File: _transformseq.py

package info (click to toggle)
python-weblogo 3.8.0-2
  • links: PTS, VCS
  • area: main
  • in suites: sid, trixie
  • size: 3,700 kB
  • sloc: xml: 14,455; python: 10,384; sh: 140; makefile: 58
file content (180 lines) | stat: -rwxr-xr-x 4,599 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
#!/usr/bin/env python

#  Copyright (c) 2006, The Regents of the University of California, through
#  Lawrence Berkeley National Laboratory (subject to receipt of any required
#  approvals from the U.S. Dept. of Energy).  All rights reserved.

#  This software is distributed under the new BSD Open Source License.
#  <http://www.opensource.org/licenses/bsd-license.html>
#  Please see the LICENSE.txt file that should have been included
#  as part of this package.


""" A tool for converting multiple sequence alignments from
one format to another.
"""

import sys
from optparse import OptionGroup

from weblogo import seq_io
from weblogo.seq import Seq, SeqList, nucleic_alphabet
from weblogo.transform import mask_low_complexity
from weblogo.utils.deoptparse import DeOptionParser

__version__ = "1.0.0"
description = """ A tool for converting multiple sequence alignments from
one format to another. """


def main() -> None:
    # ------ Parse Command line ------
    parser = _build_option_parser()
    (opts, args) = parser.parse_args(sys.argv[1:])
    if args:
        parser.error("Unparsable arguments: %s " % args)

    seqs = opts.reader.read(opts.fin)

    if opts.trans_seg:
        seqs = SeqList([mask_low_complexity(s) for s in seqs])

    if opts.subsample is not None:
        from random import random

        frac = opts.subsample
        ss = []
        for s in seqs:
            if random() < frac:
                ss.append(s)
        seqs = SeqList(ss)

    if opts.reverse:
        seqs = SeqList([s.reverse() for s in seqs])

    if opts.complement:
        seqs = SeqList([Seq(s, alphabet=nucleic_alphabet) for s in seqs])
        seqs = SeqList([s.complement() for s in seqs])

    opts.writer.write(opts.fout, seqs)


def _build_option_parser() -> DeOptionParser:
    parser = DeOptionParser(
        usage="%prog [options]  < sequence_data.fa > sequence_logo.eps",
        description=description,
        version=__version__,
        add_verbose_options=False,
    )

    io_grp = OptionGroup(
        parser,
        "Input/Output Options",
    )
    parser.add_option_group(io_grp)

    io_grp.add_option(
        "-f",
        "--fin",
        dest="fin",
        action="store",
        type="file_in",
        default=sys.stdin,
        help="Sequence input file (default: stdin)",
        metavar="FILENAME",
    )

    io_grp.add_option(
        "",
        "--format-in",
        dest="reader",
        action="store",
        type="dict",
        default=seq_io,
        choices=seq_io.format_names(),
        help="Multiple sequence alignment format: (%s)"
        % ", ".join([f.names[0] for f in seq_io.formats]),  # type: ignore
        metavar="FORMAT",
    )

    io_grp.add_option(
        "-o",
        "--fout",
        dest="fout",
        type="file_out",
        default=sys.stdout,
        help="Output file (default: stdout)",
        metavar="FILENAME",
    )

    trans_grp = OptionGroup(
        parser,
        "Transformations",
    )
    parser.add_option_group(trans_grp)

    trans_grp.add_option(
        "",
        "--seg",
        dest="trans_seg",
        action="store_true",
        default=False,
        help="Mask low complexity regions in protein sequences.",
        metavar="TRUE/FALSE",
    )

    trans_grp.add_option(
        "",
        "--subsample",
        dest="subsample",
        action="store",
        type="float",
        default=None,
        help="Return a random subsample of the sequences.",
        metavar="FRACTION",
    )

    trans_grp.add_option(
        "",
        "--reverse",
        dest="reverse",
        action="store_true",
        default=False,
        help="reverse sequences",
        metavar="TRUE/FALSE",
    )

    trans_grp.add_option(
        "",
        "--complement",
        dest="complement",
        action="store_true",
        default=False,
        help="complement DNA sequences",
        metavar="TRUE/FALSE",
    )

    # Writers
    out_formats = []
    for f in seq_io.formats:
        if hasattr(f, "write"):
            out_formats.append(f)
    out_choices = {}
    for f in out_formats:
        out_choices[f.names[0]] = f  # type: ignore
    out_names = [f.names[0] for f in out_formats]  # type: ignore

    io_grp.add_option(
        "-F",
        "--format-out",
        dest="writer",
        action="store",
        type="dict",
        default=seq_io.fasta_io,
        choices=out_choices,
        help="Multiple sequence alignment output format: (%s) (Default: fasta)"
        % ", ".join(out_names),
        metavar="FORMAT",
    )

    return parser