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
|
#!/usr/bin/env python
# File created on 24 Feb 2012
from __future__ import division
__author__ = "Greg Caporaso"
__copyright__ = "Copyright 2011, The QIIME project"
__credits__ = ["Greg Caporaso"]
__license__ = "GPL"
__version__ = "1.8.0"
__maintainer__ = "Greg Caporaso"
__email__ = "gregcaporaso@gmail.com"
from cogent.util.unit_test import TestCase, main
from cogent import LoadSeqs
from qiime.split import (split_mapping_file_on_field,
split_otu_table_on_sample_metadata,
split_fasta)
from qiime.util import (get_qiime_temp_dir,
remove_files,
get_tmp_filename)
from qiime.format import format_biom_table
from biom.parse import parse_biom_table
from biom.table import DenseOTUTable
class SplitTests(TestCase):
""" Tests of the split module """
def setUp(self):
""" """
self.mapping_f1 = mapping_f1.split('\n')
self.mapping_f2 = mapping_f2.split('\n')
self.mapping_exp = list(mapping_exp)
self.otu_table_f1 = otu_table_f1.split('\n')
def test_split_mapping_file_on_field(self):
""" split_mapping_file_on_field functions as expected with valid input
"""
actual = list(split_mapping_file_on_field(self.mapping_f1,'Treatment'))
actual.sort()
self.mapping_exp.sort()
self.assertEqual(actual,self.mapping_exp)
def test_split_otu_table_on_sample_metadata(self):
""" split_otu_table_on_sample_metadata functions as expected with valid input """
actual = list(split_otu_table_on_sample_metadata(self.otu_table_f1,
self.mapping_f1,
"Treatment"))
for id_, e in actual:
try:
parse_biom_table(e)
except:
print e
actual = [(id_,parse_biom_table(e)) for id_, e in actual]
exp = [(id_,parse_biom_table(e)) for id_, e in otu_table_exp1]
actual.sort()
exp.sort()
for a,e in zip(actual,exp):
self.assertEqual(a,e,"OTU tables are not equal:\n%s\n%s" % \
(format_biom_table(a[1]),format_biom_table(e[1])))
def test_split_otu_table_on_sample_metadata_extra_mapping_entries(self):
""" split_otu_table_on_sample_metadata functions as expected with extra mapping data """
actual = list(split_otu_table_on_sample_metadata(self.otu_table_f1,
self.mapping_f2,
"Treatment"))
actual = [(id_,parse_biom_table(e)) for id_, e in actual]
exp = [(id_,parse_biom_table(e)) for id_, e in otu_table_exp1]
actual.sort()
exp.sort()
for a,e in zip(actual,exp):
self.assertEqual(a,e,"OTU tables are not equal:\n%s\n%s" % \
(format_biom_table(a[1]),format_biom_table(e[1])))
def test_split_fasta_equal_num_seqs_per_file(self):
"""split_fasta funcs as expected when equal num seqs go to each file
"""
filename_prefix = get_tmp_filename(tmp_dir=get_qiime_temp_dir(),
prefix='split_fasta_tests',
suffix='',
result_constructor=str)
infile = ['>seq1','AACCTTAA','>seq2','TTAACC','AATTAA',\
'>seq3','CCTT--AA']
actual = split_fasta(infile, 1, filename_prefix)
actual_seqs = []
for fp in actual:
actual_seqs += list(open(fp))
remove_files(actual)
expected = ['%s.%d.fasta' % (filename_prefix,i) for i in range(3)]
self.assertEqual(actual,expected)
self.assertEqual(\
LoadSeqs(data=infile,aligned=False),\
LoadSeqs(data=actual_seqs,aligned=False))
def test_split_fasta_diff_num_seqs_per_file(self):
"""split_fasta funcs as expected when diff num seqs go to each file
"""
filename_prefix = get_tmp_filename(tmp_dir=get_qiime_temp_dir(),
prefix='split_fasta_tests',
suffix='',
result_constructor=str)
infile = ['>seq1','AACCTTAA','>seq2','TTAACC','AATTAA',\
'>seq3','CCTT--AA']
actual = split_fasta(infile, 2, filename_prefix)
actual_seqs = []
for fp in actual:
actual_seqs += list(open(fp))
remove_files(actual)
expected = ['%s.%d.fasta' % (filename_prefix,i) for i in range(2)]
# list of file paths is as expected
self.assertEqual(actual,expected)
# building seq collections from infile and the split files result in
# equivalent seq collections
self.assertEqual(\
LoadSeqs(data=infile,aligned=False),\
LoadSeqs(data=actual_seqs,aligned=False))
def test_split_fasta_diff_num_seqs_per_file_alt(self):
"""split_fasta funcs always catches all seqs
"""
# start with 59 seqs (b/c it's prime, so should make more
# confusing splits)
in_seqs = LoadSeqs(data=[('seq%s' % k,'AACCTTAA') for k in range(59)])
infile = in_seqs.toFasta().split('\n')
# test seqs_per_file from 1 to 1000
for i in range(1,1000):
filename_prefix = get_tmp_filename(tmp_dir=get_qiime_temp_dir(),
prefix='split_fasta_tests',
suffix='',
result_constructor=str)
actual = split_fasta(infile, i, filename_prefix)
actual_seqs = []
for fp in actual:
actual_seqs += list(open(fp))
# remove the files now, so if the test fails they still get
# cleaned up
remove_files(actual)
# building seq collections from infile and the split files result in
# equivalent seq collections
self.assertEqual(\
LoadSeqs(data=infile,aligned=False),\
LoadSeqs(data=actual_seqs,aligned=False))
mapping_f1 = """#SampleID BarcodeSequence LinkerPrimerSequence Treatment DOB Description
#Example mapping file for the QIIME analysis package. These 9 samples are from a study of the effects of exercise and diet on mouse cardiac physiology (Crawford, et al, PNAS, 2009).
PC.354 AGCACGAGCCTA YATGCTGCCTCCCGTAGGAGT Co_ntrol 20061218 Control_mouse_I.D._354
PC.355 AACTCGTCGATG YATGCTGCCTCCCGTAGGAGT Control 20061218 Control_mouse_I.D._355
PC.356 ACAGACCACTCA YATGCTGCCTCCCGTAGGAGT Co_ntrol 20061126 Control_mouse_I.D._356
PC.481 ACCAGCGACTAG YATGCTGCCTCCCGTAGGAGT Control 20070314 Control_mouse_I.D._481
PC.593 AGCAGCACTTGT YATGCTGCCTCCCGTAGGAGT Control 20071210 Control_mouse_I.D._593
PC.607 AACTGTGCGTAC YATGCTGCCTCCCGTAGGAGT Fast 20071112 Fasting_mouse_I.D._607
PC.634 ACAGAGTCGGCT YATGCTGCCTCCCGTAGGAGT Fast 20080116 Fasting_mouse_I.D._634
PC.635 ACCGCAGAGTCA YATGCTGCCTCCCGTAGGAGT Fast 20080116 Fasting_mouse_I.D._635
PC.636 ACGGTGAGTGTC YATGCTGCCTCCCGTAGGAGT Fast 20080116 Fasting_mouse_I.D._636
"""
mapping_f2 = """#SampleID BarcodeSequence LinkerPrimerSequence Treatment DOB Description
#Example mapping file for the QIIME analysis package. These 9 samples are from a study of the effects of exercise and diet on mouse cardiac physiology (Crawford, et al, PNAS, 2009).
PC.354 AGCACGAGCCTA YATGCTGCCTCCCGTAGGAGT Co_ntrol 20061218 Control_mouse_I.D._354
PC.355 AACTCGTCGATG YATGCTGCCTCCCGTAGGAGT Control 20061218 Control_mouse_I.D._355
PC.356 ACAGACCACTCA YATGCTGCCTCCCGTAGGAGT Co_ntrol 20061126 Control_mouse_I.D._356
PC.481 ACCAGCGACTAG YATGCTGCCTCCCGTAGGAGT Control 20070314 Control_mouse_I.D._481
PC.593 AGCAGCACTTGT YATGCTGCCTCCCGTAGGAGT Control 20071210 Control_mouse_I.D._593
PC.607 AACTGTGCGTAC YATGCTGCCTCCCGTAGGAGT Fast 20071112 Fasting_mouse_I.D._607
PC.634 ACAGAGTCGGCT YATGCTGCCTCCCGTAGGAGT Fast 20080116 Fasting_mouse_I.D._634
PC.635 ACCGCAGAGTCA YATGCTGCCTCCCGTAGGAGT Fast 20080116 Fasting_mouse_I.D._635
PC.636 ACGGTGAGTGTC YATGCTGCCTCCCGTAGGAGT Fast 20080116 Fasting_mouse_I.D._636
Fake.sample ACGGTGAGTGTC YATGCTGCCTCCCGTAGGAGT Other 20080116 Fasting_mouse_I.D._636
"""
mapping_exp = [("Co_ntrol", """#SampleID BarcodeSequence LinkerPrimerSequence Treatment DOB Description
PC.354 AGCACGAGCCTA YATGCTGCCTCCCGTAGGAGT Co_ntrol 20061218 Control_mouse_I.D._354
PC.356 ACAGACCACTCA YATGCTGCCTCCCGTAGGAGT Co_ntrol 20061126 Control_mouse_I.D._356"""),
("Control","""#SampleID BarcodeSequence LinkerPrimerSequence Treatment DOB Description
PC.355 AACTCGTCGATG YATGCTGCCTCCCGTAGGAGT Control 20061218 Control_mouse_I.D._355
PC.481 ACCAGCGACTAG YATGCTGCCTCCCGTAGGAGT Control 20070314 Control_mouse_I.D._481
PC.593 AGCAGCACTTGT YATGCTGCCTCCCGTAGGAGT Control 20071210 Control_mouse_I.D._593"""),
("Fast","""#SampleID BarcodeSequence LinkerPrimerSequence Treatment DOB Description
PC.607 AACTGTGCGTAC YATGCTGCCTCCCGTAGGAGT Fast 20071112 Fasting_mouse_I.D._607
PC.634 ACAGAGTCGGCT YATGCTGCCTCCCGTAGGAGT Fast 20080116 Fasting_mouse_I.D._634
PC.635 ACCGCAGAGTCA YATGCTGCCTCCCGTAGGAGT Fast 20080116 Fasting_mouse_I.D._635
PC.636 ACGGTGAGTGTC YATGCTGCCTCCCGTAGGAGT Fast 20080116 Fasting_mouse_I.D._636""")]
otu_table_f1 = """{
"id":null,
"format": "Biological Observation Matrix v0.9",
"format_url": "http://www.qiime.org/svn_documentation/documentation/biom_format.html",
"type": "OTU table",
"generated_by": "QIIME",
"date": "2011-12-19T19:00:00",
"rows":[
{"id":"GG_OTU_1", "metadata":null},
{"id":"GG_OTU_2", "metadata":null},
{"id":"GG_OTU_3", "metadata":null},
{"id":"GG_OTU_4", "metadata":null},
{"id":"GG_OTU_5", "metadata":null}
],
"columns": [
{"id":"PC.354", "metadata":null},
{"id":"PC.355", "metadata":null},
{"id":"PC.481", "metadata":null},
{"id":"PC.607", "metadata":null},
{"id":"PC.635", "metadata":null},
{"id":"PC.356", "metadata":null},
{"id":"PC.636", "metadata":null}
],
"matrix_type": "sparse",
"matrix_element_type": "int",
"shape": [5, 7],
"data":[[0,2,1],
[1,0,5],
[1,1,1],
[1,3,2],
[1,4,3],
[1,5,1],
[2,2,1],
[2,3,4],
[2,4,2],
[3,0,2],
[3,1,1],
[3,2,1],
[3,5,1],
[4,1,1],
[4,2,1],
[4,6,42]
]
}"""
otu_table_exp1 = [("Co_ntrol","""{
"id":null,
"format": "Biological Observation Matrix v0.9",
"format_url": "http://www.qiime.org/svn_documentation/documentation/biom_format.html",
"type": "OTU table",
"generated_by": "QIIME",
"date": "2011-12-19T19:00:00",
"rows":[
{"id":"GG_OTU_1", "metadata":null},
{"id":"GG_OTU_2", "metadata":null},
{"id":"GG_OTU_3", "metadata":null},
{"id":"GG_OTU_4", "metadata":null},
{"id":"GG_OTU_5", "metadata":null}
],
"columns": [
{"id":"PC.354", "metadata":null},
{"id":"PC.356", "metadata":null}
],
"matrix_type": "sparse",
"matrix_element_type": "float",
"shape": [5, 2],
"data":[
[1,0,5.0],
[1,1,1.0],
[3,0,2.0],
[3,1,1.0]
]
}"""),
("Control","""{
"id":null,
"format": "Biological Observation Matrix v0.9",
"format_url": "http://www.qiime.org/svn_documentation/documentation/biom_format.html",
"type": "OTU table",
"generated_by": "QIIME",
"date": "2011-12-19T19:00:00",
"rows":[
{"id":"GG_OTU_1", "metadata":null},
{"id":"GG_OTU_2", "metadata":null},
{"id":"GG_OTU_3", "metadata":null},
{"id":"GG_OTU_4", "metadata":null},
{"id":"GG_OTU_5", "metadata":null}
],
"columns": [
{"id":"PC.355", "metadata":null},
{"id":"PC.481", "metadata":null}
],
"matrix_type": "sparse",
"matrix_element_type": "float",
"shape": [5, 2],
"data":[[0,1,1.0],
[1,0,1.0],
[2,1,1.0],
[3,0,1.0],
[3,1,1.0],
[4,0,1.0],
[4,1,1.0]
]
}
"""),
("Fast","""{
"id":null,
"format": "Biological Observation Matrix v0.9",
"format_url": "http://www.qiime.org/svn_documentation/documentation/biom_format.html",
"type": "OTU table",
"generated_by": "QIIME",
"date": "2011-12-19T19:00:00",
"rows":[
{"id":"GG_OTU_1", "metadata":null},
{"id":"GG_OTU_2", "metadata":null},
{"id":"GG_OTU_3", "metadata":null},
{"id":"GG_OTU_4", "metadata":null},
{"id":"GG_OTU_5", "metadata":null}
],
"columns": [
{"id":"PC.607", "metadata":null},
{"id":"PC.635", "metadata":null},
{"id":"PC.636", "metadata":null}
],
"matrix_type": "sparse",
"matrix_element_type": "float",
"shape": [5, 3],
"data":[[1,0,2.0],
[1,1,3.0],
[2,0,4.0],
[2,1,2.0],
[4,2,42]
]
}""")]
if __name__ == "__main__":
main()
|
