-
Notifications
You must be signed in to change notification settings - Fork 17
/
leviosam-test.py
347 lines (308 loc) · 11.6 KB
/
leviosam-test.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
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
import subprocess
import sys
import unittest
import pysam
LEVIOSAM = "../leviosam2"
WG_MAJOR_LFT = "major.lft"
BWA_SE_H38 = "bwa-se-grch38.bam"
BWA_SE_MAJOR = "bwa-se-major.bam"
BWA_SE_OUT_PREFIX = "bwa-se-major-lifted"
BT2_SE_H38 = "bt2-se-grch38.bam"
BT2_SE_MAJOR = "bt2-se-major.bam"
BT2_SE_OUT_PREFIX = "bt2-se-major-lifted"
BWA_PE_H38 = "bwa-pe-grch38.bam"
BWA_PE_MAJOR = "bwa-pe-major.bam"
BWA_PE_OUT_PREFIX = "bwa-pe-major-lifted"
BT2_PE_H38 = "bt2-pe-grch38.bam"
BT2_PE_MAJOR = "bt2-pe-major.bam"
BT2_PE_OUT_PREFIX = "bt2-pe-major-lifted"
OVRLP_LFT = "overlapping_example.lft"
OVRLP_GOLD = "overlapping_example-lifted-gold.bam"
OVRLP_SAM = "overlapping_example.bam"
OVRLP_OUT_PREFIX = "overlapping_example-lifted"
params = [
{
"name": "BWA-SE",
"gold": BWA_SE_H38,
"sam": BWA_SE_MAJOR,
"out_prefix": BWA_SE_OUT_PREFIX,
"lft": WG_MAJOR_LFT,
"mode": "SE",
},
{
"name": "BT2-PE",
"gold": BT2_SE_H38,
"sam": BT2_SE_MAJOR,
"out_prefix": BT2_SE_OUT_PREFIX,
"lft": WG_MAJOR_LFT,
"mode": "SE",
},
{
"name": "BWA-PE",
"gold": BWA_PE_H38,
"sam": BWA_PE_MAJOR,
"out_prefix": BWA_PE_OUT_PREFIX,
"lft": WG_MAJOR_LFT,
"mode": "PE",
},
{
"name": "BT2-PE",
"gold": BT2_PE_H38,
"sam": BT2_PE_MAJOR,
"out_prefix": BT2_PE_OUT_PREFIX,
"lft": WG_MAJOR_LFT,
"mode": "PE",
},
{
"name": "OVRLP",
"gold": OVRLP_GOLD,
"sam": OVRLP_SAM,
"out_prefix": OVRLP_OUT_PREFIX,
"lft": OVRLP_LFT,
"mode": "SE",
},
]
class SamProcessing(unittest.TestCase):
@classmethod
def setUpClass(cls):
for param in params:
process = subprocess.Popen(
[
LEVIOSAM,
"lift",
"-l",
param["lft"],
"-a",
param["sam"],
"-p",
param["out_prefix"],
"-O",
"bam",
],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
stdout, stderr = process.communicate()
@classmethod
def tearDownClass(cls):
for param in params:
cmd = f'rm {param["out_prefix"]}.bam; rm {param["out_prefix"]}-RG.bam'
process_rm = subprocess.Popen(cmd, stdout=subprocess.PIPE, shell=True)
stdout, stderr = process_rm.communicate()
print(
f'Cleaned up {param["out_prefix"]}.bam and {param["out_prefix"]}-RG.bam'
)
"""Read a SAM file as a dict."""
def read_sam_file_as_dict(self, fn):
d = {}
print(fn, file=sys.stderr)
f = pysam.AlignmentFile(fn)
for rec in f:
qname = rec.query_name
if not d.get(qname):
d[qname] = [None, None]
if (not rec.is_paired) or rec.is_read1:
d[qname][0] = rec
else:
d[qname][1] = rec
return d
"""Test if the lifted fields are identical to the alignments against standard reference.
This is not globally true, since some reads could be mapped to other regions in an augmented
reference, but we only provide cases where mapping fields are not altered.
"""
def test_identical_fields(self):
def compare_fields(lift, gold):
self.assertEqual(lift.reference_start, gold.reference_start)
self.assertEqual(lift.reference_name, gold.reference_name)
self.assertEqual(lift.cigarstring, gold.cigarstring)
# self.assertEqual(lift.next_reference_start, gold.next_reference_start)
self.assertEqual(lift.next_reference_name, gold.next_reference_name)
self.assertEqual(lift.template_length, gold.template_length)
self.assertEqual(lift.query_sequence, gold.query_sequence)
self.assertEqual(lift.query_qualities, gold.query_qualities)
for i, param in enumerate(params):
assert param["mode"] in ["SE", "PE"]
# Each subtest here is one parameter set (e.g. BWA-SE, BT2-PE)
with self.subTest(aln_param_idx=param):
dict_lifted = self.read_sam_file_as_dict(f'{param["out_prefix"]}.bam')
dict_gold = self.read_sam_file_as_dict(f'{param["gold"]}')
for k in dict_lifted.keys():
# Single-end
if param["mode"] == "SE":
compare_fields(dict_lifted[k][0], dict_gold[k][0])
# Paired-end
elif param["mode"] == "PE":
compare_fields(dict_lifted[k][0], dict_gold[k][0])
compare_fields(dict_lifted[k][1], dict_gold[k][1])
""" Test if the lifted SAM file passes `picard ValidateSamFile`. """
def test_picard_validate(self):
for i, param in enumerate(params):
with self.subTest(aln_param_idx=i):
process = subprocess.Popen(
[
"picard",
f'AddOrReplaceReadGroups I={param["out_prefix"]}.bam \
O={param["out_prefix"]}-RG.bam \
RGID=test RGLB=test RGPL=illumina RGSM=test RGPU=TEST',
],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
stdout, stderr = process.communicate()
process2 = subprocess.Popen(
[
"picard",
f'ValidateSamFile I={param["out_prefix"]}-RG.bam MODE= VERBOSE',
],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
stdout, stderr = process2.communicate()
self.assertNotIn(
"ERROR", stderr.decode(), msg='Check "No errors found"'
)
print(
f'[PASSED] Picard AddOrReplaceReadGroups & ValidateSamFile ({param["out_prefix"]}.bam)'
)
BT2_PE_CHM13 = "bt2-pe-chm13_v1.1_hg2y.bam"
BT2_SE_CHM13 = "bt2-se-chm13_v1.1_hg2y.bam"
BWA_PE_CHM13 = "bwa-pe-chm13_v1.1_hg2y.bam"
BWA_SE_CHM13 = "bwa-se-chm13_v1.1_hg2y.bam"
MM2_HIFI_1 = "mm2-test1.sam"
MM2_HIFI_2 = "mm2-test2.sam"
CLFT_CHM13_TO_H38 = "chm13_v1.1_hg2Y-grch38.clft"
PE_CHAIN_TESTS = {BT2_PE_CHM13: BT2_PE_H38, BWA_PE_CHM13: BWA_PE_H38}
SE_CHAIN_TESTS = {BT2_SE_CHM13: BT2_SE_H38, BWA_SE_CHM13: BWA_SE_H38}
class Chain(unittest.TestCase):
def compare_aln(self, gold, result):
if (
gold.is_unmapped
or result.is_unmapped
or gold.is_supplementary
or result.is_supplementary
):
return
self.assertLess(abs(gold.reference_start - result.reference_start), 5)
self.assertEqual(gold.reference_name, result.reference_name)
self.assertEqual(gold.next_reference_name, result.next_reference_name)
self.assertEqual(gold.query_sequence, result.query_sequence)
self.assertEqual(gold.query_qualities, result.query_qualities)
def read_single_end(self, fn):
f = pysam.AlignmentFile(fn)
reads1 = {}
for r in f:
reads1[r.query_name] = r
return reads1
def test_single_end_chain(self):
for i, (orig, gold) in enumerate(SE_CHAIN_TESTS.items()):
lifted_pre = orig + "-lifted"
lifted_fn = lifted_pre + ".bam"
process = subprocess.Popen(
[
LEVIOSAM,
"lift",
"-C",
CLFT_CHM13_TO_H38,
"-a",
orig,
"-p",
lifted_pre,
"-O",
"bam",
],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
stdout, stderr = process.communicate()
reads_gold1 = self.read_single_end(gold)
reads_lift1 = self.read_single_end(lifted_fn)
for _, (name, v) in enumerate(reads_gold1.items()):
result = reads_lift1.get(name)
self.assertFalse(result is None)
self.compare_aln(v, result)
cmd = f"rm {lifted_fn}"
process_rm = subprocess.Popen(cmd, stdout=subprocess.PIPE, shell=True)
stdout, stderr = process_rm.communicate()
def read_paired_end(self, fn):
f = pysam.AlignmentFile(fn)
reads1 = {}
reads2 = {}
for r in f:
if r.is_read1:
reads1[r.query_name] = r
elif r.is_read2:
reads2[r.query_name] = r
else:
print(f"Invalid record in {fn}. Please check")
print(r)
exit(1)
return reads1, reads2
def test_paired_end_chain(self):
for i, (orig, gold) in enumerate(PE_CHAIN_TESTS.items()):
lifted_pre = orig + "-lifted"
lifted_fn = lifted_pre + ".bam"
process = subprocess.Popen(
[
LEVIOSAM,
"lift",
"-C",
CLFT_CHM13_TO_H38,
"-a",
orig,
"-p",
lifted_pre,
"-O",
"bam",
],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
stdout, stderr = process.communicate()
reads_gold1, reads_gold2 = self.read_paired_end(gold)
reads_lift1, reads_lift2 = self.read_paired_end(lifted_fn)
for _, (name, v) in enumerate(reads_gold1.items()):
result = reads_lift1.get(name)
self.assertFalse(result is None)
self.compare_aln(v, result)
for _, (name, v) in enumerate(reads_gold2.items()):
result = reads_lift2.get(name)
self.assertFalse(result is None)
self.compare_aln(v, result)
cmd = f"rm {lifted_fn}"
process_rm = subprocess.Popen(cmd, stdout=subprocess.PIPE, shell=True)
stdout, stderr = process_rm.communicate()
def test_validate_long_reads(self):
for fn in [MM2_HIFI_1, MM2_HIFI_2]:
process = subprocess.Popen(
[
LEVIOSAM,
"lift",
"-C",
CLFT_CHM13_TO_H38,
"-a",
fn,
"-p",
fn + "-lifted",
"-O",
"bam",
],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
stdout, stderr = process.communicate()
process2 = subprocess.Popen(
["picard", f"ValidateSamFile I={fn}-lifted.bam MODE= VERBOSE"],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
stdout, stderr = process2.communicate()
self.assertNotIn("ERROR", stderr.decode(), msg='Check "No errors found"')
cmd = f"rm {fn}-lifted.bam"
process_rm = subprocess.Popen(cmd, stdout=subprocess.PIPE, shell=True)
stdout, stderr = process_rm.communicate()
print(f"[PASSED] Picard ValidateSamFile ({fn})")
if __name__ == "__main__":
if len(sys.argv) > 1:
LEVIOSAM = sys.argv.pop()
print(f"Use the leviosam software at {LEVIOSAM}", file=sys.stderr)
unittest.main()