renluyao
/
high_confidence_calls_manuscript
Observar 1
Favorito 0
Fork 0
Código Issues 0 Pull requests 0 Versões 0 Wiki Atividade
Você não pode selecionar mais de 25 tópicos Os tópicos devem começar com uma letra ou um número, podem incluir traços ('-') e podem ter até 35 caracteres.
11 Commits
1 Branch
Tag: c0415bc2de
Branches Tags
${ item.name }
Criar branch ${ searchTerm }
de c0415bc2de
${ noResults }
high_confidence_calls_manus.../codescripts/FinalResult2VCF.py

296 linhas
23KB
Original Anotar Histórico 

  1. from __future__ import division

  2. import pandas as pd

  3. import sys, argparse, os

  4. import fileinput

  5. import re

  6. 

  7. # input arguments

  8. parser = argparse.ArgumentParser(description="this script is to get final high confidence calls and information of all replicates")

  9. 

  10. 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)

  11. parser.add_argument('-mendelianInfo', '--mendelianInfo', type=str, help='The merged mendelian information of all samples',  required=True)

  12. parser.add_argument('-prefix', '--prefix', type=str, help='The prefix of output filenames',  required=True)

  13. parser.add_argument('-sample', '--sample_name', type=str, help='which sample of quartet',  required=True)

  14. 

  15. 

  16. args = parser.parse_args()

  17. vcfInfo = args.vcfInfo

  18. mendelianInfo = args.mendelianInfo

  19. prefix = args.prefix

  20. sample_name = args.sample_name

  21. 

  22. vcf_header = '''##fileformat=VCFv4.2

  23. ##fileDate=20200331

  24. ##source=high_confidence_calls_intergration(choppy app)

  25. ##reference=GRCh38.d1.vd1

  26. ##INFO=<ID=location,Number=1,Type=String,Description="Repeat region">

  27. ##INFO=<ID=DPCT,Number=1,Type=Float,Description="Percentage of detected votes">

  28. ##INFO=<ID=VPCT,Number=1,Type=Float,Description="Percentage of consnesus votes">

  29. ##INFO=<ID=FPCT,Number=1,Type=Float,Description="Percentage of mendelian consisitent votes">

  30. ##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">

  31. ##FORMAT=<ID=DP,Number=1,Type=Int,Description="Depth">

  32. ##FORMAT=<ID=AF,Number=1,Type=Float,Description="Allele frequency">

  33. ##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype quality">

  34. ##FORMAT=<ID=MQ,Number=1,Type=Float,Description="Mapping quality">

  35. ##contig=<ID=chr1,length=248956422>

  36. ##contig=<ID=chr2,length=242193529>

  37. ##contig=<ID=chr3,length=198295559>

  38. ##contig=<ID=chr4,length=190214555>

  39. ##contig=<ID=chr5,length=181538259>

  40. ##contig=<ID=chr6,length=170805979>

  41. ##contig=<ID=chr7,length=159345973>

  42. ##contig=<ID=chr8,length=145138636>

  43. ##contig=<ID=chr9,length=138394717>

  44. ##contig=<ID=chr10,length=133797422>

  45. ##contig=<ID=chr11,length=135086622>

  46. ##contig=<ID=chr12,length=133275309>

  47. ##contig=<ID=chr13,length=114364328>

  48. ##contig=<ID=chr14,length=107043718>

  49. ##contig=<ID=chr15,length=101991189>

  50. ##contig=<ID=chr16,length=90338345>

  51. ##contig=<ID=chr17,length=83257441>

  52. ##contig=<ID=chr18,length=80373285>

  53. ##contig=<ID=chr19,length=58617616>

  54. ##contig=<ID=chr20,length=64444167>

  55. ##contig=<ID=chr21,length=46709983>

  56. ##contig=<ID=chr22,length=50818468>

  57. ##contig=<ID=chrX,length=156040895>

  58. '''

  59. 

  60. vcf_header_all_sample = '''##fileformat=VCFv4.2

  61. ##fileDate=20200331

  62. ##reference=GRCh38.d1.vd1

  63. ##INFO=<ID=location,Number=1,Type=String,Description="Repeat region">

  64. ##INFO=<ID=DPCT,Number=1,Type=Float,Description="Percentage of detected votes">

  65. ##INFO=<ID=VPCT,Number=1,Type=Float,Description="Percentage of consnesus votes">

  66. ##INFO=<ID=FPCT,Number=1,Type=Float,Description="Percentage of mendelian consisitent votes">

  67. ##INFO=<ID=ALL_ALT,Number=1,Type=Float,Description="Sum of alternative reads of all samples">

  68. ##INFO=<ID=ALL_DP,Number=1,Type=Float,Description="Sum of depth of all samples">

  69. ##INFO=<ID=ALL_AF,Number=1,Type=Float,Description="Allele frequency of net alternatice reads and net depth">

  70. ##INFO=<ID=GQ_MEAN,Number=1,Type=Float,Description="Mean of genotype quality of all samples">

  71. ##INFO=<ID=MQ_MEAN,Number=1,Type=Float,Description="Mean of mapping quality of all samples">

  72. ##INFO=<ID=PCR,Number=1,Type=String,Description="Consensus of PCR votes">

  73. ##INFO=<ID=PCR_FREE,Number=1,Type=String,Description="Consensus of PCR-free votes">

  74. ##INFO=<ID=CONSENSUS,Number=1,Type=String,Description="Consensus calls">

  75. ##INFO=<ID=CONSENSUS_SEQ,Number=1,Type=String,Description="Consensus sequence">

  76. ##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">

  77. ##FORMAT=<ID=DP,Number=1,Type=String,Description="Depth">

  78. ##FORMAT=<ID=AF,Number=1,Type=String,Description="Allele frequency">

  79. ##FORMAT=<ID=GQ,Number=1,Type=String,Description="Genotype quality">

  80. ##FORMAT=<ID=MQ,Number=1,Type=String,Description="Mapping quality">

  81. ##FORMAT=<ID=TWINS,Number=1,Type=String,Description="1 is twins shared, 0 is twins discordant ">

  82. ##FORMAT=<ID=TRIO5,Number=1,Type=String,Description="1 is LCL7, LCL8 and LCL5 mendelian consistent, 0 is mendelian vioaltion">

  83. ##FORMAT=<ID=TRIO6,Number=1,Type=String,Description="1 is LCL7, LCL8 and LCL6 mendelian consistent, 0 is mendelian vioaltion">

  84. ##contig=<ID=chr1,length=248956422>

  85. ##contig=<ID=chr2,length=242193529>

  86. ##contig=<ID=chr3,length=198295559>

  87. ##contig=<ID=chr4,length=190214555>

  88. ##contig=<ID=chr5,length=181538259>

  89. ##contig=<ID=chr6,length=170805979>

  90. ##contig=<ID=chr7,length=159345973>

  91. ##contig=<ID=chr8,length=145138636>

  92. ##contig=<ID=chr9,length=138394717>

  93. ##contig=<ID=chr10,length=133797422>

  94. ##contig=<ID=chr11,length=135086622>

  95. ##contig=<ID=chr12,length=133275309>

  96. ##contig=<ID=chr13,length=114364328>

  97. ##contig=<ID=chr14,length=107043718>

  98. ##contig=<ID=chr15,length=101991189>

  99. ##contig=<ID=chr16,length=90338345>

  100. ##contig=<ID=chr17,length=83257441>

  101. ##contig=<ID=chr18,length=80373285>

  102. ##contig=<ID=chr19,length=58617616>

  103. ##contig=<ID=chr20,length=64444167>

  104. ##contig=<ID=chr21,length=46709983>

  105. ##contig=<ID=chr22,length=50818468>

  106. ##contig=<ID=chrX,length=156040895>

  107. '''

  108. 

  109. # output file

  110. file_name = prefix + '_benchmarking_calls.vcf'

  111. outfile = open(file_name,'w')

  112. 

  113. all_sample_file_name = prefix + '_all_sample_information.vcf'

  114. all_sample_outfile = open(all_sample_file_name, 'w')

  115. 

  116. # write VCF

  117. outputcolumn = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t' + sample_name + '_high_confidence_calls\n'

  118. outfile.write(vcf_header)

  119. outfile.write(outputcolumn)

  120. 

  121. outputcolumn_all_sample = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t'+ \

  122. 'Quartet_DNA_BGI_SEQ2000_BGI_1_20180518\tQuartet_DNA_BGI_SEQ2000_BGI_2_20180530\tQuartet_DNA_BGI_SEQ2000_BGI_3_20180530\t' + \

  123. 'Quartet_DNA_BGI_T7_WGE_1_20191105\tQuartet_DNA_BGI_T7_WGE_2_20191105\tQuartet_DNA_BGI_T7_WGE_3_20191105\t' + \

  124. 'Quartet_DNA_ILM_Nova_ARD_1_20181108\tQuartet_DNA_ILM_Nova_ARD_2_20181108\tQuartet_DNA_ILM_Nova_ARD_3_20181108\t' + \

  125. 'Quartet_DNA_ILM_Nova_ARD_4_20190111\tQuartet_DNA_ILM_Nova_ARD_5_20190111\tQuartet_DNA_ILM_Nova_ARD_6_20190111\t' + \

  126. 'Quartet_DNA_ILM_Nova_BRG_1_20180930\tQuartet_DNA_ILM_Nova_BRG_2_20180930\tQuartet_DNA_ILM_Nova_BRG_3_20180930\t' + \

  127. 'Quartet_DNA_ILM_Nova_WUX_1_20190917\tQuartet_DNA_ILM_Nova_WUX_2_20190917\tQuartet_DNA_ILM_Nova_WUX_3_20190917\t' + \

  128. 'Quartet_DNA_ILM_XTen_ARD_1_20170403\tQuartet_DNA_ILM_XTen_ARD_2_20170403\tQuartet_DNA_ILM_XTen_ARD_3_20170403\t' + \

  129. 'Quartet_DNA_ILM_XTen_NVG_1_20170329\tQuartet_DNA_ILM_XTen_NVG_2_20170329\tQuartet_DNA_ILM_XTen_NVG_3_20170329\t' + \

  130. 'Quartet_DNA_ILM_XTen_WUX_1_20170216\tQuartet_DNA_ILM_XTen_WUX_2_20170216\tQuartet_DNA_ILM_XTen_WUX_3_20170216\n'

  131. all_sample_outfile.write(vcf_header_all_sample)

  132. all_sample_outfile.write(outputcolumn_all_sample)

  133. 

  134. # input files

  135. vcf_info = pd.read_table(vcfInfo)

  136. mendelian_info = pd.read_table(mendelianInfo)

  137. 

  138. merged_df = pd.merge(vcf_info, mendelian_info,  how='outer', left_on=['#CHROM','POS'], right_on = ['#CHROM','POS'])

  139. merged_df = merged_df.fillna('.')

  140. 

  141. # function

  142. def single_sample_format(format_x,strings_x,strings_y):

  143. 	gt = '.'

  144. 	dp = '.'

  145. 	af = '.'

  146. 	gq = '.'

  147. 	mq = '.'

  148. 	twins = '.'

  149. 	trio5 = '.'

  150. 	trio6 = '.'

  151. 	# GT:DP:AF:GQ:MQ:TWINS:TRIO5:TRIO6

  152. 	# strings_x

  153. 	format_strings = format_x.split(':')

  154. 	if (strings_x == '.') and (strings_y != '.'):

  155. 		element_strings_y = str(strings_y).split(':')

  156. 		gt = '0/0'

  157. 		dp = '.'

  158. 		af = '.'

  159. 		gq = '.'

  160. 		mq = '.'

  161. 		twins = element_strings_y[1]

  162. 		trio5 = element_strings_y[2]

  163. 		trio6 = element_strings_y[3]		

  164. 	elif (strings_x != '.') and (strings_y == '.'):

  165. 		element_strings_x = strings_x.split(':')

  166. 		formatDict = dict(zip(format_strings, element_strings_x))

  167. 		gt = formatDict['GT']

  168. 		dp = formatDict['DP']

  169. 		af = formatDict['AF']

  170. 		gq = formatDict['GQ']

  171. 		mq = formatDict['MQ']

  172. 		twins = '.'

  173. 		trio5 = '.'

  174. 		trio6 = '.'

  175. 	elif (strings_x != '.') and (strings_y != '.'):

  176. 		element_strings_y = str(strings_y).split(':')

  177. 		element_strings_x = strings_x.split(':')

  178. 		formatDict = dict(zip(format_strings, element_strings_x))

  179. 		gt = formatDict['GT']

  180. 		dp = formatDict['DP']

  181. 		af = formatDict['AF']

  182. 		gq = formatDict['GQ']

  183. 		mq = formatDict['MQ']

  184. 		twins = element_strings_y[1]

  185. 		trio5 = element_strings_y[2]

  186. 		trio6 = element_strings_y[3]				

  187. 	else:

  188. 		pass

  189. 	merged_format = gt + ':' + dp + ':' + af + ':' + gq + ':' + mq + ':' + twins + ':' + trio5 + ':' + trio6

  190. 	return(merged_format)

  191. 

  192. #

  193. for row in merged_df.itertuples():

  194. 	vcf_count = row[10:37].count('.')

  195. 	mendelian_count = row[50:77].count('.')

  196. 	if vcf_count == mendelian_count:

  197. 		info = 'location=' + str(row.location) + ';' + str(row.INFO_y)

  198. 		if row.FILTER_y == 'reproducible':

  199. 			ref = row.DP - row._42

  200. 			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))

  201. 			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'

  202. 			outfile.write(outline1)

  203. 		else:

  204. 			pass

  205. 		if row.INFO_x != '.':

  206. 			if row.AF=='.':

  207. 				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])			

  208. 			else:

  209. 				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])			

  210. 			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)

  211. 			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)

  212. 			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)

  213. 			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)

  214. 			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)

  215. 			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)

  216. 			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)

  217. 			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)

  218. 			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)

  219. 			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)

  220. 			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)

  221. 			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)

  222. 			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)

  223. 			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)

  224. 			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)

  225. 			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)

  226. 			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)

  227. 			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)

  228. 			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)

  229. 			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)

  230. 			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)

  231. 			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)

  232. 			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)

  233. 			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)

  234. 			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)

  235. 			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)

  236. 			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)

  237. 			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' \

  238. 			+ 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' \

  239. 			+ 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' \

  240. 			+ 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' \

  241. 			+ 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' \

  242. 			+ 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' \

  243. 			+ 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' \

  244. 			+ 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' \

  245. 			+ 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' \

  246. 			+ 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'

  247. 			all_sample_outfile.write(outline2)

  248. 		else:

  249. 			info = '.'

  250. 			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)

  251. 			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)

  252. 			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)

  253. 			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)

  254. 			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)

  255. 			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)

  256. 			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)

  257. 			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)

  258. 			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)

  259. 			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)

  260. 			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)

  261. 			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)

  262. 			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)

  263. 			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)

  264. 			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)

  265. 			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)

  266. 			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)

  267. 			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)

  268. 			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)

  269. 			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)

  270. 			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)

  271. 			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)

  272. 			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)

  273. 			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)

  274. 			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)

  275. 			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)

  276. 			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)

  277. 			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' \

  278. 			+ 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' \

  279. 			+ 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' \

  280. 			+ 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' \

  281. 			+ 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' \

  282. 			+ 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' \

  283. 			+ 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' \

  284. 			+ 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' \

  285. 			+ 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' \

  286. 			+ 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'

  287. 			all_sample_outfile.write(outline2)

  288. 		else:

  289. 

  290. 

  291. 

  292. 

  293. 

  294.