try again merge mendelian and vcf info

codescripts/FinalResult2VCF.py

@@ -1,3 +1,4 @@
+from __future__ import division
 import pandas as pd
 import sys, argparse, os
 import fileinput
@@ -134,7 +135,7 @@ all_sample_outfile.write(outputcolumn_all_sample)
 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 = pd.merge(vcf_info, mendelian_info,  how='outer', left_on=['#CHROM','POS'], right_on = ['#CHROM','POS'])
 merged_df = merged_df.fillna('.')
 
 # function
@@ -190,94 +191,103 @@ def single_sample_format(format_x,strings_x,strings_y):
 
 #
 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)
+	vcf_count = row[10:37].count('.')
+	mendelian_count = row[50:77].count('.')
+	if vcf_count == mendelian_count:
+		info = 'location=' + str(row.location) + ';' + str(row.INFO_y)
+		if row.FILTER_y == 'reproducible':
+			ref = row.DP - row._42
+			FORMAT = row[79] + ':' + 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_y) + '\t' + str(row[80]) + '\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 != '.':
+			if row.AF=='.':
+				info = 'location=' + str(row.location) + ';' + str(row.INFO_y) + ';' + 'ALL_ALT=' + str(int(row._42)) + ';' + 'ALL_DP=' + str(int(row.DP)) + ';' + 'ALL_AF=' + 'NA' + ';' + 'GQ_MEAN=' + str(row.GQ) + ';' + 'MQ_MEAN=' + str(row.MQ) + ';' + 'PCR=' + str(row[77]) + ';' + 'PCR_FREE=' + str(row[78]) + ';' + 'CONSENSUS=' + str(row[79]) + ';' + 'CONSENSUS_SEQ=' + str(row[80])			
+			else:
+				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(float(row.AF),2)) + ';' + 'GQ_MEAN=' + str(row.GQ) + ';' + 'MQ_MEAN=' + str(row.MQ) + ';' + 'PCR=' + str(row[77]) + ';' + 'PCR_FREE=' + str(row[78]) + ';' + 'CONSENSUS=' + str(row[79]) + ';' + 'CONSENSUS_SEQ=' + str(row[80])			
+			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_x) + '\t' + str(row.ALT_x) + '\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_x) + '\t' + str(row.ALT_x) + '\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:
+
+
 
 
 

codescripts/merge_mendelian_vcfinfo.py

@@ -0,0 +1,127 @@
+from __future__ import division
+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('-sample', '--sample_name', type=str, help='which sample of quartet',  required=True)
+
+
+args = parser.parse_args()
+vcfInfo = args.vcfInfo
+mendelianInfo = args.mendelianInfo
+sample_name = args.sample_name
+
+
+#GT:TWINS:TRIO5:TRIO6:DP:AF:GQ:QD:MQ:FS:QUAL
+
+vcf_header = '''##fileformat=VCFv4.2
+##fileDate=20200331
+##source=high_confidence_calls_intergration(choppy app)
+##reference=GRCh38.d1.vd1
+#FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+#FORMAT=<ID=TWINS,Number=1,Type=String,Description="1 for sister consistent, 0 for sister different">
+#FORMAT=<ID=TRIO5,Number=1,Type=String,Description="1 for LCL7, LCL8 and LCL5 mendelian consistent, 0 for family violation">
+#FORMAT=<ID=TRIO6,Number=1,Type=String,Description="1 for LCL7, LCL8 and LCL6 mendelian consistent, 0 for family violation">
+##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=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##FORMAT=<ID=MQ,Number=1,Type=Float,Description="Mapping quality">
+##FORMAT=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bia">
+##FORMAT=<ID=QUAL,Number=1,Type=Float,Description="variant 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>
+'''
+
+# output file
+file_name = sample_name + '_mendelian_vcfInfo.vcf'
+outfile = open(file_name,'w')
+
+outputcolumn = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t' +  sample_name + '\n'
+outfile.write(vcf_header)
+outfile.write(outputcolumn)
+
+# 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'], right_on = ['#CHROM','POS'])
+merged_df = merged_df.fillna('.')
+
+#
+def parse_INFO(info):
+	strings = info.strip().split(';')
+	keys = []
+	values = []
+	for i in strings:
+		kv = i.split('=')
+		if kv[0] == 'DB':
+			keys.append('DB')
+			values.append('1')
+		else:
+			keys.append(kv[0])
+			values.append(kv[1])
+	infoDict = dict(zip(keys, values))
+	return infoDict
+#
+for row in merged_df.itertuples():
+	if row.Quartet_DNA_BGI_SEQ2000_BGI_1_20180518_LCL5 != '.':
+		# format
+		# GT:TWINS:TRIO5:TRIO6:DP:AF:GQ:QD:MQ:FS:QUAL
+		FORMAT_x = row.Quartet_DNA_BGI_SEQ2000_BGI_LCL5_1_20180518.split(':')
+		ALT = int(FORMAT_x[1].split(',')[1])
+		if int(FORMAT_x[2]) != 0:
+			AF = round(ALT/int(FORMAT_x[2]),2)
+		else:
+			AF = '.'
+		INFO_x = parse_INFO(row.INFO_x)
+		if FORMAT_x[2] == '0':
+			INFO_x['QD'] = '.'
+		else:
+			pass
+		FORMAT = row.Quartet_DNA_BGI_SEQ2000_BGI_1_20180518_LCL5 + ':' + FORMAT_x[2] + ':' + str(AF) + ':' + FORMAT_x[3] + ':' + INFO_x['QD'] + ':' + INFO_x['MQ'] + ':' + INFO_x['FS'] + ':' + str(row.QUAL_x)
+		# outline
+		outline = row._1 + '\t' + str(row.POS) + '\t' + row.ID_x + '\t' + row.REF_y + '\t' + row.ALT_y + '\t' + '.' + '\t' + '.' + '\t' + '.' + '\t' + 'GT:TWINS:TRIO5:TRIO6:DP:AF:GQ:QD:MQ:FS:QUAL' + '\t' + FORMAT + '\n'
+	else:
+		FORMAT_x = row.Quartet_DNA_BGI_SEQ2000_BGI_LCL5_1_20180518.split(':')
+		ALT = int(FORMAT_x[1].split(',')[1])
+		if int(FORMAT_x[2]) != 0:
+			AF = round(ALT/int(FORMAT_x[2]),2)
+		else:
+			AF = '.'
+		INFO_x = parse_INFO(row.INFO_x)
+		if FORMAT_x[2] == '0':
+			INFO_x['QD'] = '.'
+		else:
+			pass
+		FORMAT = '.:.:.:.' + ':' + FORMAT_x[2] + ':' + str(AF) + ':' + FORMAT_x[3] + ':' + INFO_x['QD'] + ':' + INFO_x['MQ'] + ':' + INFO_x['FS'] + ':' + str(row.QUAL_x)
+		# outline
+		outline = row._1 + '\t' + str(row.POS) + '\t' + row.ID_x + '\t' + row.REF_y + '\t' + row.ALT_y + '\t' + '.' + '\t' + '.' + '\t' + '.' + '\t' + 'GT:TWINS:TRIO5:TRIO6:DP:AF:GQ:QD:MQ:FS:QUAL' + '\t' + FORMAT + '\n'
+	outfile.write(outline)

codescripts/variants_quality_location_intergration.py

@@ -1,3 +1,4 @@
+from __future__ import division 
 import sys, argparse, os
 import fileinput
 import re

inputs

@@ -1,57 +1,32 @@
 {
-  "{{ project_name }}.LCL6normZip.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL5extract_info.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
   "{{ project_name }}.LCL7merge.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.fasta": "GRCh38.d1.vd1.fa",
-  "{{ project_name }}.LCL6familyzipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL7votes.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
-  "{{ project_name }}.LCL6votes.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
-  "{{ project_name }}.LCL6FinalResult.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
   "{{ project_name }}.LCL5VCFrename.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL6allSampleReform.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
+  "{{ project_name }}.LCL8mergeInfo.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
   "{{ project_name }}.LCL6mendelian.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/vbt:v1.1",
+  "{{ project_name }}.LCL5mergeInfo.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1", 
   "{{ project_name }}.mergeSister.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL7normZip.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.LCL5mendelian.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/vbt:v1.1",
+  "{{ project_name }}.LCL6allInfozipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.LCL5allInfozipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.disk_size": "150",
-  "{{ project_name }}.LCL7allSampleReform.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
+  "{{ project_name }}.LCL7mergeInfo.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
   "{{ project_name }}.inputSamplesFile": "{{ inputSamplesFile }}",
-  "{{ project_name }}.LCL6bedAnnotation.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.repeat_bed": "oss://pgx-result/renluyao/manuscript/all.repeat.bed",
   "{{ project_name }}.LCL6merge.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL5FinalResult.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
   "{{ project_name }}.LCL6variantsNorm.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9",
-  "{{ project_name }}.LCL5mergeVCF.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.LCL6zipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL8mergeVCF.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL5votes.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
-  "{{ project_name }}.LCL7familyzipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL8extract_info.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
-  "{{ project_name }}.LCL7FinalResult.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
-  "{{ project_name }}.LCL8FinalResult.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
-  "{{ project_name }}.LCL5allSampleReform.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
-  "{{ project_name }}.LCL5familyzipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL5normZip.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.LCL7allInfozipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.LCL6mergeInfo.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1", 
   "{{ project_name }}.LCL6VCFrename.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL7extract_info.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
   "{{ project_name }}.LCL5merge.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL8votes.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
   "{{ project_name }}.reformVCF.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call:v1.1",
   "{{ project_name }}.LCL5zipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.cluster_config": "OnDemand bcs.a2.xlarge img-ubuntu-vpc",
-  "{{ project_name }}.LCL8familyzipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL5bedAnnotation.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL6mergeVCF.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL6extract_info.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
+  "{{ project_name }}.cluster_config": "OnDemand bcs.b4.xlarge img-ubuntu-vpc",
+  "{{ project_name }}.LCL8allInfozipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.LCL7variantsNorm.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9",
-  "{{ project_name }}.LCL7mergeVCF.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL8allSampleReform.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
   "{{ project_name }}.LCL8merge.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.LCL5variantsNorm.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9",
-  "{{ project_name }}.LCL7bedAnnotation.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.LCL8variantsNorm.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9",
-  "{{ project_name }}.LCL8bedAnnotation.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.LCL8normZip.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.ref_dir": "oss://chinese-quartet/quartet-storage-data/reference_data/"
 }
 

tasks/VCFinfo.wdl

@@ -9,6 +9,14 @@ task VCFinfo {
 
 		python /opt/variants_quality_location_intergration.py -vcf ${repeat_annotated_vcf} -prefix ${sample}
 
+		cat ${sample}_variant_quality_location.txt | grep '#CHROM' > header
+
+		for i in chr1 chr2 chr3 chr4 chr5 chr6 chr7 chr8 chr9 chr10 chr11 chr12 chr13 chr14 chr15 chr16 chr17 chr18 chr19 chr20 chr21 chr22 chrX
+		do
+			cat ${sample}_variant_quality_location.txt | grep -w $i | cat header - > ${sample}.$i.vcfInfo.txt
+		done
+
+
 	>>>
 
 	runtime {
@@ -19,5 +27,6 @@ task VCFinfo {
 	}
 	output {
 		File extracted_info = "${sample}_variant_quality_location.txt"
+		Array[File] chromo_vcfInfo = glob("*.vcfInfo.txt")
 	}
 }

tasks/final_result.wdl

@@ -1,7 +1,7 @@
 task FinalResult {
 	File extracted_info
 	File annotated_txt
-	String prefix
+	String prefix = basename(annotated_txt,".mendelian.txt")
 	String sample
 	String docker
 	String cluster_config

tasks/extract_info.wdl → tasks/merge_info.wdl

@@ -1,13 +1,14 @@
-task extract_info {
-	File normed_vcf
-	String sampleName
+task merge_info {
+	File vcfInfo
+	File mendelianInfo
+	String sample
 	String docker
 	String cluster_config
 	String disk_size
 	
 	command <<<
 
-		python /opt/vcf_mq_af.py -vcf ${normed_vcf} -prefix ${sampleName}
+		python /opt/merge_mendelian_vcfinfo.py -vcfInfo ${vcfInfo} -mendelianInfo ${mendelianInfo} -sample ${sample}
 
 	>>>
 
@@ -18,6 +19,6 @@ task extract_info {
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File vcf_info = "${sampleName}_variant_quality_location.vcf"
+		File all_info = "${sample}_mendelian_vcfInfo.vcf"
 	}
 }

tasks/variantsNorm.wdl

@@ -16,10 +16,6 @@ task variantsNorm {
 
 		/opt/hall-lab/bcftools-1.9/bin/bcftools norm -f ${ref_dir}/${fasta} ${sampleName}.filtered.vcf > ${sampleName}.normed.vcf
 
-		cat ${sampleName}.normed.vcf | grep -v '#' | cut -f8 | sed s'/MQ=/\t/g' | cut -f2 | sed s'/;/\t/g' | cut -f1 > MQ
-		cat ${sampleName}.normed.vcf | grep -v '#' | awk '{print $1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9":MQ""\t"$10}' | paste - MQ -d ":" > body
-		cat ${sampleName}.normed.vcf | grep '#' | cat - body > ${sampleName}.normed.mq.vcf
-
 	>>>
 
 	runtime {
@@ -30,6 +26,5 @@ task variantsNorm {
 	}
 	output {
 		File normed_vcf = "${sampleName}.normed.vcf"
-		File normed_mq_vcf = "${sampleName}.normed.mq.vcf"
 	}
 }

tasks/votes.wdl

@@ -11,6 +11,14 @@ task votes {
 		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
+
+		cat ${prefix}.txt | grep '#CHROM' > header
+
+		for i in chr1 chr2 chr3 chr4 chr5 chr6 chr7 chr8 chr9 chr10 chr11 chr12 chr13 chr14 chr15 chr16 chr17 chr18 chr19 chr20 chr21 chr22 chrX
+		do
+			cat ${prefix}.txt | grep -w $i | cat header - > ${sample}.$i.mendelian.txt
+		done
+
 	>>>
 
 	runtime {
@@ -22,5 +30,7 @@ task votes {
 	output {
 		File annotated_vcf = "${prefix}_annotated.vcf"
 		File annotated_txt = "${prefix}.txt"
+		Array[File] chromo_votes = glob("*.mendelian.txt")
 	}
 }
+

workflow.wdl

@@ -1,22 +1,16 @@
 import "./tasks/variantsNorm.wdl" as variantsNorm
-import "./tasks/extract_info.wdl" as extract_info
+import "./tasks/merge_info.wdl" as merge_info
 import "./tasks/mendelian.wdl" as mendelian
 import "./tasks/zipIndex.wdl" as zipIndex
 import "./tasks/VCFrename.wdl" as VCFrename
 import "./tasks/mergeSister.wdl" as mergeSister
 import "./tasks/reformVCF.wdl" as reformVCF
 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
 	Array[Array[File]] inputSamples = read_tsv(inputSamplesFile)
 	File ref_dir
-	File repeat_bed
 	String fasta
 	String cluster_config
 	String disk_size
@@ -58,58 +52,6 @@ workflow {{ project_name }} {
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}
-		call extract_info.extract_info as LCL5extract_info {
-			input:
-			normed_vcf=LCL5variantsNorm.normed_vcf,
-			sampleName=quartet[4],
-			cluster_config=cluster_config,
-			disk_size=disk_size
-		}
-		call extract_info.extract_info as LCL6extract_info {
-			input:
-			normed_vcf=LCL6variantsNorm.normed_vcf,
-			sampleName=quartet[5],
-			cluster_config=cluster_config,
-			disk_size=disk_size
-		}
-		call extract_info.extract_info as LCL7extract_info {
-			input:
-			normed_vcf=LCL7variantsNorm.normed_vcf,
-			sampleName=quartet[6],
-			cluster_config=cluster_config,
-			disk_size=disk_size
-		}
-		call extract_info.extract_info as LCL8extract_info {
-			input:
-			normed_vcf=LCL8variantsNorm.normed_vcf,
-			sampleName=quartet[8],
-			cluster_config=cluster_config,
-			disk_size=disk_size
-		}		
-		call zipIndex.zipIndex as LCL5normZip{
-			input:
-			vcf=LCL5extract_info.vcf_info,
-			cluster_config=cluster_config,
-			disk_size=disk_size
-		}
-		call zipIndex.zipIndex as LCL6normZip{
-			input:
-			vcf=LCL6extract_info.vcf_info,
-			cluster_config=cluster_config,
-			disk_size=disk_size		
-		}
-		call zipIndex.zipIndex as LCL7normZip{
-			input:
-			vcf=LCL7extract_info.vcf_info,
-			cluster_config=cluster_config,
-			disk_size=disk_size		
-		}
-		call zipIndex.zipIndex as LCL8normZip{
-			input:
-			vcf=LCL8extract_info.vcf_info,
-			cluster_config=cluster_config,
-			disk_size=disk_size		
-		}
 		call mendelian.mendelian as LCL5mendelian {
 			input:
 			child_vcf=LCL5variantsNorm.normed_vcf,
@@ -189,27 +131,59 @@ workflow {{ project_name }} {
 			cluster_config=cluster_config,
 			disk_size=disk_size			
 		}
-		call zipIndex.zipIndex as LCL5familyzipIndex {
+		call merge_info.merge_info as LCL5mergeInfo {
+			input:
+			vcfInfo=LCL5variantsNorm.normed_vcf,
+			mendelianInfo=reformVCF.LCL5_family_info,
+			sample=quartet[4],
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call merge_info.merge_info as LCL6mergeInfo {
+			input:
+			vcfInfo=LCL6variantsNorm.normed_vcf,
+			mendelianInfo=reformVCF.LCL6_family_info,
+			sample=quartet[5],
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call merge_info.merge_info as LCL7mergeInfo {
+			input:
+			vcfInfo=LCL7variantsNorm.normed_vcf,
+			mendelianInfo=reformVCF.LCL7_family_info,
+			sample=quartet[6],
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call merge_info.merge_info as LCL8mergeInfo {
+			input:
+			vcfInfo=LCL8variantsNorm.normed_vcf,
+			mendelianInfo=reformVCF.LCL8_family_info,
+			sample=quartet[7],
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}	
+		call zipIndex.zipIndex as LCL5allInfozipIndex {
 			input:
-			vcf=reformVCF.LCL5_family_info,
+			vcf=LCL5mergeInfo.all_info,
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}
-		call zipIndex.zipIndex as LCL6familyzipIndex {
+		call zipIndex.zipIndex as LCL6allInfozipIndex {
 			input:
-			vcf=reformVCF.LCL6_family_info,
+			vcf=LCL6mergeInfo.all_info,
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}
-		call zipIndex.zipIndex as LCL7familyzipIndex {
+		call zipIndex.zipIndex as LCL7allInfozipIndex {
 			input:
-			vcf=reformVCF.LCL7_family_info,
+			vcf=LCL7mergeInfo.all_info,
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}
-		call zipIndex.zipIndex as LCL8familyzipIndex {
+		call zipIndex.zipIndex as LCL8allInfozipIndex {
 			input:
-			vcf=reformVCF.LCL8_family_info,
+			vcf=LCL8mergeInfo.all_info,
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}		
@@ -217,204 +191,34 @@ workflow {{ project_name }} {
 	### family info merge
 	call merge.merge as LCL5merge {
 		input:
-		family_vcf_gz=LCL5familyzipIndex.vcf_gz,
-		family_vcf_idx=LCL5familyzipIndex.vcf_idx,
+		family_vcf_gz=LCL5allInfozipIndex.vcf_gz,
+		family_vcf_idx=LCL5allInfozipIndex.vcf_idx,
 		sample="LCL5",
 		cluster_config=cluster_config,
 		disk_size=disk_size
 	}
-	call votes.votes as LCL5votes{
-		input:
-		merged_vcf=LCL5merge.merged_vcf,
-		vcf_dup=LCL5merge.vcf_dup,
-		sample='LCL5',
-		prefix='LCL5_consensus',
-		cluster_config=cluster_config,
-		disk_size=disk_size
-	}	
 	call merge.merge as LCL6merge {
 		input:
-		family_vcf_gz=LCL6familyzipIndex.vcf_gz,
-		family_vcf_idx=LCL6familyzipIndex.vcf_idx,
+		family_vcf_gz=LCL6allInfozipIndex.vcf_gz,
+		family_vcf_idx=LCL6allInfozipIndex.vcf_idx,
 		sample="LCL6",
 		cluster_config=cluster_config,
 		disk_size=disk_size
 	}
-	call votes.votes as LCL6votes {
-		input:
-		merged_vcf=LCL6merge.merged_vcf,
-		vcf_dup=LCL6merge.vcf_dup,
-		sample='LCL6',
-		prefix='LCL6_consensus',
-		cluster_config=cluster_config,
-		disk_size=disk_size
-	}	
 	call merge.merge as LCL7merge {
 		input:
-		family_vcf_gz=LCL7familyzipIndex.vcf_gz,
-		family_vcf_idx=LCL7familyzipIndex.vcf_idx,
+		family_vcf_gz=LCL7allInfozipIndex.vcf_gz,
+		family_vcf_idx=LCL7allInfozipIndex.vcf_idx,
 		sample="LCL7",
 		cluster_config=cluster_config,
 		disk_size=disk_size
 	}
-	call votes.votes as LCL7votes {
-		input:
-		merged_vcf=LCL7merge.merged_vcf,
-		vcf_dup=LCL7merge.vcf_dup,
-		sample='LCL7',
-		prefix='LCL7_consensus',
-		cluster_config=cluster_config,
-		disk_size=disk_size
-	}	
 	call merge.merge as LCL8merge {
 		input:
-		family_vcf_gz=LCL8familyzipIndex.vcf_gz,
-		family_vcf_idx=LCL8familyzipIndex.vcf_idx,
+		family_vcf_gz=LCL8allInfozipIndex.vcf_gz,
+		family_vcf_idx=LCL8allInfozipIndex.vcf_idx,
 		sample="LCL8",
 		cluster_config=cluster_config,
 		disk_size=disk_size
 	}
-	call votes.votes as LCL8votes {
-		input:
-		merged_vcf=LCL8merge.merged_vcf,
-		vcf_dup=LCL8merge.vcf_dup,
-		sample='LCL8',
-		prefix='LCL8_consensus',
-		cluster_config=cluster_config,
-		disk_size=disk_size
-	}
-	### vcf original information
-	call mergeVCFInfo.mergeVCFInfo as LCL5mergeVCF {
-		input:
-		vcf_gz=LCL5normZip.vcf_gz,
-		vcf_idx=LCL5normZip.vcf_idx,
-		sample='LCL5',
-		cluster_config=cluster_config,
-		disk_size=disk_size
-	}
-	call bed_annotation.bed_annotation as LCL5bedAnnotation {
-		input:
-		merged_vcf=LCL5mergeVCF.merged_vcf,
-		merged_vcf_idx=LCL5mergeVCF.merged_vcf_idx,
-		repeat_bed=repeat_bed,
-		sample='LCL5',
-		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,
-		vcf_idx=LCL6normZip.vcf_idx,
-		sample='LCL6',
-		cluster_config=cluster_config,
-		disk_size=disk_size
-	}
-	call bed_annotation.bed_annotation as LCL6bedAnnotation {
-		input:
-		merged_vcf=LCL6mergeVCF.merged_vcf,
-		merged_vcf_idx=LCL6mergeVCF.merged_vcf_idx,
-		repeat_bed=repeat_bed,
-		sample='LCL6',
-		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,
-		vcf_idx=LCL7normZip.vcf_idx,
-		sample='LCL7',
-		cluster_config=cluster_config,
-		disk_size=disk_size
-	}
-	call bed_annotation.bed_annotation as LCL7bedAnnotation {
-		input:
-		merged_vcf=LCL7mergeVCF.merged_vcf,
-		merged_vcf_idx=LCL7mergeVCF.merged_vcf_idx,
-		repeat_bed=repeat_bed,
-		sample='LCL7',
-		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,
-		vcf_idx=LCL8normZip.vcf_idx,
-		sample='LCL8',
-		cluster_config=cluster_config,
-		disk_size=disk_size
-	}
-	call bed_annotation.bed_annotation as LCL8bedAnnotation {
-		input:
-		merged_vcf=LCL8mergeVCF.merged_vcf,
-		merged_vcf_idx=LCL8mergeVCF.merged_vcf_idx,
-		repeat_bed=repeat_bed,
-		sample='LCL8',
-		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,
-	}
-}
-
+}