|
- from __future__ import division
- import pandas as pd
- import sys, argparse, os
-
-
- # input arguments
- parser = argparse.ArgumentParser(description="this script is to calculate reproducibility between Quartet_D5 and Quartet_D6s")
-
- parser.add_argument('-sister', '--sister', type=str, help='sister.txt', required=True)
- parser.add_argument('-project', '--project', type=str, help='project name', required=True)
-
-
- args = parser.parse_args()
- sister_file = args.sister
- project_name = args.project
-
- # output file
- output_name = project_name + '.sister.reproducibility.txt'
-
- output_file = open(output_name,'w')
-
- # input files
- sister_dat = pd.read_table(sister_file)
-
- sister_same = 0
- sister_diff = 0
-
- for row in sister_dat.itertuples():
- # sister
- if row[5] == row[6]:
- if row[5] == './.':
- mendelian = 'noInfo'
- sister_count = "no"
- elif row[5] == '0/0':
- mendelian = 'Ref'
- sister_count = "no"
- else:
- mendelian = '1'
- sister_count = "yes_same"
- else:
- mendelian = '0'
- if (row[5] == './.' or row[5] == '0/0') and (row[6] == './.' or row[6] == '0/0'):
- sister_count = "no"
- else:
- sister_count = "yes_diff"
- if sister_count == 'yes_same':
- sister_same += 1
- elif sister_count == 'yes_diff':
- sister_diff += 1
- else:
- pass
-
- sister = sister_same/(sister_same + sister_diff)
- outcolumn = 'Project\tReproducibility_D5_D6\n'
- outResult = project_name + '\t' + str(sister) + '\n'
- output_file.write(outcolumn)
- output_file.write(outResult)
-
-
|
