array[File] family_vcf_gz
+	Array[File] family_vcf_idx
+	String sample
 	String docker
 	String cluster_config
 	String disk_size
 	
 	command <<<
-		rtg vcfmerge --force-merge-all --no-gzip -o ${sample_name}.violation.sister.vcf ${sep=" " child_violation_sister}
 
-		rtg vcfmerge --force-merge-all --no-gzip -o ${sample_name}.violation.nonsister.vcf ${sep=" " child_violation_nonsister}
+		rtg vcfmerge --force-merge-all --no-gzip -o ${sample}.merged.vcf ${sep=" " family_vcf_gz}
+
+		cat ${sample}.merged.vcf | grep -v '#' | cut -f1-2 | sed s'/\t/_/g' | sort | uniq -c | sed 's/\s\+/\t/g' | awk '{ if ($1 != 1) { print } }' | cut -f3 > ${sample}.vcf_dup.txt
 
-		rtg vcfmerge --force-merge-all --no-gzip -o ${sample_name}.consistent.sister.vcf ${sep=" " child_consistent_sister}
-		
-		rtg vcfmerge --force-merge-all --no-gzip -o ${sample_name}.consistent.nonsister.vcf ${sep=" " child_consistent_nonsister}
 	>>>
 
 	runtime {
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File violation_sister_merged_vcf = "${sample_name}.violation.sister.vcf"
-		File violation_nonsister_merged_vcf = "${sample_name}.violation.nonsister.vcf"
-		File consistent_sister_merged_vcf = "${sample_name}.consistent.sister.vcf"
-		File consistent_nonsister_merged_vcf = "${sample_name}.consistent.nonsister.vcf"
+		File merged_vcf = "${sample}.merged.vcf"
+		File vcf_dup = "${sample}.vcf_dup.txt"
 	}
 }

tasks/mergeBed.wdl

-task mergeBed {
-	Array[File] snv_true_bed
-	Array[File] snv_false_bed
-	Array[File] indel_true_bed
-	Array[File] indel_false_bed
-	Array[File]	indel_padding
-	Array[File] snv_padding
-	String docker
-	String cluster_config
-	String disk_size
-	
-	command <<<
-
-	/opt/ccdg/bedtools-2.27.1/bin/bedtools multiinter -i ${sep=" " snv_true_bed} ${sep=" " indel_true_bed}  > merged.true.bed
-
-	/opt/ccdg/bedtools-2.27.1/bin/bedtools multiinter -i ${sep=" " snv_false_bed} ${sep=" " indel_false_bed}  > merged.false.bed
-
-	/opt/ccdg/bedtools-2.27.1/bin/bedtools multiinter -i ${sep=" " snv_padding} ${sep=" " indel_padding}  > merged.padding.bed	
-
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-
-	output {
-		File true_bed = "merged.true.bed"
-		File false_bed = "merged.false.bed"
-		File padding = "merged.padding.bed"
-	}
-}
-

tasks/mergeSister.wdl

+task mergeSister {
+	File LCL5_trio_vcf_gz
+	File LCL5_trio_vcf_idx
+	File LCL6_trio_vcf_gz
+	File LCL6_trio_vcf_idx
+	String family_name
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+		rtg vcfmerge -o LCL5.LCL6.merged.vcf.gz ${LCL5_trio_vcf_gz} ${LCL6_trio_vcf_gz}
+
+		rtg vcfmerge -o LCL6.LCL5.merged.vcf.gz ${LCL6_trio_vcf_gz} ${LCL5_trio_vcf_gz}
+
+		zcat LCL5.LCL6.merged.vcf.gz | grep '##' > header
+		zcat LCL5.LCL6.merged.vcf.gz | grep -v '##' | cut -f8 > LCL5.mendelian
+		zcat LCL6.LCL5.merged.vcf.gz | grep -v '##' | paste - LCL5.mendelian > body
+
+		cat header body > ${family_name}.trio.info.vcf
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File family_mendelian_info = "${family_name}.trio.info.vcf"
+	}
+
+}

tasks/mergeVCF.wdl

-task mergeVCF {
-	Array[File] snv_true_vcf
-	Array[File] snv_true_vcf_index
-	Array[File] snv_false_vcf
-	Array[File] snv_false_vcf_index
-	Array[File] snv_remain_vcf
-	Array[File] snv_remain_vcf_index
-	Array[File] snv_padding_vcf
-	Array[File] snv_padding_vcf_index
-
-	Array[File] indel_true_vcf
-	Array[File] indel_true_vcf_index
-	Array[File] indel_false_vcf
-	Array[File] indel_false_vcf_index
-	Array[File] indel_remain_vcf
-	Array[File] indel_remain_vcf_index 
-	Array[File] indel_padding_vcf
-	Array[File] indel_padding_vcf_index
-
-	String quartet_sample
-	String docker
-	String cluster_config
-	String disk_size
-	
-	command <<<
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.snv.true.vcf.gz ${sep=" " snv_true_vcf}
-
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.snv.false.vcf.gz ${sep=" " snv_false_vcf}
-
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.snv.remain.vcf.gz ${sep=" " snv_remain_vcf}
-
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.snv.padding.vcf.gz ${sep=" " snv_padding_vcf}
-
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.indel.true.vcf.gz ${sep=" " indel_true_vcf}
-
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.indel.false.vcf.gz ${sep=" " indel_false_vcf}
-
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.indel.remain.vcf.gz ${sep=" " indel_remain_vcf}
-
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.indel.padding.vcf.gz ${sep=" " indel_padding_vcf}
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-
-	output {
-		File merged_snv_true = "${quartet_sample}.snv.true.vcf.gz"
-		File merged_snv_false = "${quartet_sample}.snv.false.vcf.gz"
-		File merged_snv_remain = "${quartet_sample}.snv.remain.vcf.gz"
-		File merged_snv_padding = "${quartet_sample}.snv.padding.vcf.gz"
-		File merged_indel_true = "${quartet_sample}.indel.true.vcf.gz"
-		File merged_indel_false = "${quartet_sample}.indel.false.vcf.gz"
-		File merged_indel_remain = "${quartet_sample}.indel.remain.vcf.gz"
-		File merged_indel_padding = "${quartet_sample}.indel.padding.vcf.gz"
-	}
-
-}

tasks/reformVCF.wdl

+task reformVCF {
+	File family_mendelian_info
+	File family_name
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+
+	python /opt/reformVCF.py -vcf ${family_mendelian_info} -name ${family_name}
+	
+
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File LCL5_family_info = "${family_name}.LCL5.vcf"
+		File LCL6_family_info = "${family_name}.LCL6.vcf"
+		File LCL7_family_info = "${family_name}.LCL7.vcf"
+		File LCL8_family_info = "${family_name}.LCL8.vcf"
+		File family_info = "${family_name}.vcf"
+	}
+}
+

tasks/sister.wdl

 task sister {
-	File violation_vcf_gz
-	File violation_vcf_idx
-	File consistent_vcf_gz
-	File consistent_vcf_idx
-	File sister_vcf_gz
-	File sister_vcf_idx
-	File sdf
+	File LCL5_vcf
+	File LCL6_vcf
+	File ref_dir
+	String fasta
 	String family_name
 	String docker
 	String cluster_config
 	String disk_size
 	
 	command <<<
-		rtg vcfeval -b ${sister_vcf_gz} -c ${violation_vcf_gz} -o violation -t ${sdf}
+		export LD_LIBRARY_PATH=/opt/htslib-1.9
 
-		rtg vcfeval -b ${sister_vcf_gz} -c ${consistent_vcf_gz} -o consistent -t ${sdf}
+		mkdir sister
+		/opt/VBT-TrioAnalysis/vbt varcomp -called ${LCL5_vcf} -base ${LCL6_vcf} -ref ${ref_dir}/${fasta} -outDir sister -filter none
 
-		mv violation/tp.vcf.gz ${family_name}.violation.sister.vcf.gz
-		mv violation/fp.vcf.gz ${family_name}.violation.nonsister.vcf.gz
-		mv violation/tp.vcf.gz.tbi ${family_name}.violation.sister.vcf.gz.tbi
-		mv violation/fp.vcf.gz.tbi ${family_name}.violation.nonsister.vcf.gz.tbi
-		mv violation/summary.txt ${family_name}.violation.summary.txt
-
-		mv consistent/tp.vcf.gz ${family_name}.consistent.sister.vcf.gz
-		mv consistent/fp.vcf.gz ${family_name}.consistent.nonsister.vcf.gz
-		mv consistent/tp.vcf.gz.tbi ${family_name}.consistent.sister.vcf.gz.tbi
-		mv consistent/fp.vcf.gz.tbi ${family_name}.consistent.nonsister.vcf.gz.tbi		
-		mv consistent/summary.txt ${family_name}.consistent.summary.txt
+		mv sister/TPBase.vcf ${family_name}.sister.consistent.vcf
+		mv sister/FP.vcf ${family_name}.LCL5.uniq.vcf
+		mv sister/FN.vcf ${family_name}.LCL6.uniq.vcf
+		mv sister/log.txt ${family_name}.sister.vbt.log.txt
 	>>>
 
 	runtime {
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File child_violation_sister = "${family_name}.violation.sister.vcf.gz"
-		File child_violation_sister_idx = "${family_name}.violation.sister.vcf.gz.tbi"
-		File child_violation_nonsister = "${family_name}.violation.nonsister.vcf.gz"
-		File child_violation_nonsister_idx = "${family_name}.violation.nonsister.vcf.gz.tbi"
-		File child_consistent_sister = "${family_name}.consistent.sister.vcf.gz"
-		File child_consistent_sister_idx = "${family_name}.consistent.sister.vcf.gz.tbi"
-		File child_consistent_nonsister = "${family_name}.consistent.nonsister.vcf.gz"
-		File child_consistent_nonsister_idx = "${family_name}.consistent.nonsister.vcf.gz.tbi"
-		File violation_summary = "${family_name}.violation.summary.txt"
-		File consistent_summary = "${family_name}.consistent.summary.txt"	
+		File sister_consistent_vcf = "${family_name}.sister.consistent.vcf"
+		File LCL5_uniq = "${family_name}.LCL5.uniq.vcf"
+		File LCL6_uniq = "${family_name}.LCL6.uniq.vcf"
+		File log = "${family_name}.sister.vbt.log.txt"
 	}
 }

tasks/variantsNorm.wdl

+task variantsNorm {
+	File vcf
+	File ref_dir
+	String fasta
+	String sampleName
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+
+		cat ${vcf} | grep '#' > header
+		cat ${vcf} | grep -v '#' > body
+		cat body | 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' > body.filtered
+		cat header body.filtered > ${sampleName}.filtered.vcf
+
+		/opt/hall-lab/bcftools-1.9/bin/bcftools norm -f ${ref_dir}/${fasta} ${sampleName}.filtered.vcf > ${sampleName}.normed.vcf
+
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File normed_vcf = "${sampleName}.normed.vcf"
+	}
+}

tasks/votes.wdl

+task votes {
+	File merged_vcf
+	File vcf_dup
+	String sample
+	String prefix
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+		python /opt/high_confidence_call_vote.py -vcf ${merged_vcf} -dup ${vcf_dup} -sample ${sample} -prefix ${prefix}
+		cat ${prefix}_annotated.vcf | cut -f1-9,45 | grep -v 'filtered' | grep -v 'confirm for parents' | grep -v 'pcr-free-speicifc' | grep -v 'pcr-speicifc' | grep -v 'dupVar' > ${prefix}_bechmarking_calls.vcf
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File annotated_vcf = "${prefix}_annotated.vcf"
+		File benchmark_call = "${prefix}_bechmarking_calls.vcf"
+	}
+}

tasks/zipIndex.wdl

 task zipIndex {
-	File violation_vcf
-	File consistent_vcf
-	File child_vcf_gz
-	File child_vcf_idx
-	File child_name
+	File vcf
+	String sample
 	String family_name
 	String docker
 	String cluster_config
 	String disk_size
 	
 	command <<<
-		rtg bgzip ${violation_vcf} -c > ${family_name}.violation.vcf.gz
-		rtg index -f vcf ${family_name}.violation.vcf.gz
-
-		rtg bgzip ${consistent_vcf} -c > ${family_name}.consistent.vcf
-		rtg index -f vcf ${family_name}.consistent.vcf.gz
-
-		rtg vcffilter -i ${child_vcf_gz} -o ${child_name}.violation.vcf.gz --include-vcf=${family_name}.violation.vcf.gz
-
-		rtg vcffilter -i ${child_vcf_gz} -o ${child_name}.consistent.vcf.gz --include-vcf=${family_name}.consistent.vcf.gz		
+		rtg bgzip ${vcf} -c > ${family_name}.${sample}.vcf.gz
+		rtg index -f vcf ${family_name}.${sample}.vcf.gz
 
 	>>>
 
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File violation_vcf_gz = "${child_name}.violation.vcf.gz"
-		File violation_vcf_idx = "${child_name}.violation.vcf.gz.tbi"
-		File consistent_vcf_gz = "${child_name}.consistent.vcf"
-		File consistent_vcf_idx = "${child_name}.consistent.vcf.tbi"
+		File vcf_gz = "${family_name}.${sample}.vcf.gz"
+		File vcf_idx = "${family_name}.${sample}.vcf.gz.tbi"
 	}
 }

workflow.wdl

+import "./tasks/variantsNorm.wdl" as variantsNorm
 import "./tasks/mendelian.wdl" as mendelian
-import "./tasks/sister.wdl" as sister
-import "./tasks/merge.wdl" as merge
- 
+
 workflow {{ project_name }} {
 	File inputSamplesFile
 	Array[Array[File]] inputSamples = read_tsv(inputSamplesFile)
-	File sdf
+	File ref_dir
+	String fasta
 	String cluster_config
 	String disk_size
 
-	scatter (sample in inputSamples){
-		call mendelian.mendelian as mendelian {
-			input: 
-			mother_vcf_gz=sample[0],
-			father_vcf_gz=sample[1],
-			child_vcf_gz=sample[2],
-			mother_vcf_idx=sample[4],
-			father_vcf_idx=sample[5],
-			child_vcf_idx=sample[6],
-			mother_name=sample[8],
-			father_name=sample[9],
-			child_name=sample[10],
-			family_name=sample[11],
-			sdf=sdf,
+	scatter (quartet in inputSamples){
+		call variantsNorm.variantsNorm as LCL5variantsNorm{
+			input:
+			vcf=quartet[0],
+			ref_dir=ref_dir,
+			fasta=fasta,
+			sampleName=quartet[4],
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}
-
-		call sister.sister as sister {
+		call variantsNorm.variantsNorm as LCL6variantsNorm{
 			input:
-			violation_vcf_gz=mendelian.violation_vcf_gz,
-			violation_vcf_idx=mendelian.violation_vcf_idx,
-			consistent_vcf_gz=mendelian.consistent_vcf_gz,
-			consistent_vcf_idx=mendelian.consistent_vcf_idx,
-			sister_vcf_gz=sample[3],
-			sister_vcf_idx=sample[7],
-			sdf=sdf,
-			family_name=sample[11],
+			vcf=quartet[1],
+			ref_dir=ref_dir,
+			fasta=fasta,
+			sampleName=quartet[5],
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call variantsNorm.variantsNorm as LCL7variantsNorm{
+			input:
+			vcf=quartet[2],
+			ref_dir=ref_dir,
+			fasta=fasta,
+			sampleName=quartet[6],
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call variantsNorm.variantsNorm as LCL8variantsNorm{
+			input:
+			vcf=quartet[3],
+			ref_dir=ref_dir,
+			fasta=fasta,
+			sampleName=quartet[7],
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call mendelian.mendelian as LCL5mendelian {
+			input:
+			child_vcf=LCL5variantsNorm.normed_vcf,
+			LCL7_vcf=LCL7variantsNorm.normed_vcf,
+			LCL8_vcf=LCL8variantsNorm.normed_vcf,
+			LCL7_name=quartet[6],
+			LCL8_name=quartet[7],
+			child_name=quartet[4],
+			ref_dir=ref_dir,
+			fasta=fasta,
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call mendelian.mendelian as LCL6mendelian {
+			input:
+			child_vcf=LCL6variantsNorm.normed_vcf,
+			LCL7_vcf=LCL7variantsNorm.normed_vcf,
+			LCL8_vcf=LCL8variantsNorm.normed_vcf,
+			LCL7_name=quartet[6],
+			LCL8_name=quartet[7],
+			child_name=quartet[5],
+			ref_dir=ref_dir,
+			fasta=fasta,
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}
-
-	}
-
-	call merge.merge as merge {
-		input:
-		child_violation_sister=sister.child_violation_sister,
-		child_violation_sister_idx=sister.child_violation_sister_idx,
-		child_violation_nonsister=sister.child_violation_nonsister,
-		child_violation_nonsister_idx=sister.child_violation_nonsister_idx,
-		child_consistent_sister=sister.child_consistent_sister,
-		child_consistent_sister_idx=sister.child_consistent_sister_idx,
-		child_consistent_nonsister=sister.child_consistent_nonsister,
-		child_consistent_nonsister_idx=sister.child_consistent_nonsister_idx,
-		cluster_config=cluster_config,
-		disk_size=disk_size
 	}
 }