annotate scripts/ReMatCh/utils/convert_Ns_to_gaps.py @ 6:20ff3dca457f draft default tip

planemo upload commit 6857c749c21f580c828aba3543e294b69d32b662
author iss
date Mon, 23 Oct 2023 11:45:36 +0000
parents c6bab5103a14
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
1 #!/usr/bin/env python3
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
2
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
3 # -*- coding: utf-8 -*-
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
4
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
5 """
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
6 convert_Ns_to_gaps.py - Convert the Ns into gaps
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
7 <https://github.com/B-UMMI/ReMatCh/>
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
8
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
9 Copyright (C) 2018 Miguel Machado <mpmachado@medicina.ulisboa.pt>
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
10
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
11 Last modified: October 15, 2018
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
12
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
13 This program is free software: you can redistribute it and/or modify
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
14 it under the terms of the GNU General Public License as published by
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
15 the Free Software Foundation, either version 3 of the License, or
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
16 (at your option) any later version.
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
17
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
18 This program is distributed in the hope that it will be useful,
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
19 but WITHOUT ANY WARRANTY; without even the implied warranty of
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
20 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
21 GNU General Public License for more details.
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
22
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
23 You should have received a copy of the GNU General Public License
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
24 along with this program. If not, see <http://www.gnu.org/licenses/>.
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
25 """
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
26
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
27 import os
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
28 import argparse
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
29
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
30
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
31 version = '0.2'
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
32
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
33
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
34 def conversion(infile, outfile):
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
35 last_printed = 0
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
36 counter = 1
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
37 with open(infile, 'rtU') as reader:
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
38 with open(outfile, 'wt') as writer:
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
39 for line in reader:
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
40 line = line.rstrip('\r\n')
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
41 if line.startswith('>'):
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
42 writer.write(line + '\n')
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
43 if counter % 10 == 0:
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
44 print('\n' + str(counter) + ' sequences already processed')
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
45 last_printed = counter
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
46 counter += 1
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
47 else:
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
48 if len(line) > 0:
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
49 line = line.replace('N', '-')
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
50 writer.write(line + '\n')
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
51 if last_printed < counter:
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
52 print('\n' + str(counter - 1) + ' sequences already processed')
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
53
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
54
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
55 def convert_n_2_gaps(args):
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
56 outdir = os.path.dirname(os.path.abspath(args.outfile))
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
57 if not os.path.isdir(outdir):
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
58 os.makedirs(outdir)
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
59
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
60 outfile = os.path.abspath(args.outfile)
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
61
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
62 infile = os.path.abspath(args.infile.name)
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
63
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
64 conversion(infile, outfile)
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
65
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
66
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
67 def main():
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
68 parser = argparse.ArgumentParser(prog='convert_Ns_to_gaps.py', description='Convert the Ns into gaps',
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
69 formatter_class=argparse.ArgumentDefaultsHelpFormatter)
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
70 parser.add_argument('--version', help='Version information', action='version', version=str('%(prog)s v' + version))
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
71
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
72 parser_required = parser.add_argument_group('Required options')
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
73 parser_required.add_argument('-i', '--infile', type=argparse.FileType('r'), metavar='/path/to/input/file.fasta',
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
74 help='Path to the fasta file', required=True)
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
75 parser_required.add_argument('-o', '--outfile', type=str, metavar='/path/to/converted/output/file.fasta',
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
76 help='Converted output fasta file', required=True,
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
77 default='converted_Ns_to_gaps.fasta')
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
78
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
79 args = parser.parse_args()
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
80
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
81 convert_n_2_gaps(args)
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
82
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
83
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
84 if __name__ == "__main__":
c6bab5103a14 "planemo upload commit 6abf3e299d82d07e6c3cf8642bdea80e96df64c3-dirty"
iss
parents:
diff changeset
85 main()