chaopower
/
pipeline
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

bug

master
chaopower 2024-01-10 09:46:04 +08:00
parent 39ba3fdaab
commit def064acf4
1 changed files with 17 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
codes/pollution.py
View File

@ -109,9 +109,15 @@ def process_judge_vcf(input_vcf, output_vcf):
for line in input_file: for line in input_file:
if not line.startswith("#"): if not line.startswith("#"):
fields = line.strip().split('\t') fields = line.strip().split('\t')
info = fields[9].split(":")
percentage = float(info[6])
vcf_format = fields[8].split(":")
vcf_normal = fields[-1].split(":")
vcf_info = dict(zip(vcf_format, vcf_normal))
af = vcf_info['AF']
vd = vcf_info['VD']
# info = fields[9].split(":")
# percentage = float(info[6])
percentage = float(af)
if 0.1 <= percentage <= 0.9: if 0.1 <= percentage <= 0.9:
b = 0.5 b = 0.5
elif percentage < 0.1: elif percentage < 0.1:
@ -120,7 +126,7 @@ def process_judge_vcf(input_vcf, output_vcf):
b = 1 b = 1
# 构建新的行数据 # 构建新的行数据
new_line = '\t'.join([fields[0], fields[1], fields[3], fields[4], info[4], str(b), info[2]]) new_line = '\t'.join([fields[0], fields[1], fields[3], fields[4], af, str(b), vd])
output_file.write(new_line + '\n') output_file.write(new_line + '\n')
return output_vcf return output_vcf
@ -198,8 +204,14 @@ def select_cnvkit_vcf(vcf, bed, output_file):
line.split()[1] == str(position_list[i]) and line.split()[0] == str(chr_list[i]) and len( line.split()[1] == str(position_list[i]) and line.split()[0] == str(chr_list[i]) and len(
line.split()[3]) < 2 and len(line.split()[4]) < 2] line.split()[3]) < 2 and len(line.split()[4]) < 2]
for line in filtered_lines: for line in filtered_lines:
p_value_str = line.split()[9].split(":")[6] # p_value_str = line.split()[9].split(":")[6]
p_value = float(p_value_str[:-1]) / 100 if p_value_str[-1] == "%" else float(p_value_str) # p_value = float(p_value_str[:-1]) / 100 if p_value_str[-1] == "%" else float(p_value_str)
vcf_format = line.split('\t')[8].split(":")
vcf_normal = line.split('\t')[-1].split(":")
vcf_info = dict(zip(vcf_format, vcf_normal))
p_value = float(vcf_info['AF'])
if 0.1 <= p_value <= 0.9: if 0.1 <= p_value <= 0.9:
result_data.append(line) result_data.append(line)