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
|
import unittest
import pysam
import os
import sys
import re
import copy
import gzip
from TestUtils import load_and_convert, TABIX_DATADIR
class TestParser(unittest.TestCase):
filename = os.path.join(TABIX_DATADIR, "example.gtf.gz")
def setUp(self):
self.tabix = pysam.TabixFile(self.filename)
self.compare = load_and_convert(self.filename)
def tearDown(self):
self.tabix.close()
def testRead(self):
for x, r in enumerate(self.tabix.fetch(parser=pysam.asTuple())):
c = self.compare[x]
self.assertEqual(c, list(r))
self.assertEqual(len(c), len(r))
# test indexing
for y in range(0, len(r)):
self.assertEqual(c[y], r[y])
# test slicing access
for y in range(0, len(r) - 1):
for cc in range(y + 1, len(r)):
self.assertEqual(c[y:cc],
r[y:cc])
self.assertEqual("\t".join(map(str, c)),
str(r))
def testWrite(self):
for x, r in enumerate(self.tabix.fetch(parser=pysam.asTuple())):
self.assertEqual(self.compare[x], list(r))
c = list(r)
for y in range(len(r)):
r[y] = "test_%05i" % y
c[y] = "test_%05i" % y
self.assertEqual([x for x in c], list(r))
self.assertEqual("\t".join(c), str(r))
# check second assignment
for y in range(len(r)):
r[y] = "test_%05i" % y
self.assertEqual([x for x in c], list(r))
self.assertEqual("\t".join(c), str(r))
def testUnset(self):
for x, r in enumerate(self.tabix.fetch(parser=pysam.asTuple())):
self.assertEqual(self.compare[x], list(r))
c = list(r)
e = list(r)
for y in range(len(r)):
r[y] = None
c[y] = None
e[y] = ""
self.assertEqual(c, list(r))
self.assertEqual("\t".join(e), str(r))
def testIteratorCompressed(self):
'''test iteration from compressed file.'''
with gzip.open(self.filename) as infile:
for x, r in enumerate(pysam.tabix_iterator(
infile, pysam.asTuple())):
self.assertEqual(self.compare[x], list(r))
self.assertEqual(len(self.compare[x]), len(r))
# test indexing
for c in range(0, len(r)):
self.assertEqual(self.compare[x][c], r[c])
# test slicing access
for c in range(0, len(r) - 1):
for cc in range(c + 1, len(r)):
self.assertEqual(self.compare[x][c:cc],
r[c:cc])
def testIteratorUncompressed(self):
'''test iteration from uncompressed file.'''
tmpfilename = 'tmp_testIteratorUncompressed'
with gzip.open(self.filename, "rb") as infile, \
open(tmpfilename, "wb") as outfile:
outfile.write(infile.read())
with open(tmpfilename) as infile:
for x, r in enumerate(pysam.tabix_iterator(
infile, pysam.asTuple())):
self.assertEqual(self.compare[x], list(r))
self.assertEqual(len(self.compare[x]), len(r))
# test indexing
for c in range(0, len(r)):
self.assertEqual(self.compare[x][c], r[c])
# test slicing access
for c in range(0, len(r) - 1):
for cc in range(c + 1, len(r)):
self.assertEqual(self.compare[x][c:cc],
r[c:cc])
os.unlink(tmpfilename)
def testCopy(self):
a = self.tabix.fetch(parser=pysam.asTuple()).next()
b = copy.copy(a)
self.assertEqual(a, b)
a = self.tabix.fetch(parser=pysam.asGTF()).next()
b = copy.copy(a)
self.assertEqual(a, b)
class TestGTF(TestParser):
parser = pysam.asGTF
def build_attribute_string(self, d):
"""build attribute string from dictionary d"""
s = "; ".join(["{} \"{}\"".format(x, y) for (x, y) in d.items()]) + ";"
# remove quotes around numeric values
s = re.sub("\"(\d+)\"", r"\1", s)
return s
def testRead(self):
for x, r in enumerate(self.tabix.fetch(parser=self.parser())):
c = self.compare[x]
self.assertEqual(len(c), len(r))
self.assertEqual(list(c), list(r))
self.assertEqual(c, str(r).split("\t"))
self.assertTrue(r.gene_id.startswith("ENSG"))
if r.feature != 'gene':
self.assertTrue(r.transcript_id.startswith("ENST"))
self.assertEqual(c[0], r.contig)
self.assertEqual("\t".join(map(str, c)),
str(r))
def test_setting_fields(self):
r = self.tabix.fetch(parser=self.parser()).next()
r.contig = r.contig + "_test_contig"
r.source = r.source + "_test_source"
r.feature = r.feature + "_test_feature"
r.start += 10
r.end += 10
r.score = 20
r.strand = "+"
r.frame = 0
r.attributes = 'gene_id "0001";'
r.transcript_id = "0002"
sr = str(r)
self.assertTrue("_test_contig" in sr)
self.assertTrue("_test_source" in sr)
self.assertTrue("_test_feature" in sr)
self.assertTrue("gene_id \"0001\"" in sr)
self.assertTrue("transcript_id \"0002\"" in sr)
def test_setAttribute_makes_changes(self):
r = self.tabix.fetch(parser=self.parser()).next()
r.setAttribute("transcript_id", "abcd")
sr = str(r)
self.assertEqual(r.transcript_id, "abcd")
self.assertTrue("transcript_id \"abcd\"" in sr)
def test_added_attribute_is_output(self):
r = self.tabix.fetch(parser=self.parser()).next()
r.new_int_attribute = 12
self.assertTrue("new_int_attribute 12" in str(r).split("\t")[8])
r.new_float_attribute = 12.0
self.assertTrue("new_float_attribute 12.0" in str(r).split("\t")[8])
r.new_text_attribute = "abc"
self.assertTrue("new_text_attribute \"abc\"" in str(r).split("\t")[8])
def test_setting_start_is_one_based(self):
r = self.tabix.fetch(parser=self.parser()).next()
r.start = 1800
self.assertEqual(r.start, 1800)
self.assertEqual(str(r).split("\t")[3], "1801")
def test_setting_end_is_one_based(self):
r = self.tabix.fetch(parser=self.parser()).next()
r.end = 2100
self.assertEqual(r.end, 2100)
self.assertEqual(str(r).split("\t")[4], "2100")
def test_setting_frame_to_none_produces_dot(self):
r = self.tabix.fetch(parser=self.parser()).next()
r.frame = None
self.assertEqual(str(r).split("\t")[7], ".")
r.frame = 2
self.assertEqual(str(r).split("\t")[7], "2")
r = self.tabix.fetch(parser=self.parser()).next()
r.frame = "."
self.assertEqual(r.frame, None)
self.assertEqual(str(r).split("\t")[7], ".")
def test_setting_source_to_none_produces_dot(self):
r = self.tabix.fetch(parser=self.parser()).next()
r.source = None
self.assertEqual(str(r).split("\t")[1], ".")
r.source = "source"
self.assertEqual(str(r).split("\t")[1], "source")
r = self.tabix.fetch(parser=self.parser()).next()
r.source = "."
self.assertEqual(r.source, None)
self.assertEqual(str(r).split("\t")[1], ".")
def test_setting_feature_to_none_produces_dot(self):
r = self.tabix.fetch(parser=self.parser()).next()
r.feature = None
self.assertEqual(str(r).split("\t")[2], ".")
r.feature = "feature"
self.assertEqual(str(r).split("\t")[2], "feature")
r = self.tabix.fetch(parser=self.parser()).next()
r.feature = "."
self.assertEqual(r.feature, None)
self.assertEqual(str(r).split("\t")[2], ".")
def test_setting_strand_to_none_produces_dot(self):
r = self.tabix.fetch(parser=self.parser()).next()
r.strand = None
self.assertEqual(str(r).split("\t")[6], ".")
r.strand = "-"
self.assertEqual(str(r).split("\t")[6], "-")
r = self.tabix.fetch(parser=self.parser()).next()
r.strand = "."
self.assertEqual(r.strand, None)
self.assertEqual(str(r).split("\t")[6], ".")
def test_setting_score_to_none_produces_dot(self):
r = self.tabix.fetch(parser=self.parser()).next()
r.score = None
self.assertEqual(str(r).split("\t")[5], ".")
r.score = 12.0
self.assertEqual(str(r).split("\t")[5], "12.0")
r.score = -12.0
self.assertEqual(str(r).split("\t")[5], "-12.0")
r = self.tabix.fetch(parser=self.parser()).next()
r.score = "."
self.assertEqual(r.score, None)
self.assertEqual(str(r).split("\t")[5], ".")
r.score = 12
self.assertEqual(str(r).split("\t")[5], "12")
r.score = -12
self.assertEqual(str(r).split("\t")[5], "-12")
def test_asdict_contains_attributes(self):
r = self.tabix.fetch(parser=self.parser()).next()
d = r.to_dict()
c = self.compare[0]
s = self.build_attribute_string(d)
self.assertEqual(s, c[8])
def test_asdict_can_be_modified(self):
r = self.tabix.fetch(parser=self.parser()).next()
d = r.to_dict()
d["gene_id"] = "new_gene_id"
self.assertTrue("gene_id \"new_gene_id\"", str(r))
class TestGFF3(TestGTF):
parser = pysam.asGFF3
filename = os.path.join(TABIX_DATADIR, "example.gff3.gz")
def build_attribute_string(self, d):
"""build attribute string from dictionary d"""
s = ";".join(["{}={}".format(x, y) for (x, y) in d.items()]) + ";"
return s
def build_attribute_string(self, d):
"""build attribute string from dictionary d"""
s = ";".join(["{}={}".format(x, y) for (x, y) in d.items()]) + ";"
return s
def testRead(self):
for x, r in enumerate(self.tabix.fetch(parser=self.parser())):
c = self.compare[x]
self.assertEqual(len(c), len(r))
self.assertEqual(list(c), list(r))
self.assertEqual(c, str(r).split("\t"))
self.assertEqual(c[0], r.contig)
self.assertEqual("\t".join(map(str, c)),
str(r))
self.assertTrue(r.ID.startswith("MI00"))
def test_setting_fields(self):
for r in self.tabix.fetch(parser=self.parser()):
r.contig = r.contig + "_test_contig"
r.source = "test_source"
r.feature = "test_feature"
r.start += 10
r.end += 10
r.score = 20
r.strand = "+"
r.frame = 0
r.ID = "test"
sr = str(r)
self.assertTrue("test_contig" in sr)
self.assertTrue("test_source" in sr)
self.assertTrue("test_feature" in sr)
self.assertTrue("ID=test" in sr)
def test_setAttribute_makes_changes(self):
r = self.tabix.fetch(parser=self.parser()).next()
r.setAttribute("transcript_id", "abcd")
sr = str(r)
self.assertEqual(r.transcript_id, "abcd")
self.assertTrue("transcript_id=abcd" in sr)
def test_added_attribute_is_output(self):
r = self.tabix.fetch(parser=self.parser()).next()
r.new_int_attribute = 12
self.assertTrue("new_int_attribute=12" in str(r).split("\t")[8])
r.new_float_attribute = 12.0
self.assertTrue("new_float_attribute=12.0" in str(r).split("\t")[8])
r.new_text_attribute = "abc"
self.assertTrue("new_text_attribute=abc" in str(r).split("\t")[8])
if __name__ == "__main__":
unittest.main()
|
