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
|
#!/usr/bin/env python3
"""Execute the tests for the razers3 program.
The golden test outputs are generated by the script generate_outputs.sh.
You have to give the root paths to the source and the binaries as arguments to
the program. These are the paths to the directory that contains the 'projects'
directory.
Usage: run_tests.py SOURCE_ROOT_PATH BINARY_ROOT_PATH
"""
import logging
import os.path
import sys
# Automagically add util/py_lib to PYTHONPATH environment variable.
path = os.path.abspath(os.path.join(os.path.dirname(__file__), '..',
'..', '..', 'util', 'py_lib'))
sys.path.insert(0, path)
import seqan.app_tests as app_tests
class RemovePairIdColumn(object):
"""Transformation to remove pair id column."""
def __init__(self, col_no=8, min_cols=8):
# The index of the column to remove.
self.col_no = col_no
# If there are less than min_col columns then we don't remove.
self.min_cols = min_cols
def apply(self, text, is_left):
lines = text.splitlines(True)
lines2 = []
for line in lines:
cols = line.split('\t')
if len(cols) > self.min_cols:
cols = cols[0:self.col_no] + cols[self.col_no + 1:]
lines2.append('\t'.join(cols))
return ''.join(lines2)
def main(source_base, binary_base, num_threads=1):
"""Main entry point of the script."""
print('Executing test for razers3')
print('===========================')
print()
ph = app_tests.TestPathHelper(
source_base, binary_base,
'apps/razers3/tests') # tests dir
# ============================================================
# Auto-detect the binary path.
# ============================================================
path_to_program = app_tests.autolocateBinary(
binary_base, 'bin', 'razers3')
# ============================================================
# Built TestConf list.
# ============================================================
# Build list with TestConf objects, analoguely to how the output
# was generated in generate_outputs.sh.
conf_list = []
# We prepare a list of transforms to apply to the output files. This is
# used to strip the input/output paths from the programs' output to
# make it more canonical and host independent.
ph.outFile('-') # To ensure that the out path is set.
transforms = [
app_tests.ReplaceTransform(os.path.join(ph.source_base_path, 'apps/razers3/tests') + os.sep, '', right=True),
app_tests.ReplaceTransform(ph.temp_dir + os.sep, '', right=True),
]
# Transforms for SAM output format only. Make VN field of @PG header canonical.
sam_transforms = [app_tests.RegexpReplaceTransform(r'\tVN:[^\t]*', r'\tVN:VERSION', right=True, left=True)]
# Transforms for RazerS output format only. Remove pair id column.
razers_transforms = [RemovePairIdColumn()]
# ============================================================
# Run Adeno Single-End Tests
# ============================================================
# We run the following for all read lengths we have reads for.
for rl in [36, 100]:
# Run with default options.
conf = app_tests.TestConf(
program=path_to_program,
redir_stdout=ph.outFile('se-adeno-reads%d_1-tc%d.stdout' % (rl, num_threads)),
args=['-tc', str(num_threads),
ph.inFile('adeno-genome.fa'),
ph.inFile('adeno-reads%d_1.fa' % rl),
'-o', ph.outFile('se-adeno-reads%d_1-tc%d.razers' % (rl, num_threads))],
to_diff=[(ph.inFile('se-adeno-reads%d_1-tc%d.razers' % (rl, num_threads)),
ph.outFile('se-adeno-reads%d_1-tc%d.razers' % (rl, num_threads))),
(ph.inFile('se-adeno-reads%d_1-tc%d.stdout' % (rl, num_threads)),
ph.outFile('se-adeno-reads%d_1-tc%d.stdout' % (rl, num_threads)))])
conf_list.append(conf)
# Allow indels.
conf = app_tests.TestConf(
program=path_to_program,
redir_stdout=ph.outFile('se-adeno-reads%d_1-ng-tc%d.stdout' % (rl, num_threads)),
args=['-tc', str(num_threads),
'-ng',
ph.inFile('adeno-genome.fa'),
ph.inFile('adeno-reads%d_1.fa' % rl),
'-o', ph.outFile('se-adeno-reads%d_1-ng-tc%d.razers' % (rl, num_threads))],
to_diff=[(ph.inFile('se-adeno-reads%d_1-ng-tc%d.razers' % (rl, num_threads)),
ph.outFile('se-adeno-reads%d_1-ng-tc%d.razers' % (rl, num_threads))),
(ph.inFile('se-adeno-reads%d_1-ng-tc%d.stdout' % (rl, num_threads)),
ph.outFile('se-adeno-reads%d_1-ng-tc%d.stdout' % (rl, num_threads)))])
conf_list.append(conf)
# Compute forward/reverse matches only.
for o in ['-r', '-f']:
conf = app_tests.TestConf(
program=path_to_program,
redir_stdout=ph.outFile('se-adeno-reads%d_1%s-tc%d.stdout' % (rl, o, num_threads)),
args=['-tc', str(num_threads),
o,
ph.inFile('adeno-genome.fa'),
ph.inFile('adeno-reads%d_1.fa' % rl),
'-o', ph.outFile('se-adeno-reads%d_1%s-tc%d.razers' % (rl, o, num_threads))],
to_diff=[(ph.inFile('se-adeno-reads%d_1%s-tc%d.razers' % (rl, o, num_threads)),
ph.outFile('se-adeno-reads%d_1%s-tc%d.razers' % (rl, o, num_threads))),
(ph.inFile('se-adeno-reads%d_1%s-tc%d.stdout' % (rl, o, num_threads)),
ph.outFile('se-adeno-reads%d_1%s-tc%d.stdout' % (rl, o, num_threads)))])
conf_list.append(conf)
# Compute with different identity rates.
for i in range(90, 101):
conf = app_tests.TestConf(
program=path_to_program,
redir_stdout=ph.outFile('se-adeno-reads%d_1-i%d-tc%d.stdout' % (rl, i, num_threads)),
args=['-tc', str(num_threads),
'-i', str(i),
ph.inFile('adeno-genome.fa'),
ph.inFile('adeno-reads%d_1.fa' % rl),
'-o', ph.outFile('se-adeno-reads%d_1-i%d-tc%d.razers' % (rl, i, num_threads))],
to_diff=[(ph.inFile('se-adeno-reads%d_1-i%d-tc%d.razers' % (rl, i, num_threads)),
ph.outFile('se-adeno-reads%d_1-i%d-tc%d.razers' % (rl, i, num_threads))),
(ph.inFile('se-adeno-reads%d_1-i%d-tc%d.stdout' % (rl, i, num_threads)),
ph.outFile('se-adeno-reads%d_1-i%d-tc%d.stdout' % (rl, i, num_threads)))])
conf_list.append(conf)
# Compute with different output formats.
for of, suffix in enumerate(['razers', 'fa', 'eland', 'gff', 'sam', 'afg']):
this_transforms = list(transforms)
if suffix == 'razers':
this_transforms += razers_transforms
elif suffix == 'sam':
this_transforms += sam_transforms
conf = app_tests.TestConf(
program=path_to_program,
redir_stdout=ph.outFile('se-adeno-reads%d_1-of%d-tc%d.stdout' % (rl, of, num_threads)),
args=['-tc', str(num_threads),
ph.inFile('adeno-genome.fa'),
ph.inFile('adeno-reads%d_1.fa' % rl),
'-o', ph.outFile('se-adeno-reads%d_1-of%d-tc%d.%s' % (rl, of, num_threads, suffix))],
to_diff=[(ph.inFile('se-adeno-reads%d_1-of%d-tc%d.%s' % (rl, of, num_threads, suffix)),
ph.outFile('se-adeno-reads%d_1-of%d-tc%d.%s' % (rl, of, num_threads, suffix)),
this_transforms),
(ph.inFile('se-adeno-reads%d_1-of%d-tc%d.stdout' % (rl, of, num_threads)),
ph.outFile('se-adeno-reads%d_1-of%d-tc%d.stdout' % (rl, of, num_threads)),
transforms)])
conf_list.append(conf)
# Compute with different sort orders.
for so in [0, 1]:
conf = app_tests.TestConf(
program=path_to_program,
redir_stdout=ph.outFile('se-adeno-reads%d_1-so%d-tc%d.stdout' % (rl, so, num_threads)),
args=['-tc', str(num_threads),
'-so', str(so),
ph.inFile('adeno-genome.fa'),
ph.inFile('adeno-reads%d_1.fa' % rl),
'-o', ph.outFile('se-adeno-reads%d_1-so%d-tc%d.razers' % (rl, so, num_threads))],
to_diff=[(ph.inFile('se-adeno-reads%d_1-so%d-tc%d.razers' % (rl, so, num_threads)),
ph.outFile('se-adeno-reads%d_1-so%d-tc%d.razers' % (rl, so, num_threads))),
(ph.inFile('se-adeno-reads%d_1-so%d-tc%d.stdout' % (rl, so, num_threads)),
ph.outFile('se-adeno-reads%d_1-so%d-tc%d.stdout' % (rl, so, num_threads)))])
conf_list.append(conf)
# ============================================================
# Run Adeno Paired-End Tests
# ============================================================
# We run the following for all read lengths we have reads for.
for rl in [36, 100]:
# Run with default options.
conf = app_tests.TestConf(
program=path_to_program,
redir_stdout=ph.outFile('pe-adeno-reads%d_2-tc%d.stdout' % (rl, num_threads)),
args=['-tc', str(num_threads),
ph.inFile('adeno-genome.fa'),
ph.inFile('adeno-reads%d_1.fa' % rl),
ph.inFile('adeno-reads%d_2.fa' % rl),
'-o', ph.outFile('pe-adeno-reads%d_2-tc%d.razers' % (rl, num_threads))],
to_diff=[(ph.inFile('pe-adeno-reads%d_2-tc%d.razers' % (rl, num_threads)),
ph.outFile('pe-adeno-reads%d_2-tc%d.razers' % (rl, num_threads)),
razers_transforms),
(ph.inFile('pe-adeno-reads%d_2-tc%d.stdout' % (rl, num_threads)),
ph.outFile('pe-adeno-reads%d_2-tc%d.stdout' % (rl, num_threads)))])
conf_list.append(conf)
# Allow indels.
conf = app_tests.TestConf(
program=path_to_program,
redir_stdout=ph.outFile('pe-adeno-reads%d_2-tc%d.stdout' % (rl, num_threads)),
args=['-tc', str(num_threads),
ph.inFile('adeno-genome.fa'),
ph.inFile('adeno-reads%d_1.fa' % rl),
ph.inFile('adeno-reads%d_2.fa' % rl),
'-o', ph.outFile('pe-adeno-reads%d_2-tc%d.razers' % (rl, num_threads))],
to_diff=[(ph.inFile('pe-adeno-reads%d_2-tc%d.razers' % (rl, num_threads)),
ph.outFile('pe-adeno-reads%d_2-tc%d.razers' % (rl, num_threads)),
razers_transforms),
(ph.inFile('pe-adeno-reads%d_2-tc%d.stdout' % (rl, num_threads)),
ph.outFile('pe-adeno-reads%d_2-tc%d.stdout' % (rl, num_threads)))])
conf_list.append(conf)
# Compute forward/reverse matches only.
for o in ['-r', '-f']:
conf = app_tests.TestConf(
program=path_to_program,
redir_stdout=ph.outFile('pe-adeno-reads%d_2%s-tc%d.stdout' % (rl, o, num_threads)),
args=['-tc', str(num_threads),
o,
ph.inFile('adeno-genome.fa'),
ph.inFile('adeno-reads%d_1.fa' % rl),
ph.inFile('adeno-reads%d_2.fa' % rl),
'-o', ph.outFile('pe-adeno-reads%d_2%s-tc%d.razers' % (rl, o, num_threads))],
to_diff=[(ph.inFile('pe-adeno-reads%d_2%s-tc%d.razers' % (rl, o, num_threads)),
ph.outFile('pe-adeno-reads%d_2%s-tc%d.razers' % (rl, o, num_threads)),
razers_transforms),
(ph.inFile('pe-adeno-reads%d_2%s-tc%d.stdout' % (rl, o, num_threads)),
ph.outFile('pe-adeno-reads%d_2%s-tc%d.stdout' % (rl, o, num_threads)))])
conf_list.append(conf)
# Compute with different identity rates.
for i in range(90, 101):
conf = app_tests.TestConf(
program=path_to_program,
redir_stdout=ph.outFile('pe-adeno-reads%d_2-i%d-tc%d.stdout' % (rl, i, num_threads)),
args=['-tc', str(num_threads),
'-i', str(i),
ph.inFile('adeno-genome.fa'),
ph.inFile('adeno-reads%d_1.fa' % rl),
ph.inFile('adeno-reads%d_2.fa' % rl),
'-o', ph.outFile('pe-adeno-reads%d_2-i%d-tc%d.razers' % (rl, i, num_threads))],
to_diff=[(ph.inFile('pe-adeno-reads%d_2-i%d-tc%d.razers' % (rl, i, num_threads)),
ph.outFile('pe-adeno-reads%d_2-i%d-tc%d.razers' % (rl, i, num_threads)),
razers_transforms),
(ph.inFile('pe-adeno-reads%d_2-i%d-tc%d.stdout' % (rl, i, num_threads)),
ph.outFile('pe-adeno-reads%d_2-i%d-tc%d.stdout' % (rl, i, num_threads)))])
conf_list.append(conf)
# Compute with different output formats.
for of, suffix in enumerate(['razers', 'fa', 'eland', 'gff', 'sam', 'afg']):
this_transforms = list(transforms)
if suffix == 'razers':
this_transforms += razers_transforms
elif suffix == 'sam':
this_transforms += sam_transforms
conf = app_tests.TestConf(
program=path_to_program,
redir_stdout=ph.outFile('pe-adeno-reads%d_2-of%d-tc%d.stdout' % (rl, of, num_threads)),
args=['-tc', str(num_threads),
ph.inFile('adeno-genome.fa'),
ph.inFile('adeno-reads%d_1.fa' % rl),
ph.inFile('adeno-reads%d_2.fa' % rl),
'-o', ph.outFile('pe-adeno-reads%d_2-of%d-tc%d.%s' % (rl, of, num_threads, suffix))],
to_diff=[(ph.inFile('pe-adeno-reads%d_2-of%d-tc%d.%s' % (rl, of, num_threads, suffix)),
ph.outFile('pe-adeno-reads%d_2-of%d-tc%d.%s' % (rl, of, num_threads, suffix)),
this_transforms),
(ph.inFile('pe-adeno-reads%d_2-of%d-tc%d.stdout' % (rl, of, num_threads)),
ph.outFile('pe-adeno-reads%d_2-of%d-tc%d.stdout' % (rl, of, num_threads)),
this_transforms)])
conf_list.append(conf)
# Compute with different sort orders.
for so in [0, 1]:
conf = app_tests.TestConf(
program=path_to_program,
redir_stdout=ph.outFile('pe-adeno-reads%d_2-so%d-tc%d.stdout' % (rl, so, num_threads)),
args=['-tc', str(num_threads),
'-so', str(so),
ph.inFile('adeno-genome.fa'),
ph.inFile('adeno-reads%d_1.fa' % rl),
ph.inFile('adeno-reads%d_2.fa' % rl),
'-o', ph.outFile('pe-adeno-reads%d_2-so%d-tc%d.razers' % (rl, so, num_threads))],
to_diff=[(ph.inFile('pe-adeno-reads%d_2-so%d-tc%d.razers' % (rl, so, num_threads)),
ph.outFile('pe-adeno-reads%d_2-so%d-tc%d.razers' % (rl, so, num_threads)),
razers_transforms),
(ph.inFile('pe-adeno-reads%d_2-so%d-tc%d.stdout' % (rl, so, num_threads)),
ph.outFile('pe-adeno-reads%d_2-so%d-tc%d.stdout' % (rl, so, num_threads)))])
conf_list.append(conf)
# Execute the tests.
failures = 0
for conf in conf_list:
res = app_tests.runTest(conf)
# Output to the user.
print(' '.join(['razers3'] + conf.args), end=' ')
if res:
print('OK')
else:
failures += 1
print('FAILED')
# Cleanup.
ph.deleteTempDir()
print('==============================')
print(' total tests: %d' % len(conf_list))
print(' failed tests: %d' % failures)
print('successful tests: %d' % (len(conf_list) - failures))
print('==============================')
# Compute and return return code.
return failures != 0
if __name__ == '__main__':
sys.exit(app_tests.main(main))
|
