-
Notifications
You must be signed in to change notification settings - Fork 268
/
test_grammared_sequence.py
688 lines (544 loc) · 26.4 KB
/
test_grammared_sequence.py
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
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
# ----------------------------------------------------------------------------
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file LICENSE.txt, distributed with this software.
# ----------------------------------------------------------------------------
from unittest import TestCase, main
import numpy as np
import numpy.testing as npt
import pandas as pd
from skbio.sequence import GrammaredSequence
from skbio.util import classproperty
from skbio.util import assert_data_frame_almost_equal
from skbio.metadata import IntervalMetadata
class ExampleGrammaredSequence(GrammaredSequence):
@classproperty
def degenerate_map(cls):
return {"X": set("AB"), "Y": set("BC"), "Z": set("AC")}
@classproperty
def definite_chars(cls):
return set("ABC")
@classproperty
def default_gap_char(cls):
return '-'
@classproperty
def gap_chars(cls):
return set('-.')
class ExampleMotifsTester(ExampleGrammaredSequence):
@property
def _motifs(self):
# These aren't really motifs, just a way to excercise the code paths
return {
"name1": lambda x, _, __: str(x),
"name2": lambda x, _, __: len(x)
}
class TestGrammaredSequence(TestCase):
def test_default_gap_must_be_in_gap_chars(self):
with self.assertRaisesRegex(
TypeError,
r"default_gap_char must be in gap_chars for class "
"GrammaredSequenceInvalidDefaultGap"):
class GrammaredSequenceInvalidDefaultGap(ExampleGrammaredSequence):
@classproperty
def default_gap_char(cls):
return '*'
def test_degenerates_must_expand_to_valid_definites(self):
with self.assertRaisesRegex(
TypeError,
r"degenerate_map must expand only to characters included in "
"definite_chars for class "
"GrammaredSequenceInvalidDefaultGap"):
class GrammaredSequenceInvalidDefaultGap(ExampleGrammaredSequence):
@classproperty
def degenerate_map(cls):
return {"X": set("B")}
@classproperty
def definite_chars(cls):
return set("A")
def test_gap_chars_and_degenerates_share(self):
with self.assertRaisesRegex(
TypeError,
r"gap_chars and degenerate_chars must not share any characters"
" for class GrammaredSequenceGapInDegenerateMap"):
class GrammaredSequenceGapInDegenerateMap(
ExampleGrammaredSequence):
@classproperty
def degenerate_map(cls):
return {"X": set("AB")}
@classproperty
def definite_chars(cls):
return set("ABC")
@classproperty
def gap_chars(cls):
return set(".-X")
def test_gap_chars_and_definites_share(self):
with self.assertRaisesRegex(
TypeError,
(r"gap_chars and definite_chars must not share any characters "
"for class GrammaredSequenceGapInDefiniteMap")):
class GrammaredSequenceGapInDefiniteMap(
ExampleGrammaredSequence):
@classproperty
def degenerate_map(cls):
return {"X": set("AB")}
@classproperty
def definite_chars(cls):
return set("ABC")
@classproperty
def gap_chars(cls):
return set(".-A")
def test_degenerates_and_definites_share(self):
with self.assertRaisesRegex(
TypeError,
(r"degenerate_chars and definite_chars must not share any "
"characters for class GrammaredSequenceInvalid")):
class GrammaredSequenceInvalid(ExampleGrammaredSequence):
@classproperty
def degenerate_map(cls):
return {"X": set("AB")}
@classproperty
def definite_chars(cls):
return set("ABCX")
def test_instantiation_with_no_implementation(self):
class GrammaredSequenceSubclassNoImplementation(GrammaredSequence):
pass
with self.assertRaises(TypeError) as cm:
GrammaredSequenceSubclassNoImplementation()
self.assertIn("abstract class", str(cm.exception))
self.assertIn("definite_chars", str(cm.exception))
self.assertIn("degenerate_map", str(cm.exception))
def test_init_default_parameters(self):
seq = ExampleGrammaredSequence('.-ABCXYZ')
npt.assert_equal(seq.values, np.array('.-ABCXYZ', dtype='c'))
self.assertEqual(seq.metadata, {})
assert_data_frame_almost_equal(seq.positional_metadata,
pd.DataFrame(index=range(8)))
self.assertEqual(seq.interval_metadata,
IntervalMetadata(8))
def test_init_nondefault_parameters(self):
im = IntervalMetadata(8)
im.add([(1, 8)], metadata={'gene': 'p53'})
seq = ExampleGrammaredSequence(
'.-ABCXYZ',
metadata={'id': 'foo'},
positional_metadata={'quality': range(8)},
interval_metadata=im)
npt.assert_equal(seq.values, np.array('.-ABCXYZ', dtype='c'))
self.assertEqual(seq.metadata, {'id': 'foo'})
assert_data_frame_almost_equal(seq.positional_metadata,
pd.DataFrame({'quality': range(8)}))
self.assertEqual(seq.interval_metadata, im)
def test_init_valid_empty_sequence(self):
# just make sure we can instantiate an empty sequence regardless of
# `validate` and `lowercase` parameters. more extensive tests
# are performed in Sequence base class unit tests
for validate in (True, False):
for lowercase in (True, False):
seq = ExampleGrammaredSequence(
'', validate=validate, lowercase=lowercase)
self.assertEqual(seq, ExampleGrammaredSequence(''))
def test_init_valid_single_character_sequence(self):
for validate in (True, False):
for lowercase in (True, False):
seq = ExampleGrammaredSequence(
'C', validate=validate, lowercase=lowercase)
self.assertEqual(seq, ExampleGrammaredSequence('C'))
def test_init_valid_multiple_character_sequence(self):
for validate in (True, False):
for lowercase in (True, False):
seq = ExampleGrammaredSequence(
'BAACB.XYY-AZ', validate=validate, lowercase=lowercase)
self.assertEqual(seq, ExampleGrammaredSequence('BAACB.XYY-AZ'))
def test_init_validate_parameter_single_character(self):
seq = 'w'
with self.assertRaisesRegex(ValueError, r"character.*'w'"):
ExampleGrammaredSequence(seq)
# test that we can instantiate an invalid sequence. we don't guarantee
# anything working beyond instantiation
ExampleGrammaredSequence(seq, validate=False)
def test_init_validate_parameter_multiple_characters(self):
# mix of valid and invalid characters with repeats and lowercased
# alphabet characters
seq = 'CBCBBbawCbbwBXYZ-.x'
with self.assertRaisesRegex(ValueError, r"\['a', 'b', 'w', 'x'\]"):
ExampleGrammaredSequence(seq)
ExampleGrammaredSequence(seq, validate=False)
def test_init_lowercase_all_lowercase(self):
s = 'cbcbbbazcbbzbxyz-.x'
with self.assertRaisesRegex(ValueError,
r"\['a', 'b', 'c', 'x', 'y', 'z'\]"):
ExampleGrammaredSequence(s)
seq = ExampleGrammaredSequence(s, lowercase=True)
self.assertEqual(seq, ExampleGrammaredSequence('CBCBBBAZCBBZBXYZ-.X'))
def test_init_lowercase_mixed_case(self):
s = 'CBCBBbazCbbzBXYZ-.x'
with self.assertRaisesRegex(ValueError, r"\['a', 'b', 'x', 'z'\]"):
ExampleGrammaredSequence(s)
seq = ExampleGrammaredSequence(s, lowercase=True)
self.assertEqual(seq, ExampleGrammaredSequence('CBCBBBAZCBBZBXYZ-.X'))
def test_init_lowercase_no_validation(self):
s = 'car'
with self.assertRaisesRegex(ValueError, r"\['a', 'c', 'r'\]"):
ExampleGrammaredSequence(s)
with self.assertRaisesRegex(ValueError, r"character.*'R'"):
ExampleGrammaredSequence(s, lowercase=True)
ExampleGrammaredSequence(s, lowercase=True, validate=False)
def test_init_lowercase_byte_ownership(self):
bytes = np.array([97, 98, 97], dtype=np.uint8)
with self.assertRaisesRegex(ValueError, r"\['a', 'b'\]"):
ExampleGrammaredSequence(bytes)
seq = ExampleGrammaredSequence(bytes, lowercase=True)
self.assertEqual(seq, ExampleGrammaredSequence('ABA'))
# should not share the same memory
self.assertIsNot(seq._bytes, bytes)
# we should have copied `bytes` before modifying in place to convert to
# upper. make sure `bytes` hasn't been mutated
npt.assert_equal(bytes, np.array([97, 98, 97], dtype=np.uint8))
def test_init_lowercase_invalid_keys(self):
for invalid_key in ((), [], 2):
invalid_type = type(invalid_key)
with self.assertRaisesRegex(TypeError,
r"lowercase keyword argument expected "
"a bool or string, but got %s" %
invalid_type):
ExampleGrammaredSequence('ACGTacgt', lowercase=invalid_key)
def test_degenerate_chars(self):
expected = set("XYZ")
self.assertIs(type(ExampleGrammaredSequence.degenerate_chars), set)
self.assertEqual(ExampleGrammaredSequence.degenerate_chars, expected)
ExampleGrammaredSequence.degenerate_chars.add("W")
self.assertEqual(ExampleGrammaredSequence.degenerate_chars, expected)
self.assertEqual(ExampleGrammaredSequence('').degenerate_chars,
expected)
with self.assertRaises(AttributeError):
ExampleGrammaredSequence('').degenerate_chars = set("BAR")
# TODO: duplicate of test_definite_chars, remove when nondegenerate_chars,
# is removed
def test_nondegenerate_chars(self):
expected = set("ABC")
self.assertEqual(ExampleGrammaredSequence.nondegenerate_chars,
expected)
ExampleGrammaredSequence.degenerate_chars.add("D")
self.assertEqual(ExampleGrammaredSequence.nondegenerate_chars,
expected)
self.assertEqual(ExampleGrammaredSequence('').nondegenerate_chars,
expected)
with self.assertRaises(AttributeError):
ExampleGrammaredSequence('').nondegenerate_chars = set("BAR")
def test_definite_chars(self):
expected = set("ABC")
self.assertEqual(ExampleGrammaredSequence.definite_chars,
expected)
ExampleGrammaredSequence.degenerate_chars.add("D")
self.assertEqual(ExampleGrammaredSequence.definite_chars,
expected)
self.assertEqual(ExampleGrammaredSequence('').definite_chars,
expected)
with self.assertRaises(AttributeError):
ExampleGrammaredSequence('').definite_chars = set("BAR")
def test_gap_chars(self):
expected = set(".-")
self.assertIs(type(ExampleGrammaredSequence.gap_chars), set)
self.assertEqual(ExampleGrammaredSequence.gap_chars, expected)
ExampleGrammaredSequence.gap_chars.add("_")
self.assertEqual(ExampleGrammaredSequence.gap_chars, expected)
self.assertEqual(ExampleGrammaredSequence('').gap_chars, expected)
with self.assertRaises(AttributeError):
ExampleGrammaredSequence('').gap_chars = set("_ =")
def test_default_gap_char(self):
self.assertIs(type(ExampleGrammaredSequence.default_gap_char), str)
self.assertEqual(ExampleGrammaredSequence.default_gap_char, '-')
self.assertEqual(ExampleGrammaredSequence('').default_gap_char, '-')
with self.assertRaises(AttributeError):
ExampleGrammaredSequence('').default_gap_char = '.'
def test_alphabet(self):
expected = set("ABC.-XYZ")
self.assertIs(type(ExampleGrammaredSequence.alphabet), set)
self.assertEqual(ExampleGrammaredSequence.alphabet, expected)
ExampleGrammaredSequence.alphabet.add("DEF")
self.assertEqual(ExampleGrammaredSequence.alphabet, expected)
self.assertEqual(ExampleGrammaredSequence('').alphabet, expected)
with self.assertRaises(AttributeError):
ExampleGrammaredSequence('').alphabet = set("ABCDEFG.-WXYZ")
def test_degenerate_map(self):
expected = {"X": set("AB"), "Y": set("BC"), "Z": set("AC")}
self.assertEqual(ExampleGrammaredSequence.degenerate_map, expected)
ExampleGrammaredSequence.degenerate_map['W'] = set("ABC")
ExampleGrammaredSequence.degenerate_map['X'] = set("CA")
self.assertEqual(ExampleGrammaredSequence.degenerate_map, expected)
self.assertEqual(ExampleGrammaredSequence('').degenerate_map, expected)
with self.assertRaises(AttributeError):
ExampleGrammaredSequence('').degenerate_map = {'W': "ABC"}
def test_gaps(self):
self.assertIs(type(ExampleGrammaredSequence("").gaps()), np.ndarray)
self.assertIs(ExampleGrammaredSequence("").gaps().dtype,
np.dtype('bool'))
npt.assert_equal(ExampleGrammaredSequence("ABCXBZYABC").gaps(),
np.zeros(10).astype(bool))
npt.assert_equal(ExampleGrammaredSequence(".-.-.").gaps(),
np.ones(5).astype(bool))
npt.assert_equal(ExampleGrammaredSequence("A.B-C.X-Y.").gaps(),
np.array([0, 1] * 5, dtype=bool))
npt.assert_equal(ExampleGrammaredSequence("AB.AC.XY-").gaps(),
np.array([0, 0, 1] * 3, dtype=bool))
npt.assert_equal(ExampleGrammaredSequence("A.BC.-").gaps(),
np.array([0, 1, 0, 0, 1, 1], dtype=bool))
def test_has_gaps(self):
self.assertIs(type(ExampleGrammaredSequence("").has_gaps()), bool)
self.assertIs(type(ExampleGrammaredSequence("-").has_gaps()), bool)
self.assertFalse(ExampleGrammaredSequence("").has_gaps())
self.assertFalse(ExampleGrammaredSequence("ABCXYZ").has_gaps())
self.assertTrue(ExampleGrammaredSequence("-").has_gaps())
self.assertTrue(ExampleGrammaredSequence("ABCXYZ-").has_gaps())
def test_degenerates(self):
self.assertIs(type(ExampleGrammaredSequence("").degenerates()),
np.ndarray)
self.assertIs(ExampleGrammaredSequence("").degenerates().dtype,
np.dtype('bool'))
npt.assert_equal(ExampleGrammaredSequence("ABCBC-.AB.").degenerates(),
np.zeros(10).astype(bool))
npt.assert_equal(ExampleGrammaredSequence("ZYZYZ").degenerates(),
np.ones(5).astype(bool))
npt.assert_equal(ExampleGrammaredSequence("AX.Y-ZBXCZ").degenerates(),
np.array([0, 1] * 5, dtype=bool))
npt.assert_equal(ExampleGrammaredSequence("ABXACY.-Z").degenerates(),
np.array([0, 0, 1] * 3, dtype=bool))
npt.assert_equal(ExampleGrammaredSequence("AZBCXY").degenerates(),
np.array([0, 1, 0, 0, 1, 1], dtype=bool))
def test_has_degenerates(self):
self.assertIs(type(ExampleGrammaredSequence("").has_degenerates()),
bool)
self.assertIs(type(ExampleGrammaredSequence("X").has_degenerates()),
bool)
self.assertFalse(ExampleGrammaredSequence("").has_degenerates())
self.assertFalse(ExampleGrammaredSequence("A-.BC").has_degenerates())
self.assertTrue(ExampleGrammaredSequence("Z").has_degenerates())
self.assertTrue(ExampleGrammaredSequence("ABC.XYZ-").has_degenerates())
# TODO: duplicate of test_definites; remove when nondegenerates is removed
def test_nondegenerates(self):
self.assertIs(type(ExampleGrammaredSequence("").nondegenerates()),
np.ndarray)
self.assertIs(ExampleGrammaredSequence("").nondegenerates().dtype,
np.dtype('bool'))
npt.assert_equal(
ExampleGrammaredSequence("XYZYZ-.XY.").nondegenerates(),
np.zeros(10).astype(bool))
npt.assert_equal(ExampleGrammaredSequence("ABABA").nondegenerates(),
np.ones(5).astype(bool))
npt.assert_equal(
ExampleGrammaredSequence("XA.B-AZCXA").nondegenerates(),
np.array([0, 1] * 5, dtype=bool))
npt.assert_equal(
ExampleGrammaredSequence("XXAZZB.-C").nondegenerates(),
np.array([0, 0, 1] * 3, dtype=bool))
npt.assert_equal(ExampleGrammaredSequence("YB.-AC").nondegenerates(),
np.array([0, 1, 0, 0, 1, 1], dtype=bool))
def test_definites(self):
self.assertIs(type(ExampleGrammaredSequence("").definites()),
np.ndarray)
self.assertIs(ExampleGrammaredSequence("").definites().dtype,
np.dtype('bool'))
npt.assert_equal(
ExampleGrammaredSequence("XYZYZ-.XY.").definites(),
np.zeros(10).astype(bool))
npt.assert_equal(ExampleGrammaredSequence("ABABA").definites(),
np.ones(5).astype(bool))
npt.assert_equal(
ExampleGrammaredSequence("XA.B-AZCXA").definites(),
np.array([0, 1] * 5, dtype=bool))
npt.assert_equal(
ExampleGrammaredSequence("XXAZZB.-C").definites(),
np.array([0, 0, 1] * 3, dtype=bool))
npt.assert_equal(ExampleGrammaredSequence("YB.-AC").definites(),
np.array([0, 1, 0, 0, 1, 1], dtype=bool))
# TODO: duplicate of test_has_definites; remove when has_nondegenerates is
# removed.
def test_has_nondegenerates(self):
self.assertIs(type(ExampleGrammaredSequence("").has_nondegenerates()),
bool)
self.assertIs(type(ExampleGrammaredSequence("A").has_nondegenerates()),
bool)
self.assertFalse(ExampleGrammaredSequence("").has_nondegenerates())
self.assertFalse(
ExampleGrammaredSequence("X-.YZ").has_nondegenerates())
self.assertTrue(ExampleGrammaredSequence("C").has_nondegenerates())
self.assertTrue(
ExampleGrammaredSequence(".XYZ-ABC").has_nondegenerates())
def test_has_definites(self):
self.assertIs(type(ExampleGrammaredSequence("").has_definites()),
bool)
self.assertIs(type(ExampleGrammaredSequence("A").has_definites()),
bool)
self.assertFalse(ExampleGrammaredSequence("").has_definites())
self.assertFalse(
ExampleGrammaredSequence("X-.YZ").has_definites())
self.assertTrue(ExampleGrammaredSequence("C").has_definites())
self.assertTrue(
ExampleGrammaredSequence(".XYZ-ABC").has_definites())
def test_degap(self):
kw = {
'metadata': {
'id': 'some_id',
'description': 'some description',
},
}
self.assertEqual(
ExampleGrammaredSequence(
"", positional_metadata={'qual': []}, **kw).degap(),
ExampleGrammaredSequence(
"", positional_metadata={'qual': []}, **kw))
self.assertEqual(
ExampleGrammaredSequence(
"ABCXYZ",
positional_metadata={'qual': np.arange(6)},
**kw).degap(),
ExampleGrammaredSequence(
"ABCXYZ",
positional_metadata={'qual': np.arange(6)},
**kw))
self.assertEqual(
ExampleGrammaredSequence(
"ABC-XYZ",
positional_metadata={'qual': np.arange(7)},
**kw).degap(),
ExampleGrammaredSequence(
"ABCXYZ",
positional_metadata={'qual': [0, 1, 2, 4, 5, 6]},
**kw))
self.assertEqual(
ExampleGrammaredSequence(
".-ABC-XYZ.",
positional_metadata={'qual': np.arange(10)},
**kw).degap(),
ExampleGrammaredSequence(
"ABCXYZ",
positional_metadata={'qual': [2, 3, 4, 6, 7, 8]},
**kw))
self.assertEqual(
ExampleGrammaredSequence(
"---.-.-.-.-.",
positional_metadata={'quality': np.arange(12)},
**kw).degap(),
ExampleGrammaredSequence(
"",
positional_metadata={'quality': np.array([], dtype=np.int64)},
**kw))
def test_expand_degenerates_no_degens(self):
seq = ExampleGrammaredSequence("ABCABCABC")
self.assertEqual(list(seq.expand_degenerates()), [seq])
def test_expand_degenerates_all_degens(self):
exp = [
ExampleGrammaredSequence('ABA'), ExampleGrammaredSequence('ABC'),
ExampleGrammaredSequence('ACA'), ExampleGrammaredSequence('ACC'),
ExampleGrammaredSequence('BBA'), ExampleGrammaredSequence('BBC'),
ExampleGrammaredSequence('BCA'), ExampleGrammaredSequence('BCC')
]
# Sort based on sequence string, as order is not guaranteed.
obs = sorted(ExampleGrammaredSequence('XYZ').expand_degenerates(),
key=str)
self.assertEqual(obs, exp)
def test_expand_degenerates_with_metadata(self):
kw = {
"metadata": {
"id": "some_id",
"description": "some description"
},
"positional_metadata": {
"quality": np.arange(3),
},
}
exp = [ExampleGrammaredSequence('ABA', **kw),
ExampleGrammaredSequence('ABC', **kw),
ExampleGrammaredSequence('BBA', **kw),
ExampleGrammaredSequence('BBC', **kw)]
obs = sorted(
ExampleGrammaredSequence('XBZ', **kw).expand_degenerates(),
key=str)
self.assertEqual(obs, exp)
def test_to_regex_no_degens(self):
seq = ExampleGrammaredSequence('ABC')
regex = seq.to_regex()
self.assertEqual(regex.pattern, str(seq))
def test_to_regex_with_degens(self):
seq = ExampleGrammaredSequence('AYZ')
regex = seq.to_regex()
self.assertFalse(any(regex.match(s) is None
for s in 'ABA ABC ACA ACC'.split()))
self.assertTrue(all(regex.match(s) is None
for s in 'CBA BBA ABB AAA'.split()))
def test_to_regex_within_capture(self):
seq = ExampleGrammaredSequence('XYC')
regex = seq.to_regex(within_capture=True)
for ref in 'ABA BBB CCA'.split():
self.assertFalse(any(len(match.groups()) == 1
for match in regex.finditer(ref)))
for ref in 'ABC BBC ACC'.split():
self.assertTrue(all(len(match.groups()) == 1
for match in regex.finditer(ref)))
def test_find_motifs_no_motif(self):
seq = ExampleMotifsTester("ABCABCABC")
with self.assertRaises(ValueError) as cm:
seq.find_motifs("doesn't-exist")
self.assertIn("doesn't-exist", str(cm.exception))
seq = ExampleGrammaredSequence("ABCABCABC")
with self.assertRaises(ValueError) as cm:
seq.find_motifs("doesn't-exist")
self.assertIn("doesn't-exist", str(cm.exception))
def test_find_motifs(self):
seq = ExampleMotifsTester("ABC")
self.assertEqual(seq.find_motifs("name1"), "ABC")
self.assertEqual(seq.find_motifs("name2"), 3)
def test_repr(self):
# basic sanity checks for custom repr stats. more extensive testing is
# performed on Sequence.__repr__
# minimal
obs = repr(ExampleGrammaredSequence(''))
self.assertEqual(obs.count('\n'), 7)
self.assertTrue(obs.startswith('ExampleGrammaredSequence'))
self.assertIn('length: 0', obs)
self.assertIn('has gaps: False', obs)
self.assertIn('has degenerates: False', obs)
self.assertIn('has definites: False', obs)
self.assertTrue(obs.endswith('-'))
# no metadata, mix of gaps, degenerates, and definites
obs = repr(ExampleGrammaredSequence('AY-B'))
self.assertEqual(obs.count('\n'), 8)
self.assertTrue(obs.startswith('ExampleGrammaredSequence'))
self.assertIn('length: 4', obs)
self.assertIn('has gaps: True', obs)
self.assertIn('has degenerates: True', obs)
self.assertIn('has definites: True', obs)
self.assertTrue(obs.endswith('0 AY-B'))
# metadata and positional metadata of mixed types
obs = repr(
ExampleGrammaredSequence(
'ABCA',
metadata={'foo': 42, b'bar': 33.33, None: True, False: {},
(1, 2): 3, 'acb' * 100: "'"},
positional_metadata={'foo': range(4),
42: ['a', 'b', [], 'c']}))
self.assertEqual(obs.count('\n'), 18)
self.assertTrue(obs.startswith('ExampleGrammaredSequence'))
self.assertIn('None: True', obs)
self.assertIn('\'foo\': 42', obs)
self.assertIn('42: <dtype: object>', obs)
self.assertIn('\'foo\': <dtype: int64>', obs)
self.assertIn('length: 4', obs)
self.assertIn('has gaps: False', obs)
self.assertIn('has degenerates: False', obs)
self.assertIn('has definites: True', obs)
self.assertTrue(obs.endswith('0 ABCA'))
# sequence spanning > 5 lines
obs = repr(ExampleGrammaredSequence('A' * 301))
self.assertEqual(obs.count('\n'), 12)
self.assertTrue(obs.startswith('ExampleGrammaredSequence'))
self.assertIn('length: 301', obs)
self.assertIn('has gaps: False', obs)
self.assertIn('has degenerates: False', obs)
self.assertIn('has definites: True', obs)
self.assertIn('...', obs)
self.assertTrue(obs.endswith('300 A'))
if __name__ == "__main__":
main()