101 lines
4.8 KiB
Python
Executable File
101 lines
4.8 KiB
Python
Executable File
#!/usr/bin/env python3
|
||
|
||
import argparse
|
||
import json
|
||
import os.path
|
||
|
||
import pandas as pd
|
||
|
||
|
||
def check(outputf, tumorf, normalf=None, genderf=None, cms=None):
|
||
# qc_check = {
|
||
# 'Q30(%)': 85,
|
||
# 'clean_reads_rate(%)': 90,
|
||
# 'mapped_rate(%)': 90,
|
||
# 'capture_rate(reads)': 50,
|
||
# 'mean_depth(dedup)': 500,
|
||
# 'mean_depth(dedup)_umi': 1000,
|
||
# 'coverage(>=80%)': 500,
|
||
# 'coverage(>=80%)_umi': 1000,
|
||
# 'coverage(>=0.2*meanx)': 95,
|
||
# 'coverage(>10x)': 90,
|
||
# 'coverage(>=0.1*meanx)': 90,
|
||
# 'concordence': 99,
|
||
# 'contamination_n': 1,
|
||
# 'contamination_t': 1,
|
||
# }
|
||
|
||
qc_t = pd.read_csv(tumorf, sep="\t", index_col=0, header=None).T
|
||
|
||
out = open(outputf, 'w')
|
||
|
||
##tumor
|
||
if float(qc_t['Q30(%)'][1]) < 85:
|
||
out.write('\t'.join(("Tumor:", "Q30(%)", str(qc_t['Q30(%)'][1]), "(<85%)\n")))
|
||
if float(qc_t['clean_reads_rate(%)'][1]) < 90:
|
||
out.write('\t'.join(("Tumor:", "clean_reads_rate(%)", str(qc_t['clean_reads_rate(%)'][1]), "(<90%)\n")))
|
||
if float(qc_t['mapped_rate(%)'][1]) < 90:
|
||
out.write('\t'.join(("Tumor:", "mapped_rate(%)", str(qc_t['mapped_rate(%)'][1]), "(<90%)\n")))
|
||
if float(qc_t['capture_rate(reads)'][1]) < 50:
|
||
out.write('\t'.join(("Tumor:", "capture_rate(reads)", str(qc_t['capture_rate(reads)'][1]), "(<50%)\n")))
|
||
if float(qc_t['mean_depth(dedup)'][1]) < 500:
|
||
out.write('\t'.join(("Tumor:", "mean_depth(dedup)", str(qc_t['mean_depth(dedup)'][1]), "(<500X)\n")))
|
||
if float(qc_t['coverage(>=80%)'][1]) < 500:
|
||
out.write('\t'.join(("Tumor:", "coverage(>=80%)", str(qc_t['coverage(>=80%)'][1]), "(<500X)\n")))
|
||
if float(qc_t['coverage(>=0.2*meanx)'][1]) < 95:
|
||
out.write('\t'.join(("Tumor:", "coverage(>=0.2*meanx)", str(qc_t['coverage(>=0.2*meanx)'][1]), "(<95%)\n")))
|
||
if float(qc_t['coverage(>10x)'][1]) < 95:
|
||
out.write('\t'.join(("Tumor:", "coverage(>10x)", str(qc_t['coverage(>10x)'][1]), "(<95%)\n")))
|
||
|
||
if os.path.exists(normalf):
|
||
qc_n = pd.read_csv(normalf, sep="\t", index_col=0, header=None).T
|
||
##normal
|
||
if float(qc_n['Q30(%)'][1]) < 85:
|
||
out.write('\t'.join(("Normal:", "Q30(%)", str(qc_n['Q30(%)'][1]), "(<85%)\n")))
|
||
if float(qc_n['clean_reads_rate(%)'][1]) < 90:
|
||
out.write('\t'.join(("Normal:", "clean_reads_rate(%)", str(qc_n['clean_reads_rate(%)'][1]), "(<90%)\n")))
|
||
if float(qc_n['mapped_rate(%)'][1]) < 90:
|
||
out.write('\t'.join(("Normal:", "mapped_rate(%)", str(qc_n['mapped_rate(%)'][1]), "(<90%)\n")))
|
||
if float(qc_n['capture_rate(reads)'][1]) < 50:
|
||
out.write('\t'.join(("Normal:", "capture_rate(reads)", str(qc_n['capture_rate(reads)'][1]), "(<50%)\n")))
|
||
if float(qc_n['coverage(>=80%)'][1]) < 100:
|
||
out.write('\t'.join(("Normal:", "coverage(>=80%)", str(qc_n['coverage(>=80%)'][1]), "(<100X)\n")))
|
||
if float(qc_n['coverage(>=0.2*meanx)'][1]) < 95:
|
||
out.write(
|
||
'\t'.join(("Normal:", "coverage(>=0.2*meanx)", str(qc_n['coverage(>=0.2*meanx)'][1]), "(<95%)\n")))
|
||
if float(qc_n['coverage(>10x)'][1]) < 95:
|
||
out.write('\t'.join(("Normal:", "coverage(>10x)", str(qc_n['coverage(>10x)'][1]), "(<95%)\n")))
|
||
if os.path.exists(str(genderf)):
|
||
genderf_df = pd.read_csv(genderf, sep='\t')
|
||
genderf_dict = genderf_df.to_dict(orient='records')[0]
|
||
gender_cms = ''
|
||
if os.path.exists(str(cms)):
|
||
cmsf = open(cms, "r")
|
||
cmsj = json.load(cmsf)
|
||
gender_cms_data = cmsj.get('data', [])
|
||
if gender_cms_data:
|
||
gender_cms = gender_cms_data[0].get('gender', '')
|
||
if gender_cms:
|
||
genderf_dict['gender_cms'] = gender_cms
|
||
genderf_r = [k for k, v in genderf_dict.items() if list(genderf_dict.values()).count(v) == 1]
|
||
if genderf_r:
|
||
out.write('\t'.join(("性别鉴定不一致:", str(genderf_dict))))
|
||
else:
|
||
out.write('\t'.join(("性别鉴定:", 'lims系统提供信息有误，请核查')))
|
||
else:
|
||
out.write('\t'.join(("性别鉴定:", '流程未进行性别鉴定评估')))
|
||
|
||
out.close()
|
||
|
||
|
||
if __name__ == '__main__':
|
||
parser = argparse.ArgumentParser(description="Check qcfile")
|
||
parser.add_argument('-n', '--barcode', help="sample's qcfile", required=True)
|
||
parser.add_argument('-s', '--normal', help="normal's file", default='', required=False, nargs='?')
|
||
parser.add_argument('-p', '--gender', help="gender file", default='', required=False, nargs='?')
|
||
parser.add_argument('-c', '--cms', help="cms's file", default='', required=False, nargs='?')
|
||
parser.add_argument('-o', '--output_file', help="Output directory, default ", required=True)
|
||
|
||
args = parser.parse_args()
|
||
check(args.output_file, args.barcode, args.normal, args.gender, args.cms)
|