renluyao
/
first_consensus_then_mendelian
Segui 1
Vota 0
Forka 0
Codice Problemi 0 Pull Requests 0 Rilasci 0 Wiki Attività
Sfoglia il codice sorgente

filter and benchmark

master
LUYAO REN 5 anni fa
parent
9dd60737da
commit
2cc90ce139
7 ha cambiato i file con 166 aggiunte e 94 eliminazioni
Visualizzazione separata
Diff Options
Show Stats Download Patch File Download Diff File
  1. +36
    -0
      codescripts/get_filtered_benchmark_vcfinfo.py
  2. +1
    -1
      codescripts/merge_two_family_with_genotype.py
  3. +70
    -56
      codescripts/replicates_consensus.py
  4. +3
    -0
      inputs
  5. +43
    -0
      tasks/filtered_benchmark.wdl
  6. +0
    -36
      tasks/two_family_merge.wdl
  7. +13
    -1
      workflow.wdl

+ 36
- 0
codescripts/get_filtered_benchmark_vcfinfo.py Vedi File

@@ -0,0 +1,36 @@
from __future__ import division
import pandas as pd
import sys, argparse, os
import fileinput


# input arguments
parser = argparse.ArgumentParser(description="this script is to get filtered and benchmark vcf info")

parser.add_argument('-filtered', '--filtered', type=str, help='filtered position', required=True)
parser.add_argument('-benchmark', '--benchmark', type=str, help='benchmark position', required=True)
parser.add_argument('-vcf', '--vcf', type=str, help='one specific vcf', required=True)
parser.add_argument('-filename', '--filename', type=str, help='output file name', required=True)


args = parser.parse_args()
filtered = args.filtered
benchmark = args.benchmark
vcf = args.vcf
filename = args.filename


# output file
filtered_filename = filename + '.filtered.txt'
benchmark_filename = filename + '.benchmark.txt'

# input files
filtered_dat = pd.read_table(filtered,header=None)
benchmark_dat = pd.read_table(benchmark,header=None)
vcf_dat = pd.read_table(vcf)

filtered_merged_df = pd.merge(filtered_dat, vcf_dat, how='inner',left_on=[0,1], right_on = ['#CHROM','POS'])
benchmark_merged_df = pd.merge(benchmark_dat,vcf_dat, how='inner',left_on=[0,1], right_on = ['#CHROM','POS'])

filtered_merged_df.to_csv(filtered_filename,sep='\t',index=False)
benchmark_merged_df.to_csv(benchmark_filename,sep='\t',index=False)

+ 1
- 1
codescripts/merge_two_family_with_genotype.py Vedi File

@@ -32,7 +32,7 @@ genotype_dat = pd.read_table(genotype)
merged_df = pd.merge(lcl5_dat, lcl6_dat, how='outer', left_on=['#CHROM','POS'], right_on = ['#CHROM','POS'])
merged_genotype_df = pd.merge(merged_df, genotype_dat, how='outer', left_on=['#CHROM','POS'], right_on = ['#CHROM','POS'])

merged_genotype_df_sub = merged_genotype_df.iloc[:,[0,1,22,23,24,25,26,27,7,17]]
merged_genotype_df_sub = merged_genotype_df.iloc[:,[0,1,23,24,29,30,31,32,7,17]]
merged_genotype_df_sub.columns = ['CHROM', 'POS', 'REF', 'ALT','LCL5','LCL6','LCL7','LCL8', 'TRIO5', 'TRIO6']

for row in merged_genotype_df_sub.itertuples():

+ 70
- 56
codescripts/replicates_consensus.py Vedi File

@@ -63,7 +63,7 @@ vcf_header = '''##fileformat=VCFv4.2
'''
consensus_file_name = prefix + "_consensus.vcf"
consensus_outfile = open(consensus_file_name,'w')
consensus_col = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tLCL5_consensus_calls\tLCL6_consensus_calls\tLCL7_consensus_calls\tLCL8_consensus_calls\n'
consensus_col = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tLCL5_consensus_call\tLCL6_consensus_call\tLCL7_consensus_call\tLCL8_consensus_call\n'
consensus_outfile.write(vcf_header)
consensus_outfile.write(consensus_col)

@@ -132,63 +132,77 @@ def consensus_call(vcf_info_list):


for row in vcf_dat.itertuples():
lcl5_list = [row.Quartet_DNA_BGI_SEQ2000_BGI_LCL5_1_20180518,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL5_2_20180530,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL5_3_20180530, \
row.Quartet_DNA_BGI_T7_WGE_LCL5_1_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL5_2_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL5_3_20191105, \
row.Quartet_DNA_ILM_Nova_ARD_LCL5_1_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL5_2_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL5_3_20181108, \
row.Quartet_DNA_ILM_Nova_ARD_LCL5_4_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL5_5_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL5_6_20190111, \
row.Quartet_DNA_ILM_Nova_BRG_LCL5_1_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL5_2_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL5_3_20180930, \
row.Quartet_DNA_ILM_Nova_WUX_LCL5_1_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL5_2_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL5_3_20190917, \
row.Quartet_DNA_ILM_XTen_ARD_LCL5_1_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL5_2_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL5_3_20170403, \
row.Quartet_DNA_ILM_XTen_NVG_LCL5_1_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL5_2_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL5_3_20170329, \
row.Quartet_DNA_ILM_XTen_WUX_LCL5_1_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL5_2_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL5_3_20170216]
lcl6_list = [row.Quartet_DNA_BGI_SEQ2000_BGI_LCL6_1_20180518,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL6_2_20180530,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL6_3_20180530, \
row.Quartet_DNA_BGI_T7_WGE_LCL6_1_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL6_2_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL6_3_20191105, \
row.Quartet_DNA_ILM_Nova_ARD_LCL6_1_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL6_2_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL6_3_20181108, \
row.Quartet_DNA_ILM_Nova_ARD_LCL6_4_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL6_5_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL6_6_20190111, \
row.Quartet_DNA_ILM_Nova_BRG_LCL6_1_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL6_2_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL6_3_20180930, \
row.Quartet_DNA_ILM_Nova_WUX_LCL6_1_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL6_2_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL6_3_20190917, \
row.Quartet_DNA_ILM_XTen_ARD_LCL6_1_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL6_2_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL6_3_20170403, \
row.Quartet_DNA_ILM_XTen_NVG_LCL6_1_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL6_2_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL6_3_20170329, \
row.Quartet_DNA_ILM_XTen_WUX_LCL6_1_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL6_2_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL6_3_20170216]
lcl7_list = [row.Quartet_DNA_BGI_SEQ2000_BGI_LCL7_1_20180518,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL7_2_20180530,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL7_3_20180530, \
row.Quartet_DNA_BGI_T7_WGE_LCL7_1_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL7_2_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL7_3_20191105, \
row.Quartet_DNA_ILM_Nova_ARD_LCL7_1_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL7_2_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL7_3_20181108, \
row.Quartet_DNA_ILM_Nova_ARD_LCL7_4_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL7_5_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL7_6_20190111, \
row.Quartet_DNA_ILM_Nova_BRG_LCL7_1_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL7_2_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL7_3_20180930, \
row.Quartet_DNA_ILM_Nova_WUX_LCL7_1_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL7_2_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL7_3_20190917, \
row.Quartet_DNA_ILM_XTen_ARD_LCL7_1_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL7_2_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL7_3_20170403, \
row.Quartet_DNA_ILM_XTen_NVG_LCL7_1_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL7_2_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL7_3_20170329, \
row.Quartet_DNA_ILM_XTen_WUX_LCL7_1_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL7_2_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL7_3_20170216]
lcl8_list = [row.Quartet_DNA_BGI_SEQ2000_BGI_LCL8_1_20180518,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL8_2_20180530,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL8_3_20180530, \
row.Quartet_DNA_BGI_T7_WGE_LCL8_1_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL8_2_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL8_3_20191105, \
row.Quartet_DNA_ILM_Nova_ARD_LCL8_1_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL8_2_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL8_3_20181108, \
row.Quartet_DNA_ILM_Nova_ARD_LCL8_4_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL8_5_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL8_6_20190111, \
row.Quartet_DNA_ILM_Nova_BRG_LCL8_1_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL8_2_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL8_3_20180930, \
row.Quartet_DNA_ILM_Nova_WUX_LCL8_1_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL8_2_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL8_3_20190917, \
row.Quartet_DNA_ILM_XTen_ARD_LCL8_1_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL8_2_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL8_3_20170403, \
row.Quartet_DNA_ILM_XTen_NVG_LCL8_1_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL8_2_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL8_3_20170329, \
row.Quartet_DNA_ILM_XTen_WUX_LCL8_1_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL8_2_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL8_3_20170216]
# LCL5
LCL5_consensus_call, LCL5_detected_num, LCL5_same_diff = consensus_call(lcl5_list)
# LCL6
LCL6_consensus_call, LCL6_detected_num, LCL6_same_diff = consensus_call(lcl6_list)
# LCL7
LCL7_consensus_call, LCL7_detected_num, LCL7_same_diff = consensus_call(lcl7_list)
# LCL8
LCL8_consensus_call, LCL8_detected_num, LCL8_same_diff = consensus_call(lcl8_list)
# all data
all_output = row._1 + '\t' + str(row.POS) + '\t' + row.REF + '\t' + row.ALT + '\t' + LCL5_consensus_call + '\t' + str(LCL5_detected_num) + '\t' + LCL5_same_diff + '\t' +\
LCL6_consensus_call + '\t' + str(LCL6_detected_num) + '\t' + LCL6_same_diff + '\t' +\
LCL7_consensus_call + '\t' + str(LCL7_detected_num) + '\t' + LCL7_same_diff + '\t' +\
LCL8_consensus_call + '\t' + str(LCL8_detected_num) + '\t' + LCL8_same_diff + '\n'
all_sample_outfile.write(all_output)
#consensus vcf
one_position = [LCL5_consensus_call,LCL6_consensus_call,LCL7_consensus_call,LCL8_consensus_call]
if ('notConsensus' in one_position) or (((len(set(one_position)) == 1) and ('./.' in set(one_position))) or ((len(set(one_position)) == 1) and ('0/0' in set(one_position))) or ((len(set(one_position)) == 2) and ('0/0' in set(one_position) and ('./.' in set(one_position))))):
# length
#alt
if ',' in row.ALT:
alt = row.ALT.split(',')
alt_len = [len(i) for i in alt]
alt_max = max(alt_len)
else:
alt_max = len(row.ALT)
#ref
ref_len = len(row.REF)
if (alt_max > 50) or (ref_len > 50):
pass
else:
consensus_output = row._1 + '\t' + str(row.POS) + '\t' + '.' + '\t' + row.REF + '\t' + row.ALT + '\t' + '.' + '\t' + '.' + '\t' +'.' + '\t' + 'GT' + '\t' + LCL5_consensus_call + '\t' + LCL6_consensus_call + '\t' + LCL7_consensus_call + '\t' + LCL8_consensus_call +'\n'
consensus_outfile.write(consensus_output)
# consensus
lcl5_list = [row.Quartet_DNA_BGI_SEQ2000_BGI_LCL5_1_20180518,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL5_2_20180530,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL5_3_20180530, \
row.Quartet_DNA_BGI_T7_WGE_LCL5_1_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL5_2_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL5_3_20191105, \
row.Quartet_DNA_ILM_Nova_ARD_LCL5_1_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL5_2_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL5_3_20181108, \
row.Quartet_DNA_ILM_Nova_ARD_LCL5_4_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL5_5_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL5_6_20190111, \
row.Quartet_DNA_ILM_Nova_BRG_LCL5_1_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL5_2_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL5_3_20180930, \
row.Quartet_DNA_ILM_Nova_WUX_LCL5_1_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL5_2_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL5_3_20190917, \
row.Quartet_DNA_ILM_XTen_ARD_LCL5_1_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL5_2_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL5_3_20170403, \
row.Quartet_DNA_ILM_XTen_NVG_LCL5_1_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL5_2_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL5_3_20170329, \
row.Quartet_DNA_ILM_XTen_WUX_LCL5_1_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL5_2_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL5_3_20170216]
lcl6_list = [row.Quartet_DNA_BGI_SEQ2000_BGI_LCL6_1_20180518,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL6_2_20180530,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL6_3_20180530, \
row.Quartet_DNA_BGI_T7_WGE_LCL6_1_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL6_2_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL6_3_20191105, \
row.Quartet_DNA_ILM_Nova_ARD_LCL6_1_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL6_2_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL6_3_20181108, \
row.Quartet_DNA_ILM_Nova_ARD_LCL6_4_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL6_5_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL6_6_20190111, \
row.Quartet_DNA_ILM_Nova_BRG_LCL6_1_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL6_2_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL6_3_20180930, \
row.Quartet_DNA_ILM_Nova_WUX_LCL6_1_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL6_2_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL6_3_20190917, \
row.Quartet_DNA_ILM_XTen_ARD_LCL6_1_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL6_2_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL6_3_20170403, \
row.Quartet_DNA_ILM_XTen_NVG_LCL6_1_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL6_2_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL6_3_20170329, \
row.Quartet_DNA_ILM_XTen_WUX_LCL6_1_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL6_2_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL6_3_20170216]
lcl7_list = [row.Quartet_DNA_BGI_SEQ2000_BGI_LCL7_1_20180518,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL7_2_20180530,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL7_3_20180530, \
row.Quartet_DNA_BGI_T7_WGE_LCL7_1_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL7_2_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL7_3_20191105, \
row.Quartet_DNA_ILM_Nova_ARD_LCL7_1_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL7_2_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL7_3_20181108, \
row.Quartet_DNA_ILM_Nova_ARD_LCL7_4_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL7_5_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL7_6_20190111, \
row.Quartet_DNA_ILM_Nova_BRG_LCL7_1_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL7_2_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL7_3_20180930, \
row.Quartet_DNA_ILM_Nova_WUX_LCL7_1_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL7_2_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL7_3_20190917, \
row.Quartet_DNA_ILM_XTen_ARD_LCL7_1_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL7_2_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL7_3_20170403, \
row.Quartet_DNA_ILM_XTen_NVG_LCL7_1_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL7_2_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL7_3_20170329, \
row.Quartet_DNA_ILM_XTen_WUX_LCL7_1_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL7_2_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL7_3_20170216]
lcl8_list = [row.Quartet_DNA_BGI_SEQ2000_BGI_LCL8_1_20180518,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL8_2_20180530,row.Quartet_DNA_BGI_SEQ2000_BGI_LCL8_3_20180530, \
row.Quartet_DNA_BGI_T7_WGE_LCL8_1_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL8_2_20191105,row.Quartet_DNA_BGI_T7_WGE_LCL8_3_20191105, \
row.Quartet_DNA_ILM_Nova_ARD_LCL8_1_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL8_2_20181108,row.Quartet_DNA_ILM_Nova_ARD_LCL8_3_20181108, \
row.Quartet_DNA_ILM_Nova_ARD_LCL8_4_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL8_5_20190111,row.Quartet_DNA_ILM_Nova_ARD_LCL8_6_20190111, \
row.Quartet_DNA_ILM_Nova_BRG_LCL8_1_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL8_2_20180930,row.Quartet_DNA_ILM_Nova_BRG_LCL8_3_20180930, \
row.Quartet_DNA_ILM_Nova_WUX_LCL8_1_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL8_2_20190917,row.Quartet_DNA_ILM_Nova_WUX_LCL8_3_20190917, \
row.Quartet_DNA_ILM_XTen_ARD_LCL8_1_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL8_2_20170403,row.Quartet_DNA_ILM_XTen_ARD_LCL8_3_20170403, \
row.Quartet_DNA_ILM_XTen_NVG_LCL8_1_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL8_2_20170329,row.Quartet_DNA_ILM_XTen_NVG_LCL8_3_20170329, \
row.Quartet_DNA_ILM_XTen_WUX_LCL8_1_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL8_2_20170216,row.Quartet_DNA_ILM_XTen_WUX_LCL8_3_20170216]
# LCL5
LCL5_consensus_call, LCL5_detected_num, LCL5_same_diff = consensus_call(lcl5_list)
# LCL6
LCL6_consensus_call, LCL6_detected_num, LCL6_same_diff = consensus_call(lcl6_list)
# LCL7
LCL7_consensus_call, LCL7_detected_num, LCL7_same_diff = consensus_call(lcl7_list)
# LCL8
LCL8_consensus_call, LCL8_detected_num, LCL8_same_diff = consensus_call(lcl8_list)
# all data
all_output = row._1 + '\t' + str(row.POS) + '\t' + row.REF + '\t' + row.ALT + '\t' + LCL5_consensus_call + '\t' + str(LCL5_detected_num) + '\t' + LCL5_same_diff + '\t' +\
LCL6_consensus_call + '\t' + str(LCL6_detected_num) + '\t' + LCL6_same_diff + '\t' +\
LCL7_consensus_call + '\t' + str(LCL7_detected_num) + '\t' + LCL7_same_diff + '\t' +\
LCL8_consensus_call + '\t' + str(LCL8_detected_num) + '\t' + LCL8_same_diff + '\n'
all_sample_outfile.write(all_output)
#consensus vcf
one_position = [LCL5_consensus_call,LCL6_consensus_call,LCL7_consensus_call,LCL8_consensus_call]
if ('notConsensus' in one_position) or (((len(set(one_position)) == 1) and ('./.' in set(one_position))) or ((len(set(one_position)) == 1) and ('0/0' in set(one_position))) or ((len(set(one_position)) == 2) and ('0/0' in set(one_position) and ('./.' in set(one_position))))):
pass
else:
consensus_output = row._1 + '\t' + str(row.POS) + '\t' + '.' + '\t' + row.REF + '\t' + row.ALT + '\t' + '.' + '\t' + '.' + '\t' +'.' + '\t' + 'GT' + '\t' + LCL5_consensus_call + '\t' + LCL6_consensus_call + '\t' + LCL7_consensus_call + '\t' + LCL8_consensus_call +'\n'
consensus_outfile.write(consensus_output)




+ 3
- 0
inputs Vedi File

@@ -2,9 +2,12 @@
"{{ project_name }}.fasta": "GRCh38.d1.vd1.fa",
"{{ project_name }}.replicate_consensus.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.4",
"{{ project_name }}.chromo_file": "{{ chromo_file }}",
"{{ project_name }}.filtered_benchmark.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.4",
"{{ project_name }}.mendelian.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/vbt:v1.1",
"{{ project_name }}.disk_size": "150",
"{{ project_name }}.LCL5_benchmark_call": "{{ LCL5_benchmark_call }}",
"{{ project_name }}.chromo": "{{ chromo }}",
"{{ project_name }}.LCL5_info_dir": "{{ LCL5_info_dir }}",
"{{ project_name }}.cluster_config": "OnDemand bcs.b4.xlarge img-ubuntu-vpc",
"{{ project_name }}.ref_dir": "oss://chinese-quartet/quartet-storage-data/reference_data/"
}

+ 43
- 0
tasks/filtered_benchmark.wdl Vedi File

@@ -0,0 +1,43 @@
task filtered_benchmark {
File chromo_consensus
File LCL5_info_dir
File LCL5_benchmark_call
String chromo
String docker
String cluster_config
String disk_size
command <<<
# get filtered chr and pos
cat ${chromo_consensus} | cut -f1-7 | grep notConsensus > ${chromo}.filtered.txt
cat ${chromo_consensus} | cut -f1-7 | grep '\./\.' >> ${chromo}.filtered.txt
# get benchmark chr and pos
zcat ${LCL5_benchmark_call} | grep -v '##' | grep -w ${chromo} > LCL5.benchmark.${chromo}.txt
# get vcf infomation
cat ${LCL5_info_dir}/Quartet_DNA_BGI_SEQ2000_BGI_LCL5_1_20180518_mendelian_vcfInfo.vcf | grep -v '##' > Quartet_DNA_BGI_SEQ2000_BGI_LCL5_1_20180518_mendelian_vcfInfo.txt
python /opt/get_filtered_benchmark_vcfinfo.py -filtered ${chromo}.filtered.txt -benchmark LCL5.benchmark.${chromo}.txt -vcf Quartet_DNA_BGI_SEQ2000_BGI_LCL5_1_20180518_mendelian_vcfInfo.txt -filename Quartet_DNA_BGI_SEQ2000_BGI_LCL5_1_20180518.${chromo}

cat ${LCL5_info_dir}/Quartet_DNA_BGI_SEQ2000_BGI_LCL5_2_20180530_mendelian_vcfInfo.vcf | grep -v '##' > Quartet_DNA_BGI_SEQ2000_BGI_LCL5_2_20180530_mendelian_vcfInfo.txt
python /opt/get_filtered_benchmark_vcfinfo.py -filtered ${chromo}.filtered.txt -benchmark LCL5.benchmark.${chromo}.txt -vcf Quartet_DNA_BGI_SEQ2000_BGI_LCL5_2_20180530_mendelian_vcfInfo.txt -filename Quartet_DNA_BGI_SEQ2000_BGI_LCL5_2_20180530.${chromo}

cat ${LCL5_info_dir}/Quartet_DNA_BGI_SEQ2000_BGI_LCL5_3_20180530_mendelian_vcfInfo.vcf | grep -v '##' >
Quartet_DNA_BGI_SEQ2000_BGI_LCL5_3_20180530_mendelian_vcfInfo.txt
python /opt/get_filtered_benchmark_vcfinfo.py -filtered ${chromo}.filtered.txt -benchmark LCL5.benchmark.${chromo}.txt -vcf Quartet_DNA_BGI_SEQ2000_BGI_LCL5_3_20180530_mendelian_vcfInfo.txt -filename Quartet_DNA_BGI_SEQ2000_BGI_LCL5_3_20180530.${chromo}

>>>

runtime {
docker:docker
cluster: cluster_config
systemDisk: "cloud_ssd 40"
dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
}

output {
File filtered = "${chromo}.filtered.txt"
File benchmark = "LCL5.benchmark.${chromo}.txt"
Array[File] filtered_vcf = glob("*.${chromo}.filtered.txt")
Array[File] benchmark_vcf = glob("*.${chromo}.benchmark.txt")
}

}

+ 0
- 36
tasks/two_family_merge.wdl Vedi File

@@ -1,36 +0,0 @@
task two_family_merge {
File LCL5_trio_vcf
File LCL6_trio_vcf
File genotype_file
String family_chromo_name
String docker
String cluster_config
String disk_size
command <<<
cat ${LCL5_trio_vcf} | grep -v '##' > ${family_chromo_name}.LCL5.txt
cat ${LCL6_trio_vcf} | grep -v '##' > ${family_chromo_name}.LCL6.txt
cat ${genotype_file} | grep -v '##' | awk '
BEGIN { OFS = "\t" }
NF > 2 && FNR > 1 {
for ( i=9; i<=NF; i++ ) {
split($i,a,":") ;$i = a[1];
}
}
{ print }
' | cut -f1,2,4,5,10- > ${family_chromo_name}.genotype.txt
python /opt/merge_two_family_with_genotype.py -LCL5 ${family_chromo_name}.LCL5.txt -LCL6 ${family_chromo_name}.LCL6.txt -genotype ${family_chromo_name}.genotype.txt -family ${family_chromo_name}
>>>

runtime {
docker:docker
cluster: cluster_config
systemDisk: "cloud_ssd 40"
dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
}

output {
File family_mendelian_info = "${family_chromo_name}.txt"
}

}

+ 13
- 1
workflow.wdl Vedi File

@@ -1,10 +1,13 @@
import "./tasks/replicate_consensus.wdl" as replicate_consensus
import "./tasks/mendelian.wdl" as mendelian
import "./tasks/filtered_benchmark.wdl" as filtered_benchmark

workflow {{ project_name }} {
File ref_dir
String fasta
File LCL5_info_dir
File LCL5_benchmark_call
File chromo_file
String fasta
String chromo
String cluster_config
String disk_size
@@ -26,4 +29,13 @@ workflow {{ project_name }} {
cluster_config=cluster_config,
disk_size=disk_size
}
call filtered_benchmark.filtered_benchmark as filtered_benchmark{
input:
chromo_consensus=replicate_consensus.chromo_consensus,
LCL5_info_dir=LCL5_info_dir,
LCL5_benchmark_call=LCL5_benchmark_call,
chromo=chromo,
cluster_config=cluster_config,
disk_size=disk_size
}
}

Write Preview
Loading…
Annulla
Salva