-
Notifications
You must be signed in to change notification settings - Fork 1
Expand file tree
/
Copy pathparser_fasta.py
More file actions
124 lines (97 loc) · 3.89 KB
/
parser_fasta.py
File metadata and controls
124 lines (97 loc) · 3.89 KB
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
# -------------------------------------------------------------------------
# Copyright (C) 2005-2013 Martin Strohalm <www.mmass.org>
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3 of the License, or
# (at your option) any later version.
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
# Complete text of GNU GPL can be found in the file LICENSE.TXT in the
# main directory of the program.
# -------------------------------------------------------------------------
# load libs
import re
import os.path
# load stopper
from mod_stopper import CHECK_FORCE_QUIT
# load objects
import obj_sequence
# compile basic patterns
spPattern = re.compile('^(sp\|[A-Z][A-Z0-9]+)\|(.*)')
giPattern = re.compile('^(gi\|[0-9]+[\.0-9]*)\|(.*)')
gbPattern = re.compile('^(gb\|[A-Z]{3}[0-9]{5}[\.0-9]*)\|(.*)')
refPattern = re.compile('^(ref\|[A-Z]{2}_[0-9]+[\.0-9]*)\|(.*)')
# PARSE FASTA SEQUENCE FILE
# -------------------------
class parseFASTA():
"""Parse data from FASTA."""
def __init__(self, path):
self.path = path
# check path
if not os.path.exists(path):
raise IOError, 'File not found! --> ' + self.path
# ----
def sequences(self):
"""Get sequences from document."""
# open document
try:
document = file(self.path)
rawData = document.readlines()
document.close()
except IOError:
return False
# read data
reading = False
data = []
for line in rawData:
line = line.strip()
# discard comments and empty lines
if not line or line[0] == ';':
continue
# new sequence started
if line[0] == '>':
# store previous sequence
if reading:
try:
sequence = obj_sequence.sequence(chain, title=title, accession=accession)
data.append(sequence)
except:
pass
# start new sequence
title = line[1:]
accession = ''
chain = ''
reading = True
# get accession
if spPattern.match(title):
match = spPattern.match(title)
accession = match.group(1)
title = match.group(2)
elif giPattern.match(title):
match = giPattern.match(title)
accession = match.group(1)
title = match.group(2)
elif gbPattern.match(title):
match = gbPattern.match(title)
accession = match.group(1)
title = match.group(2)
elif refPattern.match(title):
match = refPattern.match(title)
accession = match.group(1)
title = match.group(2)
# get sequence chain
elif reading:
for char in ('\t','\n','\r','\f','\v',' ', '*'):
line = line.replace(char, '')
chain += line.upper()
# store last sequence
if reading:
try:
sequence = obj_sequence.sequence(chain, title=title, accession=accession)
data.append(sequence)
except:
pass
return data
# ----