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
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
|
#!/usr/bin/env python
"""Provides Tests for BpseqParser and related functions.
"""
from cogent.util.unit_test import TestCase, main
from cogent.core.info import Info
from cogent.struct.knots import inc_order
from cogent.parse.bpseq import BpseqParseError, construct_sequence,\
parse_header, parse_residues, MinimalBpseqParser, BpseqParser,\
bpseq_specify_output
__author__ = "Sandra Smit"
__copyright__ = "Copyright 2007-2012, The Cogent Project"
__credits__ = ["Sandra Smit", "Rob Knight"]
__license__ = "GPL"
__version__ = "1.5.3"
__maintainer__ = "Sandra Smit"
__email__ = "sandra.smit@colorado.edu"
__status__ = "Production"
class BpseqParserTests(TestCase):
"""Provides tests for BpseqParser and related functions"""
def test_parse_header(self):
"""parse_header: should work on standard header"""
h1 = ['Filename: d.16.b.E.coli.bpseq','Organism: Escherichia coli',\
'Accession Number: J01695', 'Citation and related information'+\
' available at http://www.rna.icmb.utexas.edu']
self.assertEqual(parse_header(h1),{'Filename':'d.16.b.E.coli.bpseq',\
'Accession Number': 'J01695', 'Organism': 'Escherichia coli',\
'Refs': {},'Citation':'http://www.rna.icmb.utexas.edu'})
assert isinstance(parse_header(h1), Info)
# lines without ':' are skipped
h2 = ['Filename: d.16.b.E.coli.bpseq','Organism: Escherichia coli',\
'Accession Number: J01695', 'Remark this is an interesting seq']
exp = {'Filename':'d.16.b.E.coli.bpseq', 'Refs': {},\
'Organism': 'Escherichia coli', 'Accession Number':'J01695'}
self.assertEqual(parse_header(h2),exp)
def test_construct_sequence(self):
"""construct_sequence: should return correct sequence or raise error
"""
d = {0:'A',1:'C',2:'G',3:'U'}
self.assertEqual(construct_sequence(d),'ACGU')
# doesn't check residue identity
d = {0:'A',1:'-',2:'R',3:'U'}
self.assertEqual(construct_sequence(d),'A-RU')
# error when sequence isn't continuous
d = {0:'A',1:'C',2:'G',5:'U'}
self.assertRaises(BpseqParseError, construct_sequence, d)
# error when first index is not zero
d = {1:'C',2:'G',3:'U',4:'A'}
self.assertRaises(BpseqParseError, construct_sequence, d)
def test_parse_residues(self):
"""parse_residues: should work on valid data
"""
lines = RES_LINES.split('\n')
exp_seq = 'UGGUAAUACGUUGCGAAGCC'
exp_pairs = [(2,8),(3,7),(4,11),(5,10),(6,9),(12,18),(13,17)]
self.assertEqual(parse_residues(lines, num_base=1,\
unpaired_symbol='0'), (exp_seq, exp_pairs))
def test_parse_residues_errors(self):
"""parse_residues: should raise BpseqParseErrors in several cases
"""
not_all_lines = RES_LINES_NOT_ALL.split('\n')
wrong_lines = RES_LINES_WRONG.split('\n')
conflict_lines = RES_LINES_CONFLICT.split('\n')
bp_conflict = RES_LINES_BP_CONFLICT.split('\n')
self.assertRaises(BpseqParseError, parse_residues, not_all_lines,\
num_base=1, unpaired_symbol='0')
self.assertRaises(BpseqParseError, parse_residues, wrong_lines,\
num_base=1, unpaired_symbol='0')
self.assertRaises(BpseqParseError, parse_residues, conflict_lines,\
num_base=1, unpaired_symbol='0')
self.assertRaises(BpseqParseError, parse_residues, bp_conflict,\
num_base=1, unpaired_symbol='0')
def test_parse_residues_diff_base(self):
"""parse_residues: should work with diff base and unpaired_symbol"""
lines = RES_LINES_DIFF_BASE.split('\n')
exp_seq = 'CAGACU'
exp_pairs = [(1,5),(2,4)]
obs = parse_residues(lines, num_base=3, unpaired_symbol='xxx')
self.assertEqual(obs, (exp_seq, exp_pairs))
def test_MinimalBpseqParser(self):
"""MinimalBpseqParser: should separate lines correctly"""
lines = ['Accesion: J01234', 'LABEL : label', '1 U 4', '2 A 10', 'xx',\
'A B C D E']
exp = {'HEADER': ['Accesion: J01234', 'LABEL : label'],\
'SEQ_STRUCT': ['1 U 4', '2 A 10']}
self.assertEqual(MinimalBpseqParser(lines), exp)
def test_BpseqParser(self):
"""BpseqParser: should work on valid data, returning Vienna or Pairs
"""
lines = RES_LINES_W_HEADER.split('\n')
exp_seq = 'UGGUAAUACGUUGCGAAGCC'
exp_pairs = [(2,8),(3,7),(4,11),(5,10),(6,9),(12,18),(13,17)]
self.assertEqual(BpseqParser(lines),(exp_seq, exp_pairs))
self.assertEqual(BpseqParser(lines)[0].Info,\
{'Filename':'d.16.b.E.coli.bpseq',\
'Accession Number': 'J01695', 'Organism': 'Escherichia coli',\
'Refs': {},'Citation':'http://www.rna.icmb.utexas.edu'})
# should work with different base
lines = RES_LINES_DIFF_BASE.split('\n')
exp_seq = 'CAGACU'
exp_pairs = [(1,5),(2,4)]
obs_seq, obs_pairs = BpseqParser(lines, num_base=3,\
unpaired_symbol='xxx')
self.assertEqual(obs_seq, exp_seq)
self.assertEqual(obs_seq.Info, {'Refs':{}})
self.assertEqual(obs_pairs, exp_pairs)
def test_BpseqParser_errors(self):
"""BpseqParser: should skip lines in unknown format"""
exp_seq = 'UGGUAAUACGUUGCGAAGCC'
exp_vienna_m = '....(((..)))((...)).'
exp_pairs = [(2,8),(3,7),(4,11),(5,10),(6,9),(12,18),(13,17)]
#skips lines in unknown format
lines = RES_LINES_UNKNOWN.split('\n')
obs_seq, obs_pairs = BpseqParser(lines)
self.assertEqual(obs_seq, exp_seq)
self.assertEqual(obs_pairs, exp_pairs)
self.assertEqual(obs_seq.Info,\
{'Filename':'d.16.b.E.coli.bpseq',\
'Accession Number': 'J01695', 'Organism': 'Escherichia coli',\
'Refs': {},'Citation':'http://www.rna.icmb.utexas.edu'})
class ConvenienceFunctionTests(TestCase):
"""Tests for convenience functions"""
def test_bpseq_specify_output(self):
"""bpseq_specify_output: different return values"""
f = bpseq_specify_output
lines = RES_LINES_W_HEADER.split('\n')
exp_seq = 'UGGUAAUACGUUGCGAAGCC'
exp_pairs = [(2,8),(3,7),(4,11),(5,10),(6,9),(12,18),(13,17)]
exp_pairs_majority = [(4,11),(5,10),(6,9),(12,18),(13,17)]
exp_pairs_first = [(2,8),(3,7),(12,18),(13,17)]
exp_vienna_majority = '....(((..)))((...)).'
self.assertEqual(f(lines),(exp_seq, exp_pairs))
self.assertEqual(f(lines, remove_pseudo=True),\
(exp_seq, exp_pairs_majority))
self.assertEqual(f(lines, remove_pseudo=True, pseudoknot_function=inc_order),\
(exp_seq, exp_pairs_first))
self.assertEqual(f(lines, return_vienna=True),\
(exp_seq, exp_vienna_majority))
RES_LINES=\
"""1 U 0
2 G 0
3 G 9
4 U 8
5 A 12
6 A 11
7 U 10
8 A 4
9 C 3
10 G 7
11 U 6
12 U 5
13 G 19
14 C 18
15 G 0
16 A 0
17 A 0
18 G 14
19 C 13
20 C 0"""
RES_LINES_NOT_ALL=\
"""1 U 0
2 G 0
3 G 0
6 A 0"""
RES_LINES_WRONG=\
"""1 U0
2 G 0
3 G 0
6 A 0"""
RES_LINES_CONFLICT=\
"""1 U 4
2 G 3
3 G 2
4 A 1
4 A 0"""
RES_LINES_BP_CONFLICT=\
"""1 U 0
2 G 4
3 G 4
4 C 2
5 A 0"""
RES_LINES_DIFF_BASE=\
"""3 C xxx
4 A 8
5 G 7
6 A xxx
7 C 5
8 U 4"""
RES_LINES_W_HEADER=\
"""Filename: d.16.b.E.coli.bpseq
Organism: Escherichia coli
Accession Number: J01695
Citation and related information available at http://www.rna.icmb.utexas.edu
1 U 0
2 G 0
3 G 9
4 U 8
5 A 12
6 A 11
7 U 10
8 A 4
9 C 3
10 G 7
11 U 6
12 U 5
13 G 19
14 C 18
15 G 0
16 A 0
17 A 0
18 G 14
19 C 13
20 C 0"""
RES_LINES_UNKNOWN=\
"""Filename: d.16.b.E.coli.bpseq
Organism: Escherichia coli
Accession Number: J01695
Citation and related information available at http://www.rna.icmb.utexas.edu
1 U 0
2 G 0
3 G 9
UNKNOWN LINE
4 U 8
5 A 12
6 A 11
7 U 10
8 A 4
9 C 3
10 G 7
11 U 6
12 U 5
13 G 19
14 C 18
15 G 0
16 A 0
17 A 0
18 G 14
19 C 13
20 C 0"""
#run if called from command-line
if __name__ == "__main__":
main()
|
