Mercurial > repos > iuc > humann_renorm_table

comparison test-data/test-db/metaphlan-db/customizemapping.py @ 2:d7e9a3c41657 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/humann commit 0966faf8782e9043772acfa32f4a4281687a19dd
author iuc
date Tue, 07 Feb 2023 19:46:09 +0000
parents
children
comparison
equal deleted inserted replaced
1:4137b492233e 2:d7e9a3c41657
1 #!/usr/bin/env python
2 # -*- coding: utf-8 -*-
3 # Script to generate a extract a custom mapping file from input mapping file.
4 # Mostly used for a reduced-size demo data generation.
5
6
7 import argparse
8 from pathlib import Path
9
10
11 if __name__ == '__main__':
12 # Read command line
13 parser = argparse.ArgumentParser(description='Customize HUMAnN utility mapping')
14 parser.add_argument('--in_mapping', help="Path to mapping file to reduce")
15 parser.add_argument('--features', help="Path to tabular file with features to keep in first column")
16 parser.add_argument('--elements', help="Path to tabular file with elements to keep in other columns")
17 parser.add_argument('--out_mapping', help="Path to reduced mapping file")
18 args = parser.parse_args()
19
20 in_mapping_fp = Path(args.in_mapping)
21 feature_fp = Path(args.features)
22 element_fp = Path(args.elements)
23 out_mapping_fp = Path(args.out_mapping)
24
25 # extract features to keep
26 features = set()
27 with open(feature_fp, 'r') as feature_f:
28 for line in feature_f.readlines():
29 features.add(line.split("\t")[0])
30 print(features)
31
32 # extract elements to keep
33 elements = set()
34 with open(element_fp, 'r') as element_f:
35 for line in element_f.readlines():
36 elements.add(line.split("\t")[0])
37 print(elements)
38
39 # write mapping for features to keep while keeping only elements
40 with open(in_mapping_fp, 'r') as in_mapping_f:
41 with open(out_mapping_fp, 'w') as out_mapping_f:
42 for line in in_mapping_f.readlines():
43 l_split = line.split("\t")
44 feat = l_split[0]
45 if feat in features:
46 to_write = [feat]
47 for e in l_split[1:]:
48 if e in elements:
49 to_write.append(e)
50 out_mapping_f.write("%s\n" % '\t'.join(to_write))