final result

codescripts/FinalResult2VCF.py

@@ -0,0 +1,285 @@
+import pandas as pd
+import sys, argparse, os
+import fileinput
+import re
+
+# input arguments
+parser = argparse.ArgumentParser(description="this script is to get final high confidence calls and information of all replicates")
+
+parser.add_argument('-vcfInfo', '--vcfInfo', type=str, help='The txt file of variants information, this file is named as prefix__variant_quality_location.txt',  required=True)
+parser.add_argument('-mendelianInfo', '--mendelianInfo', type=str, help='The merged mendelian information of all samples',  required=True)
+parser.add_argument('-prefix', '--prefix', type=str, help='The prefix of output filenames',  required=True)
+parser.add_argument('-sample', '--sample_name', type=str, help='which sample of quartet',  required=True)
+
+
+args = parser.parse_args()
+vcfInfo = args.vcfInfo
+mendelianInfo = args.mendelianInfo
+prefix = args.prefix
+sample_name = args.sample_name
+
+vcf_header = '''##fileformat=VCFv4.2
+##fileDate=20200331
+##source=high_confidence_calls_intergration(choppy app)
+##reference=GRCh38.d1.vd1
+##INFO=<ID=location,Number=1,Type=String,Description="Repeat region">
+##INFO=<ID=DPCT,Number=1,Type=Float,Description="Percentage of detected votes">
+##INFO=<ID=VPCT,Number=1,Type=Float,Description="Percentage of consnesus votes">
+##INFO=<ID=FPCT,Number=1,Type=Float,Description="Percentage of mendelian consisitent votes">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=DP,Number=1,Type=Int,Description="Depth">
+##FORMAT=<ID=AF,Number=1,Type=Float,Description="Allele frequency">
+##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype quality">
+##FORMAT=<ID=MQ,Number=1,Type=Float,Description="Mapping quality">
+##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>
+'''
+
+vcf_header_all_sample = '''##fileformat=VCFv4.2
+##fileDate=20200331
+##reference=GRCh38.d1.vd1
+##INFO=<ID=location,Number=1,Type=String,Description="Repeat region">
+##INFO=<ID=DPCT,Number=1,Type=Float,Description="Percentage of detected votes">
+##INFO=<ID=VPCT,Number=1,Type=Float,Description="Percentage of consnesus votes">
+##INFO=<ID=FPCT,Number=1,Type=Float,Description="Percentage of mendelian consisitent votes">
+##INFO=<ID=ALL_ALT,Number=1,Type=Float,Description="Sum of alternative reads of all samples">
+##INFO=<ID=ALL_DP,Number=1,Type=Float,Description="Sum of depth of all samples">
+##INFO=<ID=ALL_AF,Number=1,Type=Float,Description="Allele frequency of net alternatice reads and net depth">
+##INFO=<ID=GQ_MEAN,Number=1,Type=Float,Description="Mean of genotype quality of all samples">
+##INFO=<ID=MQ_MEAN,Number=1,Type=Float,Description="Mean of mapping quality of all samples">
+##INFO=<ID=PCR,Number=1,Type=String,Description="Consensus of PCR votes">
+##INFO=<ID=PCR_FREE,Number=1,Type=String,Description="Consensus of PCR-free votes">
+##INFO=<ID=CONSENSUS,Number=1,Type=String,Description="Consensus calls">
+##INFO=<ID=CONSENSUS_SEQ,Number=1,Type=String,Description="Consensus sequence">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=DP,Number=1,Type=String,Description="Depth">
+##FORMAT=<ID=AF,Number=1,Type=String,Description="Allele frequency">
+##FORMAT=<ID=GQ,Number=1,Type=String,Description="Genotype quality">
+##FORMAT=<ID=MQ,Number=1,Type=String,Description="Mapping quality">
+##FORMAT=<ID=TWINS,Number=1,Type=String,Description="1 is twins shared, 0 is twins discordant ">
+##FORMAT=<ID=TRIO5,Number=1,Type=String,Description="1 is LCL7, LCL8 and LCL5 mendelian consistent, 0 is mendelian vioaltion">
+##FORMAT=<ID=TRIO6,Number=1,Type=String,Description="1 is LCL7, LCL8 and LCL6 mendelian consistent, 0 is mendelian vioaltion">
+##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>
+'''
+
+# output file
+file_name = prefix + '_benchmarking_calls.vcf'
+outfile = open(file_name,'w')
+
+all_sample_file_name = prefix + '_all_sample_information.vcf'
+all_sample_outfile = open(all_sample_file_name, 'w')
+
+# write VCF
+outputcolumn = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t' + sample_name + '_high_confidence_calls\n'
+outfile.write(vcf_header)
+outfile.write(outputcolumn)
+
+outputcolumn_all_sample = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t'+ \
+'Quartet_DNA_BGI_SEQ2000_BGI_1_20180518\tQuartet_DNA_BGI_SEQ2000_BGI_2_20180530\tQuartet_DNA_BGI_SEQ2000_BGI_3_20180530\t' + \
+'Quartet_DNA_BGI_T7_WGE_1_20191105\tQuartet_DNA_BGI_T7_WGE_2_20191105\tQuartet_DNA_BGI_T7_WGE_3_20191105\t' + \
+'Quartet_DNA_ILM_Nova_ARD_1_20181108\tQuartet_DNA_ILM_Nova_ARD_2_20181108\tQuartet_DNA_ILM_Nova_ARD_3_20181108\t' + \
+'Quartet_DNA_ILM_Nova_ARD_4_20190111\tQuartet_DNA_ILM_Nova_ARD_5_20190111\tQuartet_DNA_ILM_Nova_ARD_6_20190111\t' + \
+'Quartet_DNA_ILM_Nova_BRG_1_20180930\tQuartet_DNA_ILM_Nova_BRG_2_20180930\tQuartet_DNA_ILM_Nova_BRG_3_20180930\t' + \
+'Quartet_DNA_ILM_Nova_WUX_1_20190917\tQuartet_DNA_ILM_Nova_WUX_2_20190917\tQuartet_DNA_ILM_Nova_WUX_3_20190917\t' + \
+'Quartet_DNA_ILM_XTen_ARD_1_20170403\tQuartet_DNA_ILM_XTen_ARD_2_20170403\tQuartet_DNA_ILM_XTen_ARD_3_20170403\t' + \
+'Quartet_DNA_ILM_XTen_NVG_1_20170329\tQuartet_DNA_ILM_XTen_NVG_2_20170329\tQuartet_DNA_ILM_XTen_NVG_3_20170329\t' + \
+'Quartet_DNA_ILM_XTen_WUX_1_20170216\tQuartet_DNA_ILM_XTen_WUX_2_20170216\tQuartet_DNA_ILM_XTen_WUX_3_20170216\n'
+all_sample_outfile.write(vcf_header_all_sample)
+all_sample_outfile.write(outputcolumn_all_sample)
+
+# input files
+vcf_info = pd.read_table(vcfInfo)
+mendelian_info = pd.read_table(mendelianInfo)
+
+merged_df = pd.merge(vcf_info, mendelian_info,  how='outer', left_on=['#CHROM','POS','REF'], right_on = ['#CHROM','POS','REF'])
+merged_df = merged_df.fillna('.')
+
+# function
+def single_sample_format(format_x,strings_x,strings_y):
+	gt = '.'
+	dp = '.'
+	af = '.'
+	gq = '.'
+	mq = '.'
+	twins = '.'
+	trio5 = '.'
+	trio6 = '.'
+	# GT:DP:AF:GQ:MQ:TWINS:TRIO5:TRIO6
+	# strings_x
+	format_strings = format_x.split(':')
+	if (strings_x == '.') and (strings_y != '.'):
+		element_strings_y = str(strings_y).split(':')
+		gt = '0/0'
+		dp = '.'
+		af = '.'
+		gq = '.'
+		mq = '.'
+		twins = element_strings_y[1]
+		trio5 = element_strings_y[2]
+		trio6 = element_strings_y[3]		
+	elif (strings_x != '.') and (strings_y == '.'):
+		element_strings_x = strings_x.split(':')
+		formatDict = dict(zip(format_strings, element_strings_x))
+		gt = formatDict['GT']
+		dp = formatDict['DP']
+		af = formatDict['AF']
+		gq = formatDict['GQ']
+		mq = formatDict['MQ']
+		twins = '.'
+		trio5 = '.'
+		trio6 = '.'
+	elif (strings_x != '.') and (strings_y != '.'):
+		element_strings_y = str(strings_y).split(':')
+		element_strings_x = strings_x.split(':')
+		formatDict = dict(zip(format_strings, element_strings_x))
+		gt = formatDict['GT']
+		dp = formatDict['DP']
+		af = formatDict['AF']
+		gq = formatDict['GQ']
+		mq = formatDict['MQ']
+		twins = element_strings_y[1]
+		trio5 = element_strings_y[2]
+		trio6 = element_strings_y[3]				
+	else:
+		pass
+	merged_format = gt + ':' + dp + ':' + af + ':' + gq + ':' + mq + ':' + twins + ':' + trio5 + ':' + trio6
+	return(merged_format)
+
+#
+for row in merged_df.itertuples():
+	info = 'location=' + str(row.location) + ';' + str(row.INFO_y)
+	if row.FILTER_y == 'reproducible':
+		ref = row.DP - row._42
+		FORMAT = row[77] + ':' + str(int(ref)) + ',' + str(int(row._42)) + ':' + str(int(row.DP)) + ':' + str(round(row.AF,2)) + ':' + str(round(row.GQ,2)) + ':' + str(round(row.MQ,2))
+		outline1 = str(row._1) + '\t' + str(row.POS) + '\t' + str(row.ID_x) + '\t' +  str(row.REF) + '\t' + str(row[78]) + '\t' + '.' + '\t' + '.' + '\t' + str(info) + '\t' + 'GT:AD:DP:AF:GQ:MQ' + '\t' + str(FORMAT) + '\n'
+		outfile.write(outline1)
+	else:
+		pass
+	if row.INFO_x != '.':
+		info = 'location=' + str(row.location) + ';' + str(row.INFO_y) + ';' + 'ALL_ALT=' + str(int(row._42)) + ';' + 'ALL_DP=' + str(int(row.DP)) + ';' + 'ALL_AF=' + str(round(row.AF,1)) + ';' + 'GQ_MEAN=' + str(round(row.GQ,1)) + ';' + 'MQ_MEAN=' + str(round(row.MQ,1)) + ';' + 'PCR=' + str(row[75]) + ';' + 'PCR_FREE=' + str(row[76]) + ';' + 'CONSENSUS=' + str(row[77]) + ';' + 'CONSENSUS_SEQ=' + str(row[78])
+		Quartet_DNA_BGI_SEQ2000_BGI_1_20180518_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_BGI_SEQ2000_BGI_1_20180518_LCL5_x, row.Quartet_DNA_BGI_SEQ2000_BGI_1_20180518_LCL5_y)
+		Quartet_DNA_BGI_SEQ2000_BGI_2_20180530_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_BGI_SEQ2000_BGI_2_20180530_LCL5_x, row.Quartet_DNA_BGI_SEQ2000_BGI_2_20180530_LCL5_y)
+		Quartet_DNA_BGI_SEQ2000_BGI_3_20180530_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_BGI_SEQ2000_BGI_3_20180530_LCL5_x, row.Quartet_DNA_BGI_SEQ2000_BGI_3_20180530_LCL5_y)
+		Quartet_DNA_BGI_T7_WGE_1_20191105_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_BGI_T7_WGE_1_20191105_LCL5_x, row.Quartet_DNA_BGI_T7_WGE_1_20191105_LCL5_y)
+		Quartet_DNA_BGI_T7_WGE_2_20191105_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_BGI_T7_WGE_2_20191105_LCL5_x, row.Quartet_DNA_BGI_T7_WGE_2_20191105_LCL5_y)
+		Quartet_DNA_BGI_T7_WGE_3_20191105_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_BGI_T7_WGE_3_20191105_LCL5_x, row.Quartet_DNA_BGI_T7_WGE_3_20191105_LCL5_y)
+		Quartet_DNA_ILM_Nova_ARD_1_20181108_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_ARD_1_20181108_LCL5_x, row.Quartet_DNA_ILM_Nova_ARD_1_20181108_LCL5_y)
+		Quartet_DNA_ILM_Nova_ARD_2_20181108_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_ARD_2_20181108_LCL5_x, row.Quartet_DNA_ILM_Nova_ARD_2_20181108_LCL5_y)
+		Quartet_DNA_ILM_Nova_ARD_3_20181108_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_ARD_3_20181108_LCL5_x, row.Quartet_DNA_ILM_Nova_ARD_3_20181108_LCL5_y)
+		Quartet_DNA_ILM_Nova_ARD_4_20190111_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_ARD_4_20190111_LCL5_x, row.Quartet_DNA_ILM_Nova_ARD_4_20190111_LCL5_y)
+		Quartet_DNA_ILM_Nova_ARD_5_20190111_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_ARD_5_20190111_LCL5_x, row.Quartet_DNA_ILM_Nova_ARD_5_20190111_LCL5_y)
+		Quartet_DNA_ILM_Nova_ARD_6_20190111_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_ARD_6_20190111_LCL5_x, row.Quartet_DNA_ILM_Nova_ARD_6_20190111_LCL5_y)
+		Quartet_DNA_ILM_Nova_BRG_1_20180930_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_BRG_1_20180930_LCL5_x, row.Quartet_DNA_ILM_Nova_BRG_1_20180930_LCL5_y)
+		Quartet_DNA_ILM_Nova_BRG_2_20180930_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_BRG_2_20180930_LCL5_x, row.Quartet_DNA_ILM_Nova_BRG_2_20180930_LCL5_y)
+		Quartet_DNA_ILM_Nova_BRG_3_20180930_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_BRG_3_20180930_LCL5_x, row.Quartet_DNA_ILM_Nova_BRG_3_20180930_LCL5_y)
+		Quartet_DNA_ILM_Nova_WUX_1_20190917_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_WUX_1_20190917_LCL5_x, row.Quartet_DNA_ILM_Nova_WUX_1_20190917_LCL5_y)
+		Quartet_DNA_ILM_Nova_WUX_2_20190917_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_WUX_2_20190917_LCL5_x, row.Quartet_DNA_ILM_Nova_WUX_2_20190917_LCL5_y)
+		Quartet_DNA_ILM_Nova_WUX_3_20190917_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_WUX_3_20190917_LCL5_x, row.Quartet_DNA_ILM_Nova_WUX_3_20190917_LCL5_y)
+		Quartet_DNA_ILM_XTen_ARD_1_20170403_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_ARD_1_20170403_LCL5_x, row.Quartet_DNA_ILM_XTen_ARD_1_20170403_LCL5_y)
+		Quartet_DNA_ILM_XTen_ARD_2_20170403_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_ARD_2_20170403_LCL5_x, row.Quartet_DNA_ILM_XTen_ARD_2_20170403_LCL5_y)
+		Quartet_DNA_ILM_XTen_ARD_3_20170403_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_ARD_3_20170403_LCL5_x, row.Quartet_DNA_ILM_XTen_ARD_3_20170403_LCL5_y)
+		Quartet_DNA_ILM_XTen_NVG_1_20170329_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_NVG_1_20170329_LCL5_x, row.Quartet_DNA_ILM_XTen_NVG_1_20170329_LCL5_y)
+		Quartet_DNA_ILM_XTen_NVG_2_20170329_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_NVG_2_20170329_LCL5_x, row.Quartet_DNA_ILM_XTen_NVG_2_20170329_LCL5_y)
+		Quartet_DNA_ILM_XTen_NVG_3_20170329_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_NVG_3_20170329_LCL5_x, row.Quartet_DNA_ILM_XTen_NVG_3_20170329_LCL5_y)
+		Quartet_DNA_ILM_XTen_WUX_1_20170216_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_WUX_1_20170216_LCL5_x, row.Quartet_DNA_ILM_XTen_WUX_1_20170216_LCL5_y)
+		Quartet_DNA_ILM_XTen_WUX_2_20170216_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_WUX_2_20170216_LCL5_x, row.Quartet_DNA_ILM_XTen_WUX_2_20170216_LCL5_y)
+		Quartet_DNA_ILM_XTen_WUX_3_20170216_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_WUX_3_20170216_LCL5_x, row.Quartet_DNA_ILM_XTen_WUX_3_20170216_LCL5_y)
+		outline2 = str(row._1) + '\t' + str(row.POS) + '\t' + str(row.ID_x) +'\t' + str(row.REF) + '\t' + str(row[5]) + '\t' + '.' + '\t' + '.' + '\t' + str(info) + '\t' + 'GT:DP:AF:GQ:MQ:TWINS:TRIO5:TRIO6' + '\t' \
+		+ str(Quartet_DNA_BGI_SEQ2000_BGI_1_20180518_LCL5) + '\t' + str(Quartet_DNA_BGI_SEQ2000_BGI_2_20180530_LCL5) + '\t' + str(Quartet_DNA_BGI_SEQ2000_BGI_3_20180530_LCL5) + '\t' \
+		+ str(Quartet_DNA_BGI_T7_WGE_1_20191105_LCL5) + '\t' + str(Quartet_DNA_BGI_T7_WGE_2_20191105_LCL5) + '\t' + str(Quartet_DNA_BGI_T7_WGE_3_20191105_LCL5) + '\t' \
+		+ str(Quartet_DNA_ILM_Nova_ARD_1_20181108_LCL5) + '\t' + str(Quartet_DNA_ILM_Nova_ARD_2_20181108_LCL5) + '\t' + str(Quartet_DNA_ILM_Nova_ARD_3_20181108_LCL5) + '\t' \
+		+ str(Quartet_DNA_ILM_Nova_ARD_4_20190111_LCL5) + '\t' + str(Quartet_DNA_ILM_Nova_ARD_5_20190111_LCL5) + '\t' + str(Quartet_DNA_ILM_Nova_ARD_6_20190111_LCL5) + '\t' \
+		+ str(Quartet_DNA_ILM_Nova_BRG_1_20180930_LCL5)  + '\t' + str(Quartet_DNA_ILM_Nova_BRG_2_20180930_LCL5) + '\t' + str(Quartet_DNA_ILM_Nova_BRG_3_20180930_LCL5) + '\t' \
+		+ str(Quartet_DNA_ILM_Nova_WUX_1_20190917_LCL5) + '\t' + str(Quartet_DNA_ILM_Nova_WUX_2_20190917_LCL5) + '\t' + str(Quartet_DNA_ILM_Nova_WUX_3_20190917_LCL5) + '\t' \
+		+ str(Quartet_DNA_ILM_XTen_ARD_1_20170403_LCL5) + '\t' + str(Quartet_DNA_ILM_XTen_ARD_2_20170403_LCL5) + '\t' + str(Quartet_DNA_ILM_XTen_ARD_3_20170403_LCL5) + '\t' \
+		+ str(Quartet_DNA_ILM_XTen_NVG_1_20170329_LCL5) + '\t' + str(Quartet_DNA_ILM_XTen_NVG_2_20170329_LCL5) + '\t' + str(Quartet_DNA_ILM_XTen_NVG_3_20170329_LCL5) + '\t' \
+		+ str(Quartet_DNA_ILM_XTen_WUX_1_20170216_LCL5) + '\t' + str(Quartet_DNA_ILM_XTen_WUX_2_20170216_LCL5) + '\t' + str(Quartet_DNA_ILM_XTen_WUX_3_20170216_LCL5) + '\n'
+		all_sample_outfile.write(outline2)
+	else:
+		info = '.'
+		Quartet_DNA_BGI_SEQ2000_BGI_1_20180518_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_BGI_SEQ2000_BGI_1_20180518_LCL5_x, row.Quartet_DNA_BGI_SEQ2000_BGI_1_20180518_LCL5_y)
+		Quartet_DNA_BGI_SEQ2000_BGI_2_20180530_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_BGI_SEQ2000_BGI_2_20180530_LCL5_x, row.Quartet_DNA_BGI_SEQ2000_BGI_2_20180530_LCL5_y)
+		Quartet_DNA_BGI_SEQ2000_BGI_3_20180530_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_BGI_SEQ2000_BGI_3_20180530_LCL5_x, row.Quartet_DNA_BGI_SEQ2000_BGI_3_20180530_LCL5_y)
+		Quartet_DNA_BGI_T7_WGE_1_20191105_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_BGI_T7_WGE_1_20191105_LCL5_x, row.Quartet_DNA_BGI_T7_WGE_1_20191105_LCL5_y)
+		Quartet_DNA_BGI_T7_WGE_2_20191105_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_BGI_T7_WGE_2_20191105_LCL5_x, row.Quartet_DNA_BGI_T7_WGE_2_20191105_LCL5_y)
+		Quartet_DNA_BGI_T7_WGE_3_20191105_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_BGI_T7_WGE_3_20191105_LCL5_x, row.Quartet_DNA_BGI_T7_WGE_3_20191105_LCL5_y)
+		Quartet_DNA_ILM_Nova_ARD_1_20181108_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_ARD_1_20181108_LCL5_x, row.Quartet_DNA_ILM_Nova_ARD_1_20181108_LCL5_y)
+		Quartet_DNA_ILM_Nova_ARD_2_20181108_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_ARD_2_20181108_LCL5_x, row.Quartet_DNA_ILM_Nova_ARD_2_20181108_LCL5_y)
+		Quartet_DNA_ILM_Nova_ARD_3_20181108_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_ARD_3_20181108_LCL5_x, row.Quartet_DNA_ILM_Nova_ARD_3_20181108_LCL5_y)
+		Quartet_DNA_ILM_Nova_ARD_4_20190111_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_ARD_4_20190111_LCL5_x, row.Quartet_DNA_ILM_Nova_ARD_4_20190111_LCL5_y)
+		Quartet_DNA_ILM_Nova_ARD_5_20190111_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_ARD_5_20190111_LCL5_x, row.Quartet_DNA_ILM_Nova_ARD_5_20190111_LCL5_y)
+		Quartet_DNA_ILM_Nova_ARD_6_20190111_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_ARD_6_20190111_LCL5_x, row.Quartet_DNA_ILM_Nova_ARD_6_20190111_LCL5_y)
+		Quartet_DNA_ILM_Nova_BRG_1_20180930_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_BRG_1_20180930_LCL5_x, row.Quartet_DNA_ILM_Nova_BRG_1_20180930_LCL5_y)
+		Quartet_DNA_ILM_Nova_BRG_2_20180930_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_BRG_2_20180930_LCL5_x, row.Quartet_DNA_ILM_Nova_BRG_2_20180930_LCL5_y)
+		Quartet_DNA_ILM_Nova_BRG_3_20180930_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_BRG_3_20180930_LCL5_x, row.Quartet_DNA_ILM_Nova_BRG_3_20180930_LCL5_y)
+		Quartet_DNA_ILM_Nova_WUX_1_20190917_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_WUX_1_20190917_LCL5_x, row.Quartet_DNA_ILM_Nova_WUX_1_20190917_LCL5_y)
+		Quartet_DNA_ILM_Nova_WUX_2_20190917_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_WUX_2_20190917_LCL5_x, row.Quartet_DNA_ILM_Nova_WUX_2_20190917_LCL5_y)
+		Quartet_DNA_ILM_Nova_WUX_3_20190917_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_Nova_WUX_3_20190917_LCL5_x, row.Quartet_DNA_ILM_Nova_WUX_3_20190917_LCL5_y)
+		Quartet_DNA_ILM_XTen_ARD_1_20170403_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_ARD_1_20170403_LCL5_x, row.Quartet_DNA_ILM_XTen_ARD_1_20170403_LCL5_y)
+		Quartet_DNA_ILM_XTen_ARD_2_20170403_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_ARD_2_20170403_LCL5_x, row.Quartet_DNA_ILM_XTen_ARD_2_20170403_LCL5_y)
+		Quartet_DNA_ILM_XTen_ARD_3_20170403_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_ARD_3_20170403_LCL5_x, row.Quartet_DNA_ILM_XTen_ARD_3_20170403_LCL5_y)
+		Quartet_DNA_ILM_XTen_NVG_1_20170329_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_NVG_1_20170329_LCL5_x, row.Quartet_DNA_ILM_XTen_NVG_1_20170329_LCL5_y)
+		Quartet_DNA_ILM_XTen_NVG_2_20170329_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_NVG_2_20170329_LCL5_x, row.Quartet_DNA_ILM_XTen_NVG_2_20170329_LCL5_y)
+		Quartet_DNA_ILM_XTen_NVG_3_20170329_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_NVG_3_20170329_LCL5_x, row.Quartet_DNA_ILM_XTen_NVG_3_20170329_LCL5_y)
+		Quartet_DNA_ILM_XTen_WUX_1_20170216_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_WUX_1_20170216_LCL5_x, row.Quartet_DNA_ILM_XTen_WUX_1_20170216_LCL5_y)
+		Quartet_DNA_ILM_XTen_WUX_2_20170216_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_WUX_2_20170216_LCL5_x, row.Quartet_DNA_ILM_XTen_WUX_2_20170216_LCL5_y)
+		Quartet_DNA_ILM_XTen_WUX_3_20170216_LCL5 = single_sample_format(row.FORMAT_x, row.Quartet_DNA_ILM_XTen_WUX_3_20170216_LCL5_x, row.Quartet_DNA_ILM_XTen_WUX_3_20170216_LCL5_y)
+		outline2 = str(row._1) + '\t' + str(row.POS) + '\t' + str(row.ID_x) +'\t' + str(row.REF) + '\t' + str(row[5]) + '\t' + '.' + '\t' + '.' + '\t' + str(info) + '\t' + 'GT:DP:AF:GQ:MQ:TWINS:TRIO5:TRIO6' + '\t' \
+		+ str(Quartet_DNA_BGI_SEQ2000_BGI_1_20180518_LCL5) + '\t' + str(Quartet_DNA_BGI_SEQ2000_BGI_2_20180530_LCL5) + '\t' + str(Quartet_DNA_BGI_SEQ2000_BGI_3_20180530_LCL5) + '\t' \
+		+ str(Quartet_DNA_BGI_T7_WGE_1_20191105_LCL5) + '\t' + str(Quartet_DNA_BGI_T7_WGE_2_20191105_LCL5) + '\t' + str(Quartet_DNA_BGI_T7_WGE_3_20191105_LCL5) + '\t' \
+		+ str(Quartet_DNA_ILM_Nova_ARD_1_20181108_LCL5) + '\t' + str(Quartet_DNA_ILM_Nova_ARD_2_20181108_LCL5) + '\t' + str(Quartet_DNA_ILM_Nova_ARD_3_20181108_LCL5) + '\t' \
+		+ str(Quartet_DNA_ILM_Nova_ARD_4_20190111_LCL5) + '\t' + str(Quartet_DNA_ILM_Nova_ARD_5_20190111_LCL5) + '\t' + str(Quartet_DNA_ILM_Nova_ARD_6_20190111_LCL5) + '\t' \
+		+ str(Quartet_DNA_ILM_Nova_BRG_1_20180930_LCL5)  + '\t' + str(Quartet_DNA_ILM_Nova_BRG_2_20180930_LCL5) + '\t' + str(Quartet_DNA_ILM_Nova_BRG_3_20180930_LCL5) + '\t' \
+		+ str(Quartet_DNA_ILM_Nova_WUX_1_20190917_LCL5) + '\t' + str(Quartet_DNA_ILM_Nova_WUX_2_20190917_LCL5) + '\t' + str(Quartet_DNA_ILM_Nova_WUX_3_20190917_LCL5) + '\t' \
+		+ str(Quartet_DNA_ILM_XTen_ARD_1_20170403_LCL5) + '\t' + str(Quartet_DNA_ILM_XTen_ARD_2_20170403_LCL5) + '\t' + str(Quartet_DNA_ILM_XTen_ARD_3_20170403_LCL5) + '\t' \
+		+ str(Quartet_DNA_ILM_XTen_NVG_1_20170329_LCL5) + '\t' + str(Quartet_DNA_ILM_XTen_NVG_2_20170329_LCL5) + '\t' + str(Quartet_DNA_ILM_XTen_NVG_3_20170329_LCL5) + '\t' \
+		+ str(Quartet_DNA_ILM_XTen_WUX_1_20170216_LCL5) + '\t' + str(Quartet_DNA_ILM_XTen_WUX_2_20170216_LCL5) + '\t' + str(Quartet_DNA_ILM_XTen_WUX_3_20170216_LCL5) + '\n'
+		all_sample_outfile.write(outline2)
+
+
+
+
+

codescripts/bed_for_bamReadcount.py

@@ -1,68 +0,0 @@
-import sys,getopt
-import os
-import re
-import fileinput
-
-def usage():
-    print(
-        """
-Usage: python bed_for_bamReadcount.py -i input_vcf_file -o prefix
-
-This script selects SNPs and Indels supported by all callsets.
-
-Please notice that bam-readcount only takes in 1-based coordinates.
-
-Input:
--i a vcf file
-
-Output:
--o  a indel bed file for bam-readcount
-        """)
-
-# select supported small variants
-def process(oneLine):
-    m = re.match('^\#',oneLine)
-    if m is not None:
-        pass
-    else:
-        line = oneLine.rstrip()
-        strings = line.strip().split('\t')
-        # convert the position to bed file for bam-readcount
-        # deletion
-        if len(strings[3]) > 1 and len(strings[4]) == 1:
-            pos = int(strings[1]) + 1
-            outline = strings[0] + '\t' + str(pos) + '\t' + str(pos) + '\t' + strings[3] + '\t' + strings[4]+'\n'
-            outINDEL.write(outline)
-        # insertion
-        elif len(strings[3]) == 1 and len(strings[4]) > 1 and (',' not in strings[4]):
-            outline = strings[0] + '\t' + strings[1] + '\t' + strings[1] +  '\t' + strings[3] +  '\t' + strings[4] + '\n'
-            outINDEL.write(outline)
-        else:
-            outMNP.write(oneLine)
-
-opts,args = getopt.getopt(sys.argv[1:],"hi:o:")
-for op,value in opts:
-    if op == "-i":
-        inputFile=value
-    elif op == "-o":
-        prefix=value    
-    elif op == "-h":
-        usage()
-        sys.exit()
-
-if len(sys.argv[1:]) < 3:
-    usage()
-    sys.exit()
-
-INDELname = prefix + '.bed'
-MNPname = prefix + '_MNP.txt'
-
-outINDEL = open(INDELname,'w')
-outMNP = open(MNPname,'w')
-
-for line in fileinput.input(inputFile):
-    process(line)
-
-outINDEL.close()
-outMNP.close()
-

codescripts/high_confidence_call_vote.py

@@ -27,6 +27,7 @@ vcf_header = '''##fileformat=VCFv4.2
 ##reference=GRCh38.d1.vd1
 ##INFO=<ID=DPCT,Number=1,Type=Float,Description="Percentage of detected votes">
 ##INFO=<ID=VPCT,Number=1,Type=Float,Description="Percentage of consnesus votes">
+##INFO=<ID=FPCT,Number=1,Type=Float,Description="Percentage of mendelian consisitent votes">
 ##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
 ##contig=<ID=chr1,length=248956422>
 ##contig=<ID=chr2,length=242193529>
@@ -82,7 +83,14 @@ def vote_percentage(strings,consensus_call):
 	return(str(percentage))
 
 def family_vote(strings,consensus_call):
-	pass
+	strings = [x.replace('.','0/0') for x in strings]
+	gt = [x.split(':')[0] for x in strings]
+	gt = list(map(gt_uniform,[i for i in gt]))
+	mendelian = [x[-5:] for x in strings]
+	indices = [i for i, x in enumerate(gt) if x == consensus_call]
+	matched_mendelian = itemgetter(*indices)(mendelian)
+	percentage = round(matched_mendelian.count('1:1:1')/27,4)
+	return(str(percentage))
 
 def gt_uniform(strings):
 	uniformed_gt = ''
@@ -140,10 +148,10 @@ def main():
 				outfile.write(outLine)
 			else:
 				# pre-define
-				pcr_consensus = ''
-				pcr_free_consensus = ''
-				consensus_call = ''
-				consensus_alt_seq = ''
+				pcr_consensus = '.'
+				pcr_free_consensus = '.'
+				consensus_call = '.'
+				consensus_alt_seq = '.'
 				# pcr 
 				pcr = itemgetter(*[9,10,11,27,28,29,30,31,32,33,34,35])(strings)
 				SEQ2000 = decide_by_rep(pcr[0:3])
@@ -183,6 +191,8 @@ def main():
 					strings[7] = 'VPCT=' + VPCT
 					DPCT = detected_percentage(strings[9:])
 					strings[7] = strings[7] + ';DPCT=' + DPCT
+					FPCT = family_vote(strings[9:],consensus_call)
+					strings[7] = strings[7] + ';FPCT=' + FPCT
 					# Delete multiple alternative genotype to necessary expression
 					strings[6] = 'reproducible'
 					alt = strings[4]

codescripts/variants_quality_location_intergration.py

@@ -27,33 +27,34 @@ def get_location(info):
 	return repeat
 
 
-def extract_info_normal(strings):
-	AF = []
+def extract_info_normal(FORMAT,strings):
 	GQ = []
 	MQ = []
 	DP = []
 	ALT = []
+	format_strings = FORMAT.split(':')
 	for element in strings:
 		if element == '.':
 			pass
 		else:
-			ad = element.split(':')[1]
-			ref = ad.split(',')[0]
-			alt = ad.split(',')[1]
-			af = float(int(alt)/(int(ref) + int(alt)))
-			gq = int(element.split(':')[3])
-			mq = float(element.split(':')[5])
-			dp = int(element.split(':')[2])
-			AF.append(af)
+			element_strings = element.split(':')
+			formatDict = dict(zip(format_strings, element_strings))		
+			alt = int(formatDict['ALT'])
+			dp = int(formatDict['DP'])
+			gq = int(formatDict['GQ'])
+			mq = float(formatDict['MQ'])
 			GQ.append(gq)
 			MQ.append(mq)
 			DP.append(dp)
-			ALT.append(int(alt))
-	AF_m = statistics.mean(AF)
-	GQ_m = statistics.mean(GQ)
-	MQ_m = statistics.mean(MQ)
+			ALT.append(alt)
 	DP_a = sum(DP)
 	ALT_a = sum(ALT)
+	if DP_a == 0:
+		AF_m = 'NA'
+	else:
+		AF_m = float(ALT_a/DP_a)
+	GQ_m = statistics.mean(GQ)
+	MQ_m = statistics.mean(MQ)
 	return AF_m,GQ_m,MQ_m,DP_a,ALT_a
 
 
@@ -61,6 +62,7 @@ file_name = prefix + '_variant_quality_location.txt'
 outfile = open(file_name,'w')
 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_T7_WGE_1_20191105_LCL5\tQuartet_DNA_BGI_T7_WGE_2_20191105_LCL5\tQuartet_DNA_BGI_T7_WGE_3_20191105_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_20180930_LCL5\tQuartet_DNA_ILM_Nova_BRG_2_20180930_LCL5\tQuartet_DNA_ILM_Nova_BRG_3_20180930_LCL5\tQuartet_DNA_ILM_Nova_WUX_1_20190917_LCL5\tQuartet_DNA_ILM_Nova_WUX_2_20190917_LCL5\tQuartet_DNA_ILM_Nova_WUX_3_20190917_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' +'\t'+ 'location' + '\t' + 'AF' + '\t' + 'GQ' + '\t' + 'MQ' + '\t' + 'DP' + '\t' + 'ALT' +'\n'
 outfile.write(outputcolumn)
+
 for line in fileinput.input(multi_sample_vcf):
 	m = re.match('^\#',line)
 	if m is not None:
@@ -69,7 +71,7 @@ for line in fileinput.input(multi_sample_vcf):
 		line = line.strip()
 		strings = line.split('\t')
 		repeat = get_location(strings[7])
-		AF,GQ,MQ,DP,ALT = extract_info_normal(strings[9:])
+		AF,GQ,MQ,DP,ALT = extract_info_normal(strings[8],strings[9:])
 		outLine = '\t'.join(strings) + '\t' + repeat +'\t' + str(AF) + '\t' + str(GQ) + '\t' + str(MQ) + '\t' + str(DP) + '\t' + str(ALT) + '\n'
 		outfile.write(outLine)
 

codescripts/vcf_mq_af.py

@@ -15,7 +15,7 @@ normed_vcf = args.normed_vcf
 prefix = args.prefix
 
 
-file_name = prefix + '.variant_quality_location.vcf'
+file_name = prefix + '_variant_quality_location.vcf'
 outfile = open(file_name,'w')
 
 for line in fileinput.input(normed_vcf):

tasks/VCFinfo.wdl

@@ -1,5 +1,5 @@
 task VCFinfo {
-	File merged_info
+	File repeat_annotated_vcf
 	String sample
 	String docker
 	String cluster_config
@@ -7,8 +7,8 @@ task VCFinfo {
 	
 	command <<<
 
-		
- 
+		python /opt/variants_quality_location_intergration.py -vcf ${repeat_annotated_vcf} -prefix ${sample}
+
 	>>>
 
 	runtime {
@@ -18,6 +18,6 @@ task VCFinfo {
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File extracted_info = ""
+		File extracted_info = "${sample}_variant_quality_location.txt"
 	}
 }

tasks/bed_annotation.wdl

@@ -9,43 +9,9 @@ task bed_annotation {
 	
 	command <<<
 
-		rtg vcfannotate --bed-info=${repeat_bed} -i ${merged_vcf} -o ${sample}.normed.repeatAnno.vcf.gz	
-		
-		## DP
-		zcat ${sample}.normed.repeatAnno.vcf.gz | grep -v '##' | awk '
-		    BEGIN { OFS = "\t" }
-		    NF > 2 && FNR > 1 { 
-		        for ( i=9; i<=NF; i++ ) { 
-		            split($i,a,":") ;$i = a[3];
-		        } 
-		    } 
-		    { print }
-		' > ${sample}.depth.txt
-		
-		## GQ
-		zcat ${sample}.normed.repeatAnno.vcf.gz | grep -v '##' | awk '
-		    BEGIN { OFS = "\t" }
-		    NF > 2 && FNR > 1 { 
-		        for ( i=9; i<=NF; i++ ) { 
-		            split($i,a,":") ;$i = a[4];
-		        } 
-		    } 
-		    { print }
-		' > ${sample}.genotypeQuality.txt
-
-		## MQ
-		zcat ${sample}.normed.repeatAnno.vcf.gz | grep -v '##' | awk '
-		    BEGIN { OFS = "\t" }
-		    NF > 2 && FNR > 1 { 
-		        for ( i=9; i<=NF; i++ ) { 
-		            split($i,a,":") ;$i = a[6];
-		        } 
-		    } 
-		    { print }
-		' > ${sample}.mappinyQuality.txt
-
-		## Allele frequency
+		rtg vcfannotate --bed-info=${repeat_bed} -i ${merged_vcf} -o ${sample}.normed.repeatAnno.vcf.gz
 
+		gunzip ${sample}.normed.repeatAnno.vcf.gz
 
 	>>>
 
@@ -56,7 +22,6 @@ task bed_annotation {
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File repeat_annotated_vcf = "${sample}.normed.repeatAnno.vcf.gz"
-		File repeat_annotated_vcf_idx = "${sample}.normed.repeatAnno.vcf.gz.tbi"
+		File repeat_annotated_vcf = "${sample}.normed.repeatAnno.vcf"
 	}
 }

tasks/final_result.wdl

@@ -0,0 +1,26 @@
+task FinalResult {
+	File extracted_info
+	File annotated_txt
+	String prefix
+	String sample
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+
+		python /opt/FinalResult2VCF.py -vcfInfo ${extracted_info} -mendelianInfo ${annotated_txt} -prefix ${prefix} -sample ${sample}
+
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File benchmarking_calls = "${prefix}_benchmarking_calls.vcf"
+		File all_info = "${prefix}_all_sample_information.vcf"
+	}
+}

tasks/votes.wdl

@@ -9,6 +9,8 @@ task votes {
 	
 	command <<<
 		python /opt/high_confidence_call_vote.py -vcf ${merged_vcf} -dup ${vcf_dup} -sample ${sample} -prefix ${prefix}
+
+		cat ${prefix}_annotated.vcf | grep -v '##' > ${prefix}.txt
 	>>>
 
 	runtime {
@@ -19,5 +21,6 @@ task votes {
 	}
 	output {
 		File annotated_vcf = "${prefix}_annotated.vcf"
+		File annotated_txt = "${prefix}.txt"
 	}
 }

workflow.wdl

@@ -9,6 +9,8 @@ import "./tasks/merge.wdl" as merge
 import "./tasks/votes.wdl" as votes
 import "./tasks/bed_annotation.wdl" as bed_annotation
 import "./tasks/mergeVCFInfo.wdl" as mergeVCFInfo
+import "./tasks/VCFinfo.wdl" as VCFinfo
+import "./tasks/final_result.wdl" as FinalResult
 
 workflow {{ project_name }} {
 	File inputSamplesFile
@@ -299,6 +301,22 @@ workflow {{ project_name }} {
 		cluster_config=cluster_config,
 		disk_size=disk_size
 	}
+	call VCFinfo.VCFinfo as LCL5allSampleReform {
+		input:
+		repeat_annotated_vcf=LCL5bedAnnotation.repeat_annotated_vcf,
+		sample='LCL5',
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	call FinalResult.FinalResult as LCL5FinalResult {
+		input:
+		extracted_info=LCL5allSampleReform.extracted_info,
+		annotated_txt=LCL5votes.annotated_txt,
+		prefix='LCL5',
+		sample='LCL5',
+		cluster_config=cluster_config,
+		disk_size=disk_size,
+	}
 	call mergeVCFInfo.mergeVCFInfo as LCL6mergeVCF {
 		input:
 		vcf_gz=LCL6normZip.vcf_gz,
@@ -316,6 +334,22 @@ workflow {{ project_name }} {
 		cluster_config=cluster_config,
 		disk_size=disk_size
 	}
+	call VCFinfo.VCFinfo as LCL6allSampleReform {
+		input:
+		repeat_annotated_vcf=LCL6bedAnnotation.repeat_annotated_vcf,
+		sample='LCL6',
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	call FinalResult.FinalResult as LCL6FinalResult {
+		input:
+		extracted_info=LCL6allSampleReform.extracted_info,
+		annotated_txt=LCL6votes.annotated_txt,
+		prefix='LCL6',
+		sample='LCL6',
+		cluster_config=cluster_config,
+		disk_size=disk_size,
+	}
 	call mergeVCFInfo.mergeVCFInfo as LCL7mergeVCF {
 		input:
 		vcf_gz=LCL7normZip.vcf_gz,
@@ -333,6 +367,22 @@ workflow {{ project_name }} {
 		cluster_config=cluster_config,
 		disk_size=disk_size
 	}
+	call VCFinfo.VCFinfo as LCL7allSampleReform {
+		input:
+		repeat_annotated_vcf=LCL7bedAnnotation.repeat_annotated_vcf,
+		sample='LCL7',
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	call FinalResult.FinalResult as LCL7FinalResult {
+		input:
+		extracted_info=LCL7allSampleReform.extracted_info,
+		annotated_txt=LCL7votes.annotated_txt,
+		prefix='LCL7',
+		sample='LCL7',
+		cluster_config=cluster_config,
+		disk_size=disk_size,
+	}
 	call mergeVCFInfo.mergeVCFInfo as LCL8mergeVCF {
 		input:
 		vcf_gz=LCL8normZip.vcf_gz,
@@ -350,5 +400,21 @@ workflow {{ project_name }} {
 		cluster_config=cluster_config,
 		disk_size=disk_size
 	}
+	call VCFinfo.VCFinfo as LCL8allSampleReform {
+		input:
+		repeat_annotated_vcf=LCL8bedAnnotation.repeat_annotated_vcf,
+		sample='LCL8',
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	call FinalResult.FinalResult as LCL8FinalResult {
+		input:
+		extracted_info=LCL8allSampleReform.extracted_info,
+		annotated_txt=LCL8votes.annotated_txt,
+		prefix='LCL8',
+		sample='LCL8',
+		cluster_config=cluster_config,
+		disk_size=disk_size,
+	}
 }