-
Notifications
You must be signed in to change notification settings - Fork 13
/
reads_to_ctg_map.py
367 lines (323 loc) · 12.9 KB
/
reads_to_ctg_map.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
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
#!/usr/bin/env python
'''
Created on Jul 25, 2013
Modified on Oct 30, 2015
@author: ksahlin
@author: sidorov-si
'''
from __future__ import print_function
import argparse
import os
import shutil
import subprocess
import sys
import tempfile
from datetime import datetime
from sys import stdout
import pysam
import re
##
# Converts a sam file to a bam file using pysam.
#
# @param sam_path Path of the .sam file.
# @param bam_path Path of the resulting .bam file.
#
def sam_to_bam(sam_path, bam_path):
sam_file = pysam.Samfile(sam_path, "r")
bam_file = pysam.Samfile(bam_path, "wb", template=sam_file)
for alignment in sam_file:
bam_file.write(alignment)
##
# Maps the given paired end reads using bwa, and writes a
# sorted .bam file in the given output file.
#
# @param pe1_path Path of the first reads.
# @param pe2_path Path of the second reads.
# @param genome_path Path to the reference genome.
# @param output_path Path of the output file without extension ".bam".
#
def bwa_sampe(pe1_path, pe2_path, genome_path, output_path, tmp_dir, bwa_path, clear_tmp, bNoRebuildIndex, threads):
print()
print('Aligning with bwa aln/sampe.')
stdout.flush()
start = datetime.now()
work_dir = tempfile.mkdtemp() if tmp_dir == None else tmp_dir
genome_db = os.path.join(work_dir, "genome")
pe1_output = os.path.join(work_dir, "pe1.sai")
pe2_output = os.path.join(work_dir, "pe2.sai")
bwa_output = os.path.join(work_dir, "output.sam")
stderr_file = open(output_path + '.bwa.1', 'w')
print('Temp directory:', work_dir)
print('Output path: ', output_path)
print('Stderr file: ', output_path + '.bwa.1')
stdout.flush()
if ( bNoRebuildIndex and os.path.isfile(genome_db + ".sa")) :
print('bwa index exists, no need to remake (--norebuildbwaindex specified)', end=' ')
else:
print('Make bwa index...', end=' ')
stdout.flush()
subprocess.check_call([ bwa_path, "index", "-p", genome_db, genome_path ], stderr=stderr_file)
print('Done.')
stdout.flush()
with open(pe1_output, "w") as pe1_file:
print('Align forward reads with bwa aln...', end=' ')
stdout.flush()
subprocess.check_call([ bwa_path, "aln", "-t", threads, genome_db, pe1_path ],
stdout=pe1_file, stderr=stderr_file)
print('Done.')
stdout.flush()
with open(pe2_output, "w") as pe2_file:
print('Align reverse reads with bwa aln...', end=' ')
stdout.flush()
subprocess.check_call([ bwa_path, "aln", "-t", threads, genome_db, pe2_path ],
stdout=pe2_file, stderr=stderr_file)
print('Done.')
stdout.flush()
with open(bwa_output, "w") as bwa_file:
print('Start bwa sampe...', end=' ')
stdout.flush()
subprocess.check_call([ bwa_path, "sampe",
genome_db,
pe1_output, pe2_output,
pe1_path, pe2_path ], stdout=bwa_file, stderr=stderr_file)
print('Done.')
stdout.flush()
elapsed = datetime.now() - start
print('Time elapsed for bwa index and aln/sampe:', elapsed)
print()
print('Convert SAM to BAM...', end=' ')
stdout.flush()
start = datetime.now()
sam_to_bam(bwa_output, bwa_output + ".bam")
if clear_tmp:
os.remove(bwa_output)
elapsed = datetime.now() - start
print('Done.')
print('Time elapsed for SAM to BAM conversion:', elapsed)
print()
print('Sort BAM...', end=' ')
stdout.flush()
start = datetime.now()
pysam.sort(bwa_output + ".bam", output_path)
if clear_tmp:
os.remove(bwa_output + ".bam")
elapsed = datetime.now() - start
print('Done.')
print('Time elapsed for BAM sorting:', elapsed)
print()
print('Index BAM...', end=' ')
stdout.flush()
start = datetime.now()
pysam.index(output_path + '.bam')
elapsed = datetime.now() - start
print('Done.')
print('Time elapsed for BAM indexing:', elapsed)
print()
print('Remove temp files...', end=' ')
stdout.flush()
start = datetime.now()
if bNoRebuildIndex:
print('Keeping genome index files for future use in ' + work_dir, end=' ')
for f in os.listdir(work_dir):
if not re.search("genome", f):
os.remove(os.path.join(work_dir, f))
else:
shutil.rmtree(work_dir)
elapsed = datetime.now() - start
print('Done.')
print('Time elapsed for temp files removing:', elapsed)
stdout.flush()
def bwa_mem(pe1_path, pe2_path, genome_path, threads, output_path, tmp_dir, bwa_path, clear_tmp, bNoRebuildIndex):
print()
print('Aligning with bwa mem.')
stdout.flush()
start = datetime.now()
work_dir = tempfile.mkdtemp() if tmp_dir == None else tmp_dir
genome_db = os.path.join(work_dir, "genome")
pe1_output = os.path.join(work_dir, "pe1.sai")
pe2_output = os.path.join(work_dir, "pe2.sai")
bwa_output = os.path.join(work_dir, "output.sam")
stderr_file = open(output_path + '.bwa.1', 'w')
print('Temp directory:', work_dir)
print('Output path: ', output_path)
print('Stderr file: ', output_path + '.bwa.1')
stdout.flush()
if ( bNoRebuildIndex and os.path.isfile(genome_db + ".sa")) :
print('bwa index exists, no need to remake (--norebuildbwaindex specified)', end=' ')
else:
print('Make bwa index...', end=' ')
stdout.flush()
subprocess.check_call([ bwa_path, "index", "-p", genome_db, genome_path ], stderr=stderr_file)
print('Done.')
stdout.flush()
with open(bwa_output, "w") as bwa_file:
print('Align with bwa mem...', end=' ')
stdout.flush()
subprocess.check_call([ bwa_path, "mem", "-t", threads, "-w", "0", "-O", "99", # new params found by sebastien/guillaume
genome_db, pe1_path, pe2_path ],
stdout=bwa_file,
stderr=stderr_file)
print('Done.')
stdout.flush()
elapsed = datetime.now() - start
print('Time elapsed for bwa index and mem: ', elapsed)
print()
print('Convert SAM to BAM...', end=' ')
stdout.flush()
start = datetime.now()
sam_to_bam(bwa_output, bwa_output + ".bam")
if clear_tmp:
os.remove(bwa_output)
elapsed = datetime.now() - start
print('Done.')
print('Time elapsed for SAM to BAM conversion:', elapsed)
print()
print('Sort BAM...', end=' ')
stdout.flush()
start = datetime.now()
pysam.sort(bwa_output + ".bam", output_path)
if clear_tmp:
os.remove(bwa_output + ".bam")
elapsed = datetime.now() - start
print('Done.')
print('Time elapsed for BAM sorting:', elapsed)
print()
print('Index BAM...', end=' ')
stdout.flush()
start = datetime.now()
pysam.index(output_path + '.bam')
elapsed = datetime.now() - start
print('Done.')
print('Time elapsed for BAM indexing:', elapsed)
print()
print('Remove temp files...', end=' ')
stdout.flush()
start = datetime.now()
if bNoRebuildIndex:
print('Keeping genome index files for future use in ' + work_dir, end=' ')
for f in os.listdir(work_dir):
if not re.search("genome", f):
os.remove(os.path.join(work_dir, f))
else:
shutil.rmtree(work_dir)
elapsed = datetime.now() - start
print('Done.')
print('Time elapsed for temp files removing:', elapsed)
stdout.flush()
def map_single_reads(pe_path, genome_path, output_path, bwa_path, threads):
print()
print('Aligning with bwa aln/samse.')
stdout.flush()
start = datetime.now()
work_dir = tempfile.mkdtemp()
genome_db = os.path.join(work_dir, "genome")
pe_output = os.path.join(work_dir, "pe.sai")
bwa_output = os.path.join(work_dir, "output.sam")
print('Temp directory:', work_dir)
print('Output path: ', output_path)
print('Stderr file: /dev/null')
stdout.flush()
null = open("/dev/null")
if ( bNoRebuildIndex and os.path.isfile(genome_db + ".sa")) :
print('bwa index exists, no need to remake (--norebuildbwaindex specified)', end=' ')
else:
print('Make bwa index...', end=' ')
stdout.flush()
subprocess.check_call([ bwa_path, "index", "-p", genome_db, genome_path ], stderr=stderr_file)
print('Done.')
stdout.flush()
with open(pe_output, "w") as pe_file:
print('Align with bwa aln...', end=' ')
stdout.flush()
subprocess.check_call([ bwa_path, "aln", "-t", threads, genome_db, pe_path ], stdout=pe_file, stderr=null)
print('Done.')
stdout.flush()
with open(bwa_output, "w") as bwa_file:
print('Start bwa samse...', end=' ')
stdout.flush()
subprocess.check_call([ bwa_path, "samse",
"-r", "@RG\tID:ILLUMINA\tSM:48_2\tPL:ILLUMINA\tLB:LIB1",
genome_db,
pe_output,
pe_path ], stdout=bwa_file, stderr=null)
print('Done.')
stdout.flush()
elapsed = datetime.now() - start
print('Time elapsed for bwa index and aln/samse:', elapsed)
print()
print('Copy the result to the output directory and remove temp files...', end=' ')
stdout.flush()
start = datetime.now()
shutil.move(bwa_output, output_path)
if bNoRebuildIndex:
print('Keeping genome index files for future use in ' + work_dir, end=' ')
for f in os.listdir(work_dir):
if not re.search("genome", f):
os.remove(os.path.join(work_dir, f))
else:
shutil.rmtree(work_dir)
elapsed = datetime.now() - start
print('Done.')
print('Time elapsed for copying result to the output directory and removing temp files:', elapsed)
stdout.flush()
if __name__ == '__main__':
parser = argparse.ArgumentParser(description="Maps the given reads with bwa.")
parser.add_argument('pe1_path', type=str, help='Path to the first reads in a read pair (if paired reads). Just the reads if single reads')
parser.add_argument('pe2_path', type=str, nargs='?', default=False, help='Path to the second pairs. Leave unspecified if single reads.')
parser.add_argument('genome_path', type=str, help='Path to the reference genome/contigs.')
parser.add_argument('output_path', type=str, help='Output path of resulting .bam and .bai file.')
parser.add_argument('--tmp_path', type=str, required=False, help='Output path of temporary files.')
parser.add_argument('--bwa_path', type=str, default='bwa', required=False, help='Path to bwa binary with bwa binary name at the end.')
parser.add_argument('--threads', type=str, default='8', required=False, help='Number of threads for bwa mem.')
parser.add_argument('--clear', action="store_true", required=False,
help='Remove SAM file when BAM is already created, and remove BAM file when sorted BAM is already created.')
parser.add_argument('--nomem', action="store_true", required=False,
help='bwa mem default, If flag specified the script uses old bwa algorithm with "aln" and "sampe". ')
parser.add_argument('--norebuildindex', action="store_true", required=False,
help='Do not rebuild bwa index if it already exists in the tmp_dir.')
args = parser.parse_args()
tmp_path = args.tmp_path
if tmp_path != None and not os.path.exists(tmp_path):
os.makedirs(tmp_path)
output_path = args.output_path
if not os.path.exists(output_path):
os.makedirs(output_path)
print()
print('pe1_path:', args.pe1_path)
print('pe2_path:', args.pe2_path)
print('genome_path:', args.genome_path)
print('output_path:', output_path)
if tmp_path != None:
print("tmp_path:", tmp_path)
print('bwa path:', args.bwa_path)
print('number of threads:', args.threads)
print('Remove temp SAM and BAM files:', end=' ')
if args.clear:
print('Yes')
else:
print('No')
print('Use bwa aln and sampe instead of bwa mem:', end=' ')
if args.nomem:
print('Yes')
else:
print('No')
print('Do not rebuild bwa index if already exists in tmp dir:', end=' ')
if args.norebuildindex:
print('Yes')
else:
print('No')
stdout.flush()
print()
print('Start processing.')
stdout.flush()
if args.pe2_path and args.nomem:
bwa_sampe(args.pe1_path, args.pe2_path, args.genome_path, output_path, tmp_path,
args.bwa_path, args.clear, args.norebuildindex, args.threads)
elif args.pe2_path:
bwa_mem(args.pe1_path, args.pe2_path, args.genome_path, args.threads, output_path,
tmp_path, args.bwa_path, args.clear, args.norebuildindex)
else:
map_single_reads(args.pe1_path, args.genome_path, args.output_path, args.bwa_path, args.norebuildindex, args.threads)
print()
print('Processing is finished.')
stdout.flush()