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
|
# Copyright 2009-2013 by Peter Cock. All rights reserved.
# Parts copyright 1999 by Jeffrey Chang. 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.
from __future__ import print_function
import unittest
from Bio._py3k import StringIO
from Bio import SeqIO
from Bio.SeqIO.FastaIO import FastaIterator
from Bio.Alphabet import generic_protein, generic_nucleotide, generic_dna
def title_to_ids(title):
"""Function to convert a title into the id, name, and description.
This is just a quick-n-dirty implementation, and is definetely not meant
to handle every FASTA title line case.
"""
# first split the id information from the description
# the first item is the id info block, the rest is the description
all_info = title.split(" ")
id_info = all_info[0]
rest = all_info[1:]
descr = " ".join(rest)
# now extract the ids from the id block
# gi|5690369|gb|AF158246.1|AF158246
id_info_items = id_info.split("|")
if len(id_info_items) >=4:
assert id_info_items[2] in ["gb", "emb", "dbj", "pdb"], title
id = id_info_items[3] # the id with version info
name = id_info_items[4] # the id without version info
else:
#Fallback:
id = id_info_items[0]
name = id_info_items[0]
return id, name, descr
def read_single_with_titles(filename, alphabet):
global title_to_ids
handle = open(filename)
iterator = FastaIterator(handle, alphabet, title_to_ids)
record = next(iterator)
try:
second = next(iterator)
except StopIteration:
second = None
handle.close()
assert record is not None and second is None
return record
def read_title_and_seq(filename):
"""Crude parser that gets the first record from a FASTA file."""
handle = open(filename)
title = handle.readline().rstrip()
assert title.startswith(">")
seq = ""
for line in handle:
if line.startswith(">"):
break
seq += line.strip()
handle.close()
return title[1:], seq
class TitleFunctions(unittest.TestCase):
"""Cunning unit test where methods are added at run time."""
def simple_check(self, filename, alphabet):
"""Basic test for parsing single record FASTA files."""
title, seq = read_title_and_seq(filename) # crude parser
#First check using Bio.SeqIO.FastaIO directly with title function,
record = read_single_with_titles(filename, alphabet)
idn, name, descr = title_to_ids(title)
self.assertEqual(record.id, idn)
self.assertEqual(record.name, name)
self.assertEqual(record.description, descr)
self.assertEqual(str(record.seq), seq)
self.assertEqual(record.seq.alphabet, alphabet)
#Now check using Bio.SeqIO (default settings)
record = SeqIO.read(filename, "fasta", alphabet)
self.assertEqual(record.id, title.split()[0])
self.assertEqual(record.name, title.split()[0])
self.assertEqual(record.description, title)
self.assertEqual(str(record.seq), seq)
self.assertEqual(record.seq.alphabet, alphabet)
#Uncomment this for testing the methods are calling the right files:
#print("{%s done}" % filename)
def multi_check(self, filename, alphabet):
"""Basic test for parsing multi-record FASTA files."""
with open(filename) as handle:
re_titled = list(FastaIterator(handle, alphabet, title_to_ids))
default = list(SeqIO.parse(filename, "fasta", alphabet))
self.assertEqual(len(re_titled), len(default))
for old, new in zip(default, re_titled):
idn, name, descr = title_to_ids(old.description)
self.assertEqual(new.id, idn)
self.assertEqual(new.name, name)
self.assertEqual(new.description, descr)
self.assertEqual(str(new.seq), str(old.seq))
self.assertEqual(new.seq.alphabet, old.seq.alphabet)
#Uncomment this for testing the methods are calling the right files:
#print("{%s done}" % filename)
def test_no_name(self):
"""Test FASTA record with no identifier."""
handle = StringIO(">\nACGT")
record = SeqIO.read(handle, "fasta")
handle.close()
self.assertEqual(str(record.seq), "ACGT")
self.assertEqual("", record.id)
self.assertEqual("", record.name)
self.assertEqual("", record.description)
single_nucleic_files = ['Fasta/lupine.nu', 'Fasta/elderberry.nu',
'Fasta/phlox.nu', 'Fasta/centaurea.nu',
'Fasta/wisteria.nu', 'Fasta/sweetpea.nu',
'Fasta/lavender.nu', 'Fasta/f001']
multi_dna_files = ['Quality/example.fasta']
single_amino_files = ['Fasta/aster.pro', 'Fasta/rosemary.pro',
'Fasta/rose.pro', 'Fasta/loveliesbleeding.pro']
multi_amino_files = ['Fasta/f002', 'Fasta/fa01']
for filename in single_nucleic_files:
name = filename.split(".")[0]
def funct(fn):
f = lambda x : x.simple_check(fn, generic_nucleotide)
f.__doc__ = "Checking nucleotide file %s" % fn
return f
setattr(TitleFunctions, "test_nuc_%s"%name, funct(filename))
del funct
for filename in multi_dna_files:
name = filename.split(".")[0]
def funct(fn):
f = lambda x : x.multi_check(fn, generic_dna)
f.__doc__ = "Checking multi DNA file %s" % fn
return f
setattr(TitleFunctions, "test_mutli_dna_%s"%name, funct(filename))
del funct
for filename in single_amino_files:
name = filename.split(".")[0]
def funct(fn):
f = lambda x : x.simple_check(fn, generic_nucleotide)
f.__doc__ = "Checking protein file %s" % fn
return f
setattr(TitleFunctions, "test_pro_%s"%name, funct(filename))
del funct
for filename in multi_amino_files:
name = filename.split(".")[0]
def funct(fn):
f = lambda x : x.multi_check(fn, generic_dna)
f.__doc__ = "Checking multi protein file %s" % fn
return f
setattr(TitleFunctions, "test_mutli_pro_%s"%name, funct(filename))
del funct
if __name__ == "__main__":
runner = unittest.TextTestRunner(verbosity = 2)
unittest.main(testRunner=runner)
|
