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
|
# Copyright 2010-2013 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.
"""Testing Bio.TogoWS online code.
"""
from __future__ import print_function
import unittest
from Bio._py3k import StringIO
import requires_internet
requires_internet.check()
# We want to test these:
from Bio import TogoWS
# In order to check any sequences returned
from Bio import SeqIO
from Bio.SeqUtils.CheckSum import seguid
from Bio import Medline
#####################################################################
class TogoFields(unittest.TestCase):
def test_invalid_database(self):
"""Check asking for fields of invalid database fails"""
self.assertRaises(IOError, TogoWS._get_fields,
"http://togows.dbcls.jp/entry/invalid?fields")
def test_databases(self):
"""Check supported databases"""
dbs = set(TogoWS._get_entry_dbs())
expected = set(['nuccore', 'nucest', 'nucgss',
'nucleotide', 'protein', 'gene',
'homologene', 'snp',
'mesh', 'pubmed', # 'embl',
'uniprot', 'uniparc', 'uniref100',
'uniref90', 'uniref50', 'ddbj',
'dad', 'pdb', 'compound', 'drug',
'enzyme', 'genes', 'glycan',
'orthology', 'reaction', 'module',
'pathway'])
self.assertTrue(dbs.issuperset(expected),
"Missing DB: %s" % ", ".join(sorted(expected.difference(dbs))))
def test_pubmed(self):
"""Check supported fields for pubmed database"""
fields = set(TogoWS._get_entry_fields("pubmed"))
self.assertTrue(fields.issuperset(['abstract', 'au', 'authors',
'doi', 'mesh', 'so',
'title']), fields)
def test_ncbi_protein(self):
"""Check supported fields for NCBI protein database"""
fields = set(TogoWS._get_entry_fields("ncbi-protein"))
self.assertTrue(fields.issuperset(['entry_id', 'length', 'strand',
'moltype', 'linearity', 'division',
'date', 'definition', 'accession',
'accessions', 'version', 'versions',
'acc_version', 'gi', 'keywords',
'organism', 'common_name',
'taxonomy', 'comment', 'seq']),
fields)
def test_ddbj(self):
"""Check supported fields for ddbj database"""
fields = set(TogoWS._get_entry_fields("ddbj"))
self.assertTrue(fields.issuperset(['entry_id', 'length', 'strand',
'moltype', 'linearity', 'division',
'date', 'definition', 'accession',
'accessions', 'version', 'versions',
'acc_version', 'gi', 'keywords',
'organism', 'common_name',
'taxonomy', 'comment', 'seq']),
fields)
# def test_embl(self):
# """Check supported fields for embl database"""
# fields = set(TogoWS._get_entry_fields("embl"))
# self.assertTrue(fields.issuperset(["definition", "entry_id", "seq"]),
# fields)
def test_uniprot(self):
"""Check supported fields for uniprot database"""
fields = set(TogoWS._get_entry_fields("uniprot"))
self.assertTrue(fields.issuperset(["definition", "entry_id", "seq"]),
fields)
def test_pdb(self):
"""Check supported fields for pdb database"""
fields = set(TogoWS._get_entry_fields("pdb"))
self.assertTrue(fields.issuperset(["accession", "chains", "keywords",
"models"]), fields)
class TogoEntry(unittest.TestCase):
def test_pubmed_16381885(self):
"""Bio.TogoWS.entry("pubmed", "16381885")"""
# Gives Medline plain text
handle = TogoWS.entry("pubmed", "16381885")
data = Medline.read(handle)
handle.close()
self.assertEqual(data["TI"],
'From genomics to chemical genomics: new developments in KEGG.')
self.assertEqual(data["AU"], ['Kanehisa M', 'Goto S', 'Hattori M',
'Aoki-Kinoshita KF', 'Itoh M',
'Kawashima S', 'Katayama T', 'Araki M',
'Hirakawa M'])
def test_pubmed_16381885_ti(self):
"""Bio.TogoWS.entry("pubmed", "16381885", field="title")"""
handle = TogoWS.entry("pubmed", "16381885", field="title")
data = handle.read().strip()
handle.close()
self.assertEqual(data,
'From genomics to chemical genomics: new developments in KEGG.')
def test_pubmed_16381885_title(self):
"""Bio.TogoWS.entry("pubmed", "16381885", field="title")"""
handle = TogoWS.entry("pubmed", "16381885", field="title")
data = handle.read().strip()
handle.close()
self.assertEqual(data,
'From genomics to chemical genomics: new developments in KEGG.')
def test_pubmed_16381885_au(self):
"""Bio.TogoWS.entry("pubmed", "16381885", field="au")"""
# Gives one name per line (i.e. \n separated), no dots
handle = TogoWS.entry("pubmed", "16381885", field="au")
data = handle.read().strip().split("\n")
handle.close()
self.assertEqual(data, ['Kanehisa M', 'Goto S', 'Hattori M',
'Aoki-Kinoshita KF', 'Itoh M',
'Kawashima S', 'Katayama T', 'Araki M',
'Hirakawa M'])
def test_pubmed_16381885_authors(self):
"""Bio.TogoWS.entry("pubmed", "16381885", field="authors")"""
# Gives names tab separated (i.e. \t separated)
handle = TogoWS.entry("pubmed", "16381885", field="authors")
data = handle.read().strip().split("\t")
handle.close()
self.assertEqual(data, ['Kanehisa, M.', 'Goto, S.', 'Hattori, M.',
'Aoki-Kinoshita, K. F.', 'Itoh, M.',
'Kawashima, S.', 'Katayama, T.', 'Araki, M.',
'Hirakawa, M.'])
def test_pubmed_16381885_invalid_field(self):
"""Bio.TogoWS.entry("pubmed", "16381885", field="invalid_for_testing")"""
self.assertRaises(ValueError, TogoWS.entry,
"pubmed", "16381885", field="invalid_for_testing")
def test_pubmed_16381885_invalid_format(self):
"""Bio.TogoWS.entry("pubmed", "16381885", format="invalid_for_testing")"""
self.assertRaises(ValueError, TogoWS.entry,
"pubmed", "16381885", format="invalid_for_testing")
def test_pubmed_invalid_id(self):
"""Bio.TogoWS.entry("pubmed", "invalid_for_testing")"""
self.assertRaises(IOError, TogoWS.entry,
"pubmed", "invalid_for_testing")
def test_pubmed_16381885_and_19850725(self):
"""Bio.TogoWS.entry("pubmed", "16381885,19850725")"""
handle = TogoWS.entry("pubmed", "16381885,19850725")
records = list(Medline.parse(handle))
handle.close()
self.assertEqual(len(records), 2)
self.assertEqual(records[0]["TI"],
'From genomics to chemical genomics: new developments in KEGG.')
self.assertEqual(records[0]["AU"], ['Kanehisa M', 'Goto S',
'Hattori M', 'Aoki-Kinoshita KF',
'Itoh M', 'Kawashima S',
'Katayama T', 'Araki M',
'Hirakawa M'])
self.assertEqual(records[1]["TI"],
'DDBJ launches a new archive database with analytical tools ' +
'for next-generation sequence data.')
self.assertEqual(records[1]["AU"], ['Kaminuma E', 'Mashima J',
'Kodama Y', 'Gojobori T',
'Ogasawara O', 'Okubo K',
'Takagi T', 'Nakamura Y'])
def test_pubmed_16381885_and_19850725_authors(self):
"""Bio.TogoWS.entry("pubmed", "16381885,19850725", field="authors")"""
handle = TogoWS.entry("pubmed", "16381885,19850725", field="authors")
# Little hack to remove blank lines...
# names = handle.read().replace("\n\n", "\n").strip().split("\n")
names = handle.read().strip().split("\n")
handle.close()
self.assertEqual(2, len(names))
names1, names2 = names
self.assertEqual(names1.split("\t"),
['Kanehisa, M.', 'Goto, S.', 'Hattori, M.',
'Aoki-Kinoshita, K. F.', 'Itoh, M.',
'Kawashima, S.', 'Katayama, T.',
'Araki, M.', 'Hirakawa, M.'])
self.assertEqual(names2.split("\t"),
['Kaminuma, E.', 'Mashima, J.', 'Kodama, Y.',
'Gojobori, T.', 'Ogasawara, O.', 'Okubo, K.',
'Takagi, T.', 'Nakamura, Y.'])
def test_invalid_db(self):
"""Bio.TogoWS.entry("invalid_db", "invalid_id")"""
self.assertRaises(ValueError, TogoWS.entry,
"invalid_db", "invalid_id")
def test_ddbj_genbank_length(self):
"""Bio.TogoWS.entry("ddbj", "X52960", field="length")"""
handle = TogoWS.entry("ddbj", "X52960", field="length")
data = handle.read().strip() # ignore trailing \n
handle.close()
self.assertEqual(data, "248")
def test_ddbj_genbank(self):
"""Bio.TogoWS.entry("ddbj", "X52960")"""
handle = TogoWS.entry("ddbj", "X52960") # Returns "genbank" format
record = SeqIO.read(handle, "gb")
handle.close()
self.assertEqual(record.id, "X52960.1")
self.assertEqual(record.name, "X52960")
self.assertEqual(len(record), 248)
self.assertEqual(seguid(record.seq), "Ktxz0HgMlhQmrKTuZpOxPZJ6zGU")
def test_nucleotide_genbank_length(self):
"""Bio.TogoWS.entry("nucleotide", "X52960", field="length")"""
handle = TogoWS.entry("nucleotide", "X52960", field="length")
data = handle.read().strip() # ignore trailing \n
handle.close()
self.assertEqual(data, "248")
def test_nucleotide_genbank_seq(self):
"""Bio.TogoWS.entry("nucleotide", "X52960", field="seq")"""
handle = TogoWS.entry("nucleotide", "X52960", field="seq")
data = handle.read().strip() # ignore trailing \n
handle.close()
self.assertEqual(seguid(data), "Ktxz0HgMlhQmrKTuZpOxPZJ6zGU")
def test_nucleotide_genbank_definition(self):
"""Bio.TogoWS.entry("nucleotide", "X52960", field="definition")"""
handle = TogoWS.entry("nucleotide", "X52960", field="definition")
data = handle.read().strip() # ignore trailing \n
handle.close()
self.assertEqual(data, "Coleus blumei viroid 1 (CbVd) RNA.")
def test_nucleotide_genbank_accession(self):
"""Bio.TogoWS.entry("nucleotide", "X52960", field="accession")"""
handle = TogoWS.entry("nucleotide", "X52960", field="accession")
data = handle.read().strip() # ignore trailing \n
handle.close()
self.assertEqual(data, "X52960")
def test_nucleotide_genbank_version(self):
"""Bio.TogoWS.entry("nucleotide", "X52960", field="version")"""
handle = TogoWS.entry("nucleotide", "X52960", field="version")
data = handle.read().strip() # ignore trailing \n
handle.close()
self.assertEqual(data, "1")
def test_nucleotide_genbank_acc_version(self):
"""Bio.TogoWS.entry("nucleotide", "X52960", field="acc_version")"""
handle = TogoWS.entry("nucleotide", "X52960", field="acc_version")
data = handle.read().strip() # ignore trailing \n
handle.close()
self.assertEqual(data, "X52960.1")
def test_nucleotide_genbank_organism(self):
"""Bio.TogoWS.entry("nucleotide", "X52960", field="organism")"""
handle = TogoWS.entry("nucleotide", "X52960", field="organism")
data = handle.read().strip() # ignore trailing \n
handle.close()
self.assertEqual(data, "Coleus blumei viroid 1")
def test_ddbj_genbank_invalid_field(self):
"""Bio.TogoWS.entry("nucleotide", "X52960", field="invalid_for_testing")"""
self.assertRaises(ValueError, TogoWS.entry,
"nucleotide", "X52960", field="invalid_for_testing")
def test_nucleotide_invalid_format(self):
"""Bio.TogoWS.entry("nucleotide", "X52960", format="invalid_for_testing")"""
self.assertRaises(ValueError, TogoWS.entry,
"nucleotide", "X52960", format="invalid_for_testing")
def test_ddbj_gff3(self):
"""Bio.TogoWS.entry("ddbj", "X52960", format="gff")"""
handle = TogoWS.entry("ddbj", "X52960", format="gff")
data = handle.read()
handle.close()
self.assertTrue(data.startswith("##gff-version 3\nX52960\tDDBJ\t"), data)
def test_genbank_gff3(self):
"""Bio.TogoWS.entry("nucleotide", "X52960", format="gff")"""
# Note - Using manual URL with genbank instead of nucleotide works
handle = TogoWS.entry("nucleotide", "X52960", format="gff")
data = handle.read()
handle.close()
self.assertTrue(data.startswith("##gff-version 3\nX52960\tGenbank\t"), data)
# def test_embl_AM905444_gff3(self):
# """Bio.TogoWS.entry("embl", "AM905444", format="gff")"""
# handle = TogoWS.entry("embl", "AM905444", format="gff")
# data = handle.read()
# handle.close()
# self.assertTrue(data.startswith("##gff-version 3\nAM905444\tembl\t"), data)
# def test_embl_AM905444_seq(self):
# """Bio.TogoWS.entry("embl", "AM905444", field="seq")"""
# handle = TogoWS.entry("embl", "AM905444", field="seq")
# data = handle.read().strip() # ignore any trailing \n
# handle.close()
# self.assertEqual(seguid(data), "G0HtLpwF7i4FXUaUjDUPTjok79c")
# def test_embl_AM905444_definition(self):
# """Bio.TogoWS.entry("embl", "AM905444", field="definition")"""
# handle = TogoWS.entry("embl", "AM905444", field="definition")
# data = handle.read().strip() # ignore any trailing \n
# handle.close()
# self.assertEqual(data, "Herbaspirillum seropedicae locus tag HS193.0074 for porin")
# def test_embl_AM905444(self):
# """Bio.TogoWS.entry("embl", "AM905444")"""
# handle = TogoWS.entry("embl", "AM905444")
# record = SeqIO.read(handle, "embl")
# handle.close()
# self.assertTrue("AM905444" in record.id, record.id)
# self.assertTrue("AM905444" in record.name, record.name)
# self.assertTrue("porin" in record.description, record.description)
# self.assertEqual(len(record), 1164)
# self.assertEqual(seguid(record.seq), "G0HtLpwF7i4FXUaUjDUPTjok79c")
def test_ddbj_fasta(self):
"""Bio.TogoWS.entry("ddbj", "X52960", "fasta")"""
handle = TogoWS.entry("ddbj", "X52960", "fasta")
record = SeqIO.read(handle, "fasta")
handle.close()
self.assertTrue("X52960" in record.id, record.id)
self.assertTrue("X52960" in record.name, record.name)
self.assertEqual(len(record), 248)
self.assertEqual(seguid(record.seq), "Ktxz0HgMlhQmrKTuZpOxPZJ6zGU")
def test_uniprot_swiss(self):
"""Bio.TogoWS.entry("uniprot", ["A1AG1_HUMAN","A1AG1_MOUSE"])"""
# Returns "swiss" format:
handle = TogoWS.entry("uniprot", ["A1AG1_HUMAN", "A1AG1_MOUSE"])
record1, record2 = SeqIO.parse(handle, "swiss")
handle.close()
self.assertEqual(record1.id, "P02763")
self.assertEqual(record1.name, "A1AG1_HUMAN")
self.assertEqual(len(record1), 201)
self.assertEqual(seguid(record1.seq), "LHDJJ6oC7gUXo8CC7Xn6EUeA8Gk")
self.assertEqual(record2.id, "Q60590")
self.assertEqual(record2.name, "A1AG1_MOUSE")
self.assertEqual(len(record2), 207)
self.assertEqual(seguid(record2.seq), "FGcj+RFQhP2gRusCmwPFty5PJT0")
def test_nucleotide_fasta(self):
"""Bio.TogoWS.entry("nucleotide", "6273291", "fasta")"""
handle = TogoWS.entry("nucleotide", "6273291", "fasta")
record = SeqIO.read(handle, "fasta")
handle.close()
self.assertTrue("6273291" in record.id, record.id)
self.assertTrue("6273291" in record.name, record.name)
self.assertEqual(len(record), 902)
self.assertEqual(seguid(record.seq), "bLhlq4mEFJOoS9PieOx4nhGnjAQ")
def test_protein_fasta(self):
"""Bio.TogoWS.entry("protein", "16130152", "fasta")"""
handle = TogoWS.entry("protein", "16130152", "fasta")
record = SeqIO.read(handle, "fasta")
handle.close()
# Could use assertIn but requires Python 2.7+
self.assertTrue("16130152" in record.id, record.id)
self.assertTrue("16130152" in record.name, record.name)
self.assertTrue("porin protein" in record.description, record.description)
self.assertEqual(len(record), 367)
self.assertEqual(seguid(record.seq), "fCjcjMFeGIrilHAn6h+yju267lg")
class TogoSearch(unittest.TestCase):
"""Search tests."""
def test_bad_args_just_limit(self):
"""Reject Bio.TogoWS.search(...) with just limit"""
self.assertRaises(ValueError, TogoWS.search,
"pubmed", "lung+cancer", limit=10)
def test_bad_args_just_offset(self):
"""Reject Bio.TogoWS.search(...) with just offset"""
self.assertRaises(ValueError, TogoWS.search,
"pubmed", "lung+cancer", offset=10)
def test_bad_args_zero_limit(self):
"""Reject Bio.TogoWS.search(...) with zero limit"""
self.assertRaises(ValueError, TogoWS.search,
"pubmed", "lung+cancer", offset=1, limit=0)
def test_bad_args_zero_offset(self):
"""Reject Bio.TogoWS.search(...) with zero offset"""
self.assertRaises(ValueError, TogoWS.search,
"pubmed", "lung+cancer", offset=0, limit=10)
def test_bad_args_non_int_offset(self):
"""Reject Bio.TogoWS.search(...) with non-integer offset"""
self.assertRaises(ValueError, TogoWS.search,
"pubmed", "lung+cancer", offset="test", limit=10)
def test_bad_args_non_int_limit(self):
"""Reject Bio.TogoWS.search(...) with non-integer limit"""
self.assertRaises(ValueError, TogoWS.search,
"pubmed", "lung+cancer", offset=1, limit="lots")
def test_pubmed_search_togows(self):
"""Bio.TogoWS.search_iter("pubmed", "TogoWS") etc"""
self.check("pubmed", "TogoWS", ["20472643"])
def test_pubmed_search_bioruby(self):
"""Bio.TogoWS.search_iter("pubmed", "BioRuby") etc"""
self.check("pubmed", "BioRuby", ["22994508", "22399473",
"20739307", "20015970", "14693808"])
def test_pubmed_search_porin(self):
"""Bio.TogoWS.search_iter("pubmed", "human porin") etc
Count was 357 at time of writing, this was choosen to
be larger than the default chunk size for iteration,
but still not too big to download the full list.
"""
self.check("pubmed", "human porin", ["21189321", "21835183"])
def test_pdb_search_porin(self):
"""Bio.TogoWS.search_iter("pdb", "porin") etc
Count was about 161 at time of writing.
"""
self.check("pdb", "porin", ["2j1n", "2vqg", "3m8b", "2k0l"])
# def test_embl_search_porin(self):
# """Bio.TogoWS.search_iter("embl", "human pore", limit=200) etc
#
# Count was about 297 at time of writing.
# """
# self.check("embl", "human pore", limit=200)
def test_uniprot_search_lung_cancer(self):
"""Bio.TogoWS.search_iter("uniprot", "terminal+lung+cancer", limit=150) etc
Search count was 211 at time of writing, a bit large to
download all the results in a unit test. Want to use a limit
larger than the batch size (100) to ensure at least two
batches.
"""
self.check("uniprot", "terminal+lung+cancer", limit=150)
def check(self, database, search_term, expected_matches=(), limit=None):
if expected_matches and limit:
raise ValueError("Bad test - TogoWS makes no promises about order")
search_count = TogoWS.search_count(database, search_term)
if expected_matches and search_count < len(expected_matches):
raise ValueError("Only %i matches, expected at least %i"
% (search_count, len(expected_matches)))
if search_count > 5000 and not limit:
print("%i results, skipping" % search_count)
return
if limit:
count = min(search_count, limit)
else:
count = search_count
# Iteration should find everything... unless a limit is used
search_iter = list(TogoWS.search_iter(database, search_term, limit))
self.assertEqual(count, len(search_iter))
for match in expected_matches:
self.assertTrue(match in search_iter,
"Expected %s in results but not" % match)
class TogoConvert(unittest.TestCase):
"""Conversion tests."""
def test_invalid_format(self):
"""Check convert file format checking."""
self.assertRaises(ValueError, TogoWS.convert,
StringIO("PLACEHOLDER"),
"genbank", "invalid_for_testing")
self.assertRaises(ValueError, TogoWS.convert,
StringIO("PLACEHOLDER"),
"invalid_for_testing", "fasta")
def test_genbank_to_fasta(self):
"""Conversion of GenBank to FASTA."""
filename = "GenBank/NC_005816.gb"
old = SeqIO.read(filename, "gb")
with open(filename) as handle:
new = SeqIO.read(TogoWS.convert(handle, "genbank", "fasta"), "fasta")
self.assertEqual(str(old.seq), str(new.seq))
# def test_genbank_to_embl(self):
# """Conversion of GenBank to EMBL."""
# filename = "GenBank/NC_005816.gb"
# old = SeqIO.read(filename, "gb")
# with open(filename) as handle:
# new = SeqIO.read(TogoWS.convert(handle, "genbank", "embl"), "embl")
# self.assertEqual(str(old.seq), str(new.seq))
if __name__ == "__main__":
runner = unittest.TextTestRunner(verbosity=2)
unittest.main(testRunner=runner)
|
