-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathtest_variants.py
296 lines (269 loc) · 9.76 KB
/
test_variants.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
# Copyright (c) 2015. Mount Sinai School of Medicine
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import absolute_import
import subprocess
import warnings
import logging
import pandas
import numpy
from nose.tools import eq_
from varlens.commands import variants
from . import data_path, run_and_parse_csv, cols_concat, temp_file
def run(args):
logging.info("Running with args: " + ' '.join(args))
return run_and_parse_csv(variants.run, args)
reference_fasta = data_path("chr22.no_line_wrap.fa")
expected_cols = [
"genome", "contig", "interbase_start", "interbase_end", "ref", "alt",
]
def test_basic():
result = run([
data_path("CELSR1/vcfs/vcf_1.vcf"),
"--genome", "b37",
])
eq_(sorted(cols_concat(result, expected_cols)), sorted({
"GRCh37-22-46931059-46931060-A-C",
"GRCh37-22-21829554-21829555-T-G",
"GRCh37-22-46931061-46931062-G-A",
"GRCh37-22-50636217-50636218-A-C",
"GRCh37-22-50875932-50875933-A-C",
}))
def test_genes_and_effects():
result = run([
data_path("CELSR1/vcfs/vcf_1.vcf"),
"--genome", "b37",
"--include-effect",
"--include-gene",
"--rename-column", "gene", "genez",
])
eq_(sorted(cols_concat(result, expected_cols + ["effect", "genez"])),
sorted({
'GRCh37-22-21829554-21829555-T-G-non-coding-transcript-PI4KAP2',
'GRCh37-22-46931059-46931060-A-C-p.S670A-CELSR1',
'GRCh37-22-46931061-46931062-G-A-p.S669F-CELSR1',
'GRCh37-22-50636217-50636218-A-C-intronic-TRABD',
'GRCh37-22-50875932-50875933-A-C-splice-acceptor-PPP6R2',
}))
def test_context():
result = run([
data_path("CELSR1/vcfs/vcf_1.vcf"),
"--genome", "b37",
"--include-context",
"--context-num-bases", "5",
"--reference", reference_fasta,
])
eq_(sorted(cols_concat(result,
expected_cols + [
"context_5_prime", "context_3_prime", "context_mutation"])),
sorted({
"GRCh37-22-46931059-46931060-A-C-GCTCC-CCACC-T>G",
"GRCh37-22-21829554-21829555-T-G-CATGA-AGTGA-T>G",
"GRCh37-22-46931061-46931062-G-A-GAGCT-CTCCA-C>T",
"GRCh37-22-50636217-50636218-A-C-AGGGA-GGGCA-T>G",
"GRCh37-22-50875932-50875933-A-C-AGGCC-GGGAG-T>G",
}))
def test_mhc_binding_affinity():
# If netMHC is not installed, we skip this test
try:
# If this succeeds (no exception), we do nothing.
subprocess.call(
"netMHC", stdout=subprocess.PIPE, stderr=subprocess.PIPE)
except OSError:
warnings.warn("netMHC not installed, skipping mhc binding test")
return
with temp_file(".csv") as out_csv:
run([
data_path("CELSR1/vcfs/vcf_1.vcf"),
"--genome", "b37",
"--include-mhc-binding",
"--hla", "A:02:01 A:02:02",
"--out", out_csv,
])
['GRCh37-22-21829554-21829555-T-G-nan-nan',
'GRCh37-22-46931059-46931060-A-C-377.3-A:02:02',
'GRCh37-22-46931061-46931062-G-A-77.2-A:02:02',
'GRCh37-22-50636217-50636218-A-C-nan-nan',
'GRCh37-22-50875932-50875933-A-C-nan-nan']
results = pandas.read_csv(out_csv).set_index(expected_cols)
assert numpy.isnan(results.loc[
("GRCh37", 22, 21829554, 21829555, "T", "G")].binding_affinity)
assert numpy.isnan(results.loc[
("GRCh37", 22, 21829554, 21829555, "T", "G")].binding_allele)
eq_(results.loc[
("GRCh37", 22, 46931059, 46931060, "A", "C")].binding_allele,
"A:02:02")
eq_(results.loc[
("GRCh37", 22, 46931061, 46931062, "G", "A")].binding_allele,
"A:02:02")
def test_read_evidence():
result = run([
data_path("CELSR1/vcfs/vcf_1.vcf"),
"--include-read-evidence",
"--reads", data_path("CELSR1/bams/bam_0.bam"),
"--genome", "b37",
])
allele_groups = ["num_ref", "num_alt", "total_depth"]
for allele_group in allele_groups:
result[allele_group] = result[allele_group].astype(int)
eq_(cols_concat(
result,
["contig", "interbase_start"] + allele_groups),
{
'22-50636217-0-0-0',
'22-50875932-0-0-0',
'22-21829554-0-0-0',
"22-46931059-50-0-50",
"22-46931061-51-0-51",
})
# Same thing but with chunk rows = 1
with temp_file(".csv") as out_csv:
run([
data_path("CELSR1/vcfs/vcf_1.vcf"),
"--include-read-evidence",
"--reads", data_path("CELSR1/bams/bam_0.bam"),
"--genome", "b37",
"--chunk-rows", "1",
"--out", out_csv,
])
result = pandas.read_csv(out_csv)
allele_groups = ["num_ref", "num_alt", "total_depth"]
for allele_group in allele_groups:
result[allele_group] = result[allele_group].astype(int)
eq_(cols_concat(
result,
["contig", "interbase_start"] + allele_groups),
{
'22-50636217-0-0-0',
'22-50875932-0-0-0',
'22-21829554-0-0-0',
"22-46931059-50-0-50",
"22-46931061-51-0-51",
})
result = run([
"--include-read-evidence",
"--reads", data_path("gatk_mini_bundle_extract.bam"),
"--read-source-name", "foo",
"--single-variant", "chr20:10008951", "C", "A",
"--genome", "b37",
])
for allele_group in allele_groups:
result[allele_group] = result[allele_group].astype(int)
eq_(cols_concat(result, expected_cols + allele_groups),
{"GRCh37-20-10008950-10008951-C-A-4-1-5"})
result = run([
"--include-read-evidence",
"--reads", data_path("gatk_mini_bundle_extract.bam"),
"--read-source-name", "foo",
"--single-variant", "chr20:10008951", "C", "A",
"--genome", "b37",
"--is-reverse",
])
for allele_group in allele_groups:
result[allele_group] = result[allele_group].astype(int)
eq_(cols_concat(result, expected_cols + allele_groups),
{"GRCh37-20-10008950-10008951-C-A-1-0-1"})
def test_filtering():
result = run([
data_path("CELSR1/vcfs/vcf_1.vcf"),
"--genome", "b37",
"--ref", "A",
])
eq_(sorted(cols_concat(result, expected_cols)), sorted({
"GRCh37-22-46931059-46931060-A-C",
"GRCh37-22-50636217-50636218-A-C",
"GRCh37-22-50875932-50875933-A-C",
}))
result = run([
data_path("CELSR1/vcfs/vcf_1.vcf"),
"--genome", "b37",
"--ref", "A",
"--variant-locus", "22:50636218",
])
eq_(sorted(cols_concat(result, expected_cols)), sorted({
"GRCh37-22-50636217-50636218-A-C",
}))
result = run([
data_path("CELSR1/vcfs/vcf_1.vcf"),
data_path("CELSR1/vcfs/vcf_2.vcf"),
"--alt", "C", "G",
"--genome", "b37"
])
eq_(sorted(cols_concat(result, expected_cols)), sorted({
"GRCh37-22-21829554-21829555-T-G",
"GRCh37-22-45309892-45309893-T-G",
"GRCh37-22-46931059-46931060-A-C",
"GRCh37-22-50636217-50636218-A-C",
"GRCh37-22-50875932-50875933-A-C",
}))
'''
def test_fields():
result = run([
"--field",
"foo:ref.lower()",
"gene_names[0]",
"--variants", data_path("CELSR1/vcfs/vcf_1.vcf"),
"--variant-filter", "ref=='A'",
"--variant-genome", "b37"
])
eq_(sorted(cols_concat(result, expected_cols + ["foo", "gene_names[0]"])),
sorted({
"GRCh37-22-46931059-46931060-A-C-a-CELSR1",
"GRCh37-22-50636217-50636218-A-C-a-TRABD",
"GRCh37-22-50875932-50875933-A-C-a-PPP6R2",
}))
'''
def test_round_trip():
with temp_file(".csv") as out_csv:
variants.run([
data_path("CELSR1/vcfs/vcf_1.vcf"),
"--out", out_csv,
"--genome", "b37",
"--ref", "A",
"--include-gene",
])
result1 = pandas.read_csv(out_csv)
eq_(sorted(cols_concat(
result1, expected_cols + ["gene"])),
sorted({
"GRCh37-22-46931059-46931060-A-C-CELSR1",
"GRCh37-22-50636217-50636218-A-C-TRABD",
"GRCh37-22-50875932-50875933-A-C-PPP6R2",
}))
result2 = run([
out_csv,
"--include-gene",
])
eq_(sorted(cols_concat(
result2,
expected_cols + ["gene"])),
sorted({
"GRCh37-22-46931059-46931060-A-C-CELSR1",
"GRCh37-22-50636217-50636218-A-C-TRABD",
"GRCh37-22-50875932-50875933-A-C-PPP6R2",
}))
def test_distinct_variants():
result = run([
data_path("CELSR1/vcfs/vcf_1.vcf"),
data_path("CELSR1/vcfs/vcf_1.vcf"),
"--genome", "b37",
"--ref", "A", "T",
"--variant-source-name", "first", "second",
])
eq_(sorted(cols_concat(result, expected_cols + ["sources"])),
sorted({
"GRCh37-22-21829554-21829555-T-G-first second",
"GRCh37-22-46931059-46931060-A-C-first second",
"GRCh37-22-50636217-50636218-A-C-first second",
"GRCh37-22-50875932-50875933-A-C-first second",
}))