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
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
|
# Copyright 2006-2015 by Peter Cock. All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
#
# This module is for reading and writing FASTA format files as SeqRecord
# objects. The code is partly inspired by earlier Biopython modules,
# Bio.Fasta.* and the now deprecated Bio.SeqIO.FASTA
"""Bio.SeqIO support for the "fasta" (aka FastA or Pearson) file format.
You are expected to use this module via the Bio.SeqIO functions."""
from __future__ import print_function
from Bio.Alphabet import single_letter_alphabet
from Bio.Seq import Seq
from Bio.SeqRecord import SeqRecord
from Bio.SeqIO.Interfaces import SequentialSequenceWriter
def SimpleFastaParser(handle):
"""Generator function to iterate over Fasta records (as string tuples).
For each record a tuple of two strings is returned, the FASTA title
line (without the leading '>' character), and the sequence (with any
whitespace removed). The title line is not divided up into an
identifier (the first word) and comment or description.
>>> with open("Fasta/dups.fasta") as handle:
... for values in SimpleFastaParser(handle):
... print(values)
...
('alpha', 'ACGTA')
('beta', 'CGTC')
('gamma', 'CCGCC')
('alpha (again - this is a duplicate entry to test the indexing code)', 'ACGTA')
('delta', 'CGCGC')
"""
# Skip any text before the first record (e.g. blank lines, comments)
while True:
line = handle.readline()
if line == "":
return # Premature end of file, or just empty?
if line[0] == ">":
break
while True:
if line[0] != ">":
raise ValueError(
"Records in Fasta files should start with '>' character")
title = line[1:].rstrip()
lines = []
line = handle.readline()
while True:
if not line:
break
if line[0] == ">":
break
lines.append(line.rstrip())
line = handle.readline()
# Remove trailing whitespace, and any internal spaces
# (and any embedded \r which are possible in mangled files
# when not opened in universal read lines mode)
yield title, "".join(lines).replace(" ", "").replace("\r", "")
if not line:
return # StopIteration
assert False, "Should not reach this line"
def FastaIterator(handle, alphabet=single_letter_alphabet, title2ids=None):
"""Generator function to iterate over Fasta records (as SeqRecord objects).
Arguments:
- handle - input file
- alphabet - optional alphabet
- title2ids - A function that, when given the title of the FASTA
file (without the beginning >), will return the id, name and
description (in that order) for the record as a tuple of strings.
If this is not given, then the entire title line will be used
as the description, and the first word as the id and name.
By default this will act like calling Bio.SeqIO.parse(handle, "fasta")
with no custom handling of the title lines:
>>> with open("Fasta/dups.fasta") as handle:
... for record in FastaIterator(handle):
... print(record.id)
...
alpha
beta
gamma
alpha
delta
However, you can supply a title2ids function to alter this:
>>> def take_upper(title):
... return title.split(None, 1)[0].upper(), "", title
>>> with open("Fasta/dups.fasta") as handle:
... for record in FastaIterator(handle, title2ids=take_upper):
... print(record.id)
...
ALPHA
BETA
GAMMA
ALPHA
DELTA
"""
if title2ids:
for title, sequence in SimpleFastaParser(handle):
id, name, descr = title2ids(title)
yield SeqRecord(Seq(sequence, alphabet),
id=id, name=name, description=descr)
else:
for title, sequence in SimpleFastaParser(handle):
try:
first_word = title.split(None, 1)[0]
except IndexError:
assert not title, repr(title)
# Should we use SeqRecord default for no ID?
first_word = ""
yield SeqRecord(Seq(sequence, alphabet),
id=first_word, name=first_word, description=title)
class FastaWriter(SequentialSequenceWriter):
"""Class to write Fasta format files."""
def __init__(self, handle, wrap=60, record2title=None):
"""Create a Fasta writer.
Arguments:
- handle - Handle to an output file, e.g. as returned
by open(filename, "w")
- wrap - Optional line length used to wrap sequence lines.
Defaults to wrapping the sequence at 60 characters
Use zero (or None) for no wrapping, giving a single
long line for the sequence.
- record2title - Optional function to return the text to be
used for the title line of each record. By default
a combination of the record.id and record.description
is used. If the record.description starts with the
record.id, then just the record.description is used.
You can either use::
handle = open(filename, "w")
writer = FastaWriter(handle)
writer.write_file(myRecords)
handle.close()
Or, follow the sequential file writer system, for example::
handle = open(filename, "w")
writer = FastaWriter(handle)
writer.write_header() # does nothing for Fasta files
...
Multiple writer.write_record() and/or writer.write_records() calls
...
writer.write_footer() # does nothing for Fasta files
handle.close()
"""
SequentialSequenceWriter.__init__(self, handle)
self.wrap = None
if wrap:
if wrap < 1:
raise ValueError
self.wrap = wrap
self.record2title = record2title
def write_record(self, record):
"""Write a single Fasta record to the file."""
assert self._header_written
assert not self._footer_written
self._record_written = True
if self.record2title:
title = self.clean(self.record2title(record))
else:
id = self.clean(record.id)
description = self.clean(record.description)
if description and description.split(None, 1)[0] == id:
# The description includes the id at the start
title = description
elif description:
title = "%s %s" % (id, description)
else:
title = id
assert "\n" not in title
assert "\r" not in title
self.handle.write(">%s\n" % title)
data = self._get_seq_string(record) # Catches sequence being None
assert "\n" not in data
assert "\r" not in data
if self.wrap:
for i in range(0, len(data), self.wrap):
self.handle.write(data[i:i + self.wrap] + "\n")
else:
self.handle.write(data + "\n")
if __name__ == "__main__":
from Bio._utils import run_doctest
run_doctest(verbose=0)
|
