forked from amathelier/DNAshapedTFBS
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathDNAshapedTFBS_argsParsing.py
executable file
·565 lines (543 loc) · 32.5 KB
/
DNAshapedTFBS_argsParsing.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
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
from DNAshapedTFBS_classification import dna_shape_and_tffm_train_classifier
from DNAshapedTFBS_classification import dna_shape_and_pssm_train_classifier
from DNAshapedTFBS_classification import dna_shape_and_binary_train_classifier
from DNAshapedTFBS_classification import custom_train_classifier
from DNAshapedTFBS_classification import dna_shape_and_tffm_apply_classifier
from DNAshapedTFBS_classification import dna_shape_and_pssm_apply_classifier
from DNAshapedTFBS_classification import dna_shape_and_binary_apply_classifier
from DNAshapedTFBS_classification import custom_apply_classifier
from DNAshapedTFBS_classification import custom_train_and_validate_classifier
# TODO: change 2nd order nargs to 4 where appropriate when we re-download MGW2
def pssm_train_args_parsing(subparsers):
""" Train the PSSM + DNA shape classifier. """
help_str = "Train the PSSM + DNA shape classifier."
parser_t = subparsers.add_parser('trainPSSM', help=help_str)
jaspar_grp = parser_t.add_mutually_exclusive_group(required=True)
help_str = 'JASPAR ID corresponding to the TF '
help_str += 'binding profile to be used.'
jaspar_grp.add_argument('-j', '--jaspar', type=str, dest='jasparid',
action='store', help=help_str)
help_str = 'JASPAR file containing the TF binding profile in the '
help_str += 'JASPAR format.'
jaspar_grp.add_argument('-f', '--jasparfile', type=str, dest='jasparfile',
action='store', help=help_str)
help_str = 'Input fasta file containing the foreground sequences.'
parser_t.add_argument('-i', '--fg_fasta', required=True, type=str,
dest='fg_fasta', action='store', help=help_str)
help_str = 'Input bed file w/ positions of foreground sequences.'
parser_t.add_argument('-I', '--fg_bed', required=True, type=str,
dest='fg_bed', action='store', help=help_str)
help_str = 'Input fasta containing the background sequences.'
parser_t.add_argument('-b', '--bg_fasta', required=True, type=str,
dest='bg_fasta', action='store', help=help_str)
help_str = 'Input bed file w/ positions of background sequences.'
parser_t.add_argument('-B', '--bg_bed', required=True, type=str,
dest='bg_bed', action='store', help=help_str)
parser_t.add_argument('-o', '--outfile', required=True, type=str,
dest='output', action='store',
help='Output base name (.pkl will be added).')
help_str = 'List of 1st-order bigWig files as\n'
help_str += '-1 HelT ProT MGW Roll'
help_str += ' (note that we assume such an order)'
parser_t.add_argument('-1', '--1storder', required=True, type=str,
dest='shape_first_order', action='store', nargs=4,
help=help_str)
help_str = 'List of 2nd-order bigWig files as\n'
help_str += '-2 HelT2 ProT2 MGW2 Roll2'
help_str += ' (note that we assume such an order)'
parser_t.add_argument('-2', '--2ndorder', required=False, type=str,
dest='shape_second_order', action='store', nargs=4,
default=[], help=help_str)
parser_t.add_argument('-n', '--scaled', required=False, dest='scaled',
action='store_true', default=False,
help='Scale DNAshape values in [0, 1]')
help_str = 'Extension to be considered around TFBSs with DNAshapes'
help_str += ' (default:0).'
parser_t.add_argument('-e', '--extension', required=False, type=int,
dest='extension', action='store', default=0,
help=help_str)
parser_t.set_defaults(func=dna_shape_and_pssm_train_classifier)
def pssm_apply_args_parsing(subparsers):
""" Apply the PSSM + DNA shape classifier. """
help_str = 'Apply the PSSM + DNA shape classifier.'
parser_a = subparsers.add_parser('applyPSSM', help=help_str)
jaspar_grp = parser_a.add_mutually_exclusive_group(required=True)
help_str = 'JASPAR ID corresponding to the TF '
help_str += 'binding profile to be used.'
jaspar_grp.add_argument('-j', '--jaspar', type=str, dest='jasparid',
action='store', help=help_str)
help_str = 'JASPAR file containing the TF binding profile in the '
help_str += 'JASPAR format.'
jaspar_grp.add_argument('-f', '--jasparfile', type=str, dest='jasparfile',
action='store', help=help_str)
help_str = 'Input fasta file containing the sequences.'
parser_a.add_argument('-i', '--input_fasta', required=True, type=str,
dest='in_fasta', action='store', help=help_str)
help_str = 'Input bed file w/ positions of the sequences.'
parser_a.add_argument('-I', '--input_bed', required=True, type=str,
dest='in_bed', action='store', help=help_str)
parser_a.add_argument('-c', '--classifier', required=True, type=str,
dest='classifier', action='store',
help='Classifier (.pkl file).')
parser_a.add_argument('-o', '--outfile', required=True, type=str,
dest='output', action='store',
help='Output result file')
help_str = 'List of 1st-order bigWig files as\n'
help_str += '-1 HelT ProT MGW Roll'
help_str += ' (note that we assume such an order)'
parser_a.add_argument('-1', '--1storder', required=True, type=str,
dest='shape_first_order', action='store', nargs=4,
help=help_str)
help_str = 'List of 2nd-order bigWig files as\n'
help_str += '-2 HelT2 ProT2 MGW2 Roll2'
help_str += ' (note that we assume such an order)'
parser_a.add_argument('-2', '--2ndorder', required=False, type=str,
dest='shape_second_order', action='store', nargs=4,
default=[], help=help_str)
parser_a.add_argument('-n', '--scaled', required=False, dest='scaled',
action='store_true', default=False,
help='Scale DNAshape values in [0, 1]')
help_str = 'Extension to be considered around TFBSs with DNAshapes'
help_str += ' (default:0).'
parser_a.add_argument('-e', '--extension', required=False, type=int,
dest='extension', action='store', default=0,
help=help_str)
help_str = 'Probability threshold to predict a hit (default=0.5).'
parser_a.add_argument('-v', '--threshold', required=False,
dest='threshold', action='store', default=0.5,
type=float, help=help_str)
parser_a.set_defaults(func=dna_shape_and_pssm_apply_classifier)
def tffm_train_args_parsing(subparsers):
""" Train the TFFM + DNA shape classifier. """
help_str = "Train the TFFM + DNA shape classifier."
parser_t = subparsers.add_parser('trainTFFM', help=help_str)
parser_t.add_argument('-T', '--tffmfile', required=True, dest='tffm_file',
action='store', type=str, help='TFFM XML file.')
parser_t.add_argument('-t', '--tffm_kind', required=False,
dest='tffm_kind', action='store', type=str,
choices=['first_order', 'detailed'],
default='first_order',
help='TFFM kind ("first_order" or "detailed").')
help_str = 'Input fasta file containing the foreground sequences.'
parser_t.add_argument('-i', '--fg_fasta', required=True, type=str,
dest='fg_fasta', action='store', help=help_str)
help_str = 'Input bed file w/ positions of foreground sequences.'
parser_t.add_argument('-I', '--fg_bed', required=True, type=str,
dest='fg_bed', action='store', help=help_str)
help_str = 'Input fasta containing the background sequences.'
parser_t.add_argument('-b', '--bg_fasta', required=True, type=str,
dest='bg_fasta', action='store', help=help_str)
help_str = 'Input bed file w/ positions of background sequences.'
parser_t.add_argument('-B', '--bg_bed', required=True, type=str,
dest='bg_bed', action='store', help=help_str)
parser_t.add_argument('-o', '--outfile', required=True, type=str,
dest='output', action='store',
help='Output base name (.pkl will be added).')
help_str = 'List of 1st-order bigWig files as\n'
help_str += '-1 HelT ProT MGW Roll'
help_str += ' (note that we assume such an order)'
parser_t.add_argument('-1', '--1storder', required=True, type=str,
dest='shape_first_order', action='store', nargs=4,
help=help_str)
help_str = 'List of 2nd-order bigWig files as\n'
help_str += '-2 HelT2 ProT2 MGW2 Roll2'
help_str += ' (note that we assume such an order)'
parser_t.add_argument('-2', '--2ndorder', required=False, type=str,
dest='shape_second_order', action='store', nargs=4,
default=[], help=help_str)
parser_t.add_argument('-n', '--scaled', required=False, dest='scaled',
action='store_true', default=False,
help='Scale DNAshape values in [0, 1]')
help_str = 'Extension to be considered around TFBSs with DNAshapes'
help_str += ' (default:0).'
parser_t.add_argument('-e', '--extension', required=False, type=int,
dest='extension', action='store', default=0,
help=help_str)
parser_t.set_defaults(func=dna_shape_and_tffm_train_classifier)
def tffm_apply_args_parsing(subparsers):
""" Apply the TFFM + DNA shape classifier. """
help_str = 'Apply the TFFM + DNA shape classifier.'
parser_a = subparsers.add_parser('applyTFFM', help=help_str)
parser_a.add_argument('-T', '--tffmfile', required=True, dest='tffm_file',
action='store', type=str, help='TFFM XML file.')
parser_a.add_argument('-t', '--tffm_kind', required=False,
dest='tffm_kind', action='store', type=str,
choices=['first_order', 'detailed'],
default='first_order',
help='TFFM kind ("first_order" or "detailed").')
help_str = 'Input fasta file containing the sequences.'
parser_a.add_argument('-i', '--input_fasta', required=True, type=str,
dest='in_fasta', action='store', help=help_str)
help_str = 'Input bed file w/ positions of the sequences.'
parser_a.add_argument('-I', '--input_bed', required=True, type=str,
dest='in_bed', action='store', help=help_str)
parser_a.add_argument('-c', '--classifier', required=True, type=str,
dest='classifier', action='store',
help='Classifier (.pkl file).')
parser_a.add_argument('-o', '--outfile', required=True, type=str,
dest='output', action='store',
help='Output result file')
help_str = 'List of 1st-order bigWig files as\n'
help_str += '-1 HelT ProT MGW Roll'
help_str += ' (note that we assume such an order)'
parser_a.add_argument('-1', '--1storder', required=True, type=str,
dest='shape_first_order', action='store', nargs=4,
help=help_str)
help_str = 'List of 2nd-order bigWig files as: '
help_str += '-2 HelT2 ProT2 MGW2 Roll2'
help_str += ' (note that we assume such an order)'
parser_a.add_argument('-2', '--2ndorder', required=False, type=str,
dest='shape_second_order', action='store', nargs=4,
default=[], help=help_str)
parser_a.add_argument('-n', '--scaled', required=False, dest='scaled',
action='store_true', default=False,
help='Scale DNAshape values in [0, 1]')
help_str = 'Extension to be considered around TFBSs with DNAshapes'
help_str += ' (default:0).'
parser_a.add_argument('-e', '--extension', required=False, type=int,
dest='extension', action='store', default=0,
help=help_str)
help_str = 'Probability threshold to predict a hit (default=0.5).'
parser_a.add_argument('-v', '--threshold', required=False,
dest='threshold', action='store', default=0.5,
type=float, help=help_str)
parser_a.set_defaults(func=dna_shape_and_tffm_apply_classifier)
def binary_train_args_parsing(subparsers):
""" Train the 4-bits + DNA shape classifier. """
help_str = "Train the 4-bits + DNA shape classifier."
parser_t = subparsers.add_parser('train4bits', help=help_str)
jaspar_grp = parser_t.add_mutually_exclusive_group(required=True)
help_str = 'JASPAR ID corresponding to the TF '
help_str += 'binding profile to be used.'
jaspar_grp.add_argument('-j', '--jaspar', type=str, dest='jasparid',
action='store', help=help_str)
help_str = 'JASPAR file containing the TF binding profile in the '
help_str += 'JASPAR format.'
jaspar_grp.add_argument('-f', '--jasparfile', type=str, dest='jasparfile',
action='store', help=help_str)
help_str = 'Input fasta file containing the foreground sequences.'
parser_t.add_argument('-i', '--fg_fasta', required=True, type=str,
dest='fg_fasta', action='store', help=help_str)
help_str = 'Input bed file w/ positions of foreground sequences.'
parser_t.add_argument('-I', '--fg_bed', required=True, type=str,
dest='fg_bed', action='store', help=help_str)
help_str = 'Input fasta containing the background sequences.'
parser_t.add_argument('-b', '--bg_fasta', required=True, type=str,
dest='bg_fasta', action='store', help=help_str)
help_str = 'Input bed file w/ positions of background sequences.'
parser_t.add_argument('-B', '--bg_bed', required=True, type=str,
dest='bg_bed', action='store', help=help_str)
parser_t.add_argument('-o', '--outfile', required=True, type=str,
dest='output', action='store',
help='Output base name (.pkl will be added).')
help_str = 'List of 1st-order bigWig files as\n'
help_str += '-1 HelT ProT MGW Roll'
help_str += ' (note that we assume such an order)'
parser_t.add_argument('-1', '--1storder', required=True, type=str,
dest='shape_first_order', action='store', nargs=4,
help=help_str)
help_str = 'List of 2nd-order bigWig files as\n'
help_str += '-2 HelT2 ProT2 MGW2 Roll2'
help_str += ' (note that we assume such an order)'
parser_t.add_argument('-2', '--2ndorder', required=False, type=str,
dest='shape_second_order', action='store', nargs=4,
default=[], help=help_str)
parser_t.add_argument('-n', '--scaled', required=False, dest='scaled',
action='store_true', default=False,
help='Scale DNAshape values in [0, 1]')
help_str = 'Extension to be considered around TFBSs with DNAshapes'
help_str += ' (default:0).'
parser_t.add_argument('-e', '--extension', required=False, type=int,
dest='extension', action='store', default=0,
help=help_str)
parser_t.set_defaults(func=dna_shape_and_binary_train_classifier)
def binary_apply_args_parsing(subparsers):
""" Apply the 4-bits + DNA shape classifier. """
help_str = 'Apply the 4-bits + DNA shape classifier.'
parser_a = subparsers.add_parser('apply4bits', help=help_str)
jaspar_grp = parser_a.add_mutually_exclusive_group(required=True)
help_str = 'JASPAR ID corresponding to the TF '
help_str += 'binding profile to be used.'
jaspar_grp.add_argument('-j', '--jaspar', type=str, dest='jasparid',
action='store', help=help_str)
help_str = 'JASPAR file containing the TF binding profile in the '
help_str += 'JASPAR format.'
jaspar_grp.add_argument('-f', '--jasparfile', type=str, dest='jasparfile',
action='store', help=help_str)
help_str = 'Input fasta file containing the sequences.'
parser_a.add_argument('-i', '--input_fasta', required=True, type=str,
dest='in_fasta', action='store', help=help_str)
help_str = 'Input bed file w/ positions of the sequences.'
parser_a.add_argument('-I', '--input_bed', required=True, type=str,
dest='in_bed', action='store', help=help_str)
parser_a.add_argument('-c', '--classifier', required=True, type=str,
dest='classifier', action='store',
help='Classifier (.pkl file).')
parser_a.add_argument('-o', '--outfile', required=True, type=str,
dest='output', action='store',
help='Output result file')
help_str = 'List of 1st-order bigWig files as\n'
help_str += '-1 HelT ProT MGW Roll'
help_str += ' (note that we assume such an order)'
parser_a.add_argument('-1', '--1storder', required=True, type=str,
dest='shape_first_order', action='store', nargs=4,
help=help_str)
help_str = 'List of 2nd-order bigWig files as\n'
help_str += '-2 HelT2 ProT2 MGW2 Roll2'
help_str += ' (note that we assume such an order)'
parser_a.add_argument('-2', '--2ndorder', required=False, type=str,
dest='shape_second_order', action='store', nargs=4,
default=[], help=help_str)
parser_a.add_argument('-n', '--scaled', required=False, dest='scaled',
action='store_true', default=False,
help='Scale DNAshape values in [0, 1]')
help_str = 'Extension to be considered around TFBSs with DNAshapes'
help_str += ' (default:0).'
parser_a.add_argument('-e', '--extension', required=False, type=int,
dest='extension', action='store', default=0,
help=help_str)
help_str = 'Probability threshold to predict a hit (default=0.5).'
parser_a.add_argument('-v', '--threshold', required=False,
dest='threshold', action='store', default=0.5,
type=float, help=help_str)
parser_a.set_defaults(func=dna_shape_and_binary_apply_classifier)
def custom_train_args_parsing(subparsers):
""" Train a custom classifier (based on available combinations). """
help_str = "Train a custom classifier."
parser_t = subparsers.add_parser('custom_train', help=help_str)
jaspar_grp = parser_t.add_mutually_exclusive_group(required=True)
help_str = 'JASPAR ID corresponding to the TF '
help_str += 'binding profile to be used.'
jaspar_grp.add_argument('-j', '--jaspar', type=str, dest='jasparid',
action='store', help=help_str)
help_str = 'JASPAR file containing the TF binding profile in the '
help_str += 'JASPAR format.'
jaspar_grp.add_argument('-f', '--jasparfile', type=str, dest='jasparfile',
action='store', help=help_str)
help_str = 'Input fasta file containing the foreground sequences.'
parser_t.add_argument('-i', '--fg_fasta', required=True, type=str,
dest='fg_fasta', action='store', help=help_str)
help_str = 'Input bed file w/ positions of foreground sequences.'
parser_t.add_argument('-I', '--fg_bed', required=True, type=str,
dest='fg_bed', action='store', help=help_str)
help_str = 'Input fasta containing the background sequences.'
parser_t.add_argument('-b', '--bg_fasta', required=True, type=str,
dest='bg_fasta', action='store', help=help_str)
help_str = 'Input bed file w/ positions of background sequences.'
parser_t.add_argument('-B', '--bg_bed', required=True, type=str,
dest='bg_bed', action='store', help=help_str)
parser_t.add_argument('-o', '--outfile', required=True, type=str,
dest='output', action='store',
help='Output base name (.pkl will be added).')
help_str = 'List of 1st-order bigWig files as\n'
help_str += '-1 HelT ProT MGW Roll'
help_str += ' (note that we assume such an order)'
parser_t.add_argument('-1', '--1storder', required=True, type=str,
dest='shape_first_order', action='store', nargs=4,
help=help_str)
help_str = 'List of 2nd-order bigWig files as\n'
help_str += '-2 HelT2 ProT2 Roll2'
help_str += ' (note that we assume such an order)'
parser_t.add_argument('-2', '--2ndorder', required=False, type=str,
dest='shape_second_order', action='store', nargs=3,
default=[], help=help_str)
parser_t.add_argument('-n', '--scaled', required=False, dest='scaled',
action='store_true', default=False,
help='Scale DNAshape values in [0, 1]')
help_str = 'Extension to be considered around TFBSs with DNAshapes'
help_str += ' (default:0).'
parser_t.add_argument('-e', '--extension', required=False, type=int,
dest='extension', action='store', default=0,
help=help_str)
parser_t.set_defaults(func=custom_train_and_validate_classifier)
help_str = 'Type of feature vector to construct\n'
help_str += '(0 = seq_and_dna_shape| 1 = dna_shape_only | 2 = dna_shape_and_flexibility)'
help_str += ' (default : 0).'
parser_t.add_argument('-q', '--feature_vector_type', required=False, type=int,
dest='feature_vector_type', action='store', default=0,
help=help_str)
help_str = 'Type of DNA sequence feature to consider\n'
help_str += '(0 = PSSM | 1 = TFFM | 2 = 4bit)'
help_str += ' (default : 0).'
parser_t.add_argument('-s', '--seq_feature', required=False, type=int,
dest='seq_feature', action='store', default=0,
help=help_str)
help_str = 'Are we evaluating flexibility with a wrapper function?\n'
help_str += '(0 = False | 1 = True)'
help_str += ' (default : 0).'
parser_t.add_argument('-E', '--is_eval_f', required=False, type=int,
dest='is_eval_f', action='store', default=0,
help=help_str)
parser_t.set_defaults(func=custom_train_classifier)
def custom_apply_args_parsing(subparsers):
""" Apply a custom classifier (based on available combinations). """
help_str = "Apply a custom classifier."
parser_a = subparsers.add_parser('custom_apply', help=help_str)
jaspar_grp = parser_a.add_mutually_exclusive_group(required=True)
help_str = 'JASPAR ID corresponding to the TF '
help_str += 'binding profile to be used.'
jaspar_grp.add_argument('-j', '--jaspar', type=str, dest='jasparid',
action='store', help=help_str)
help_str = 'JASPAR file containing the TF binding profile in the '
help_str += 'JASPAR format.'
jaspar_grp.add_argument('-f', '--jasparfile', type=str, dest='jasparfile',
action='store', help=help_str)
help_str = 'Input fasta file containing the sequences.'
parser_a.add_argument('-i', '--input_fasta', required=True, type=str,
dest='in_fasta', action='store', help=help_str)
help_str = 'Input bed file w/ positions of the sequences.'
parser_a.add_argument('-I', '--input_bed', required=True, type=str,
dest='in_bed', action='store', help=help_str)
parser_a.add_argument('-c', '--classifier', required=True, type=str,
dest='classifier', action='store',
help='Classifier (.pkl file).')
parser_a.add_argument('-o', '--outfile', required=True, type=str,
dest='output', action='store',
help='Output result file')
help_str = 'List of 1st-order bigWig files as\n'
help_str += '-1 HelT ProT MGW Roll'
help_str += ' (note that we assume such an order)'
parser_a.add_argument('-1', '--1storder', required=True, type=str,
dest='shape_first_order', action='store', nargs=4,
help=help_str)
help_str = 'List of 2nd-order bigWig files as\n'
help_str += '-2 HelT2 ProT2 MGW2 Roll2'
help_str += ' (note that we assume such an order)'
parser_a.add_argument('-2', '--2ndorder', required=False, type=str,
dest='shape_second_order', action='store', nargs=3,
default=[], help=help_str)
parser_a.add_argument('-n', '--scaled', required=False, dest='scaled',
action='store_true', default=False,
help='Scale DNAshape values in [0, 1]')
help_str = 'Extension to be considered around TFBSs with DNAshapes'
help_str += ' (default:0).'
parser_a.add_argument('-e', '--extension', required=False, type=int,
dest='extension', action='store', default=0,
help=help_str)
help_str = 'Probability threshold to predict a hit (default=0.5).'
parser_a.add_argument('-v', '--threshold', required=False,
dest='threshold', action='store', default=0.5,
type=float, help=help_str)
help_str = 'Type of feature vector to construct\n'
help_str += '(0 = seq_and_dna_shape| 1 = dna_shape_only | 2 = dna_shape_and_flexibility)'
help_str += ' (default : 0).'
parser_a.add_argument('-q', '--feature_vector_type', required=False, type=int,
dest='feature_vector_type', action='store', default=0,
help=help_str)
help_str = 'Type of DNA sequence feature to consider\n'
help_str += '(0 = PSSM | 1 = TFFM | 2 = 4bit)'
help_str += ' (default : 0).'
parser_a.add_argument('-s', '--seq_feature', required=False, type=int,
dest='seq_feature', action='store', default=0,
help=help_str)
help_str = 'Are we evaluating flexibility with a wrapper function?\n'
help_str += '(0 = False | 1 = True)'
help_str += ' (default : 0).'
parser_a.add_argument('-E', '--is_eval_f', required=False, type=int,
dest='is_eval_f', action='store', default=0,
help=help_str)
parser_a.set_defaults(func=custom_apply_classifier)
def custom_train_and_validate_args_parsing(subparsers):
""" Train and apply the PSSM + DNA shape classifier. """
help_str = "Train and apply the PSSM + DNA shape classifier."
parser_t = subparsers.add_parser('custom_train_and_apply', help=help_str)
jaspar_grp = parser_t.add_mutually_exclusive_group(required=True)
help_str = 'JASPAR ID corresponding to the TF '
help_str += 'binding profile to be used.'
jaspar_grp.add_argument('-j', '--jaspar', type=str, dest='jasparid',
action='store', help=help_str)
help_str = 'JASPAR file containing the TF binding profile in the '
help_str += 'JASPAR format.'
jaspar_grp.add_argument('-f', '--jasparfile', type=str, dest='jasparfile',
action='store', help=help_str)
help_str = 'Input fasta file containing the foreground sequences.'
parser_t.add_argument('-i', '--fg_fasta', required=True, type=str,
dest='fg_fasta', action='store', help=help_str)
help_str = 'Input bed file w/ positions of foreground sequences.'
parser_t.add_argument('-I', '--fg_bed', required=True, type=str,
dest='fg_bed', action='store', help=help_str)
help_str = 'Input fasta containing the background sequences.'
parser_t.add_argument('-b', '--bg_fasta', required=True, type=str,
dest='bg_fasta', action='store', help=help_str)
help_str = 'Input bed file w/ positions of background sequences.'
parser_t.add_argument('-B', '--bg_bed', required=True, type=str,
dest='bg_bed', action='store', help=help_str)
parser_t.add_argument('-o', '--outfile', required=True, type=str,
dest='output', action='store',
help='Output base name (.pkl will be added).')
help_str = 'List of 1st-order bigWig files as\n'
help_str += '-1 HelT ProT MGW Roll'
help_str += ' (note that we assume such an order)'
parser_t.add_argument('-1', '--1storder', required=True, type=str,
dest='shape_first_order', action='store', nargs=4,
help=help_str)
help_str = 'List of 2nd-order bigWig files as\n'
help_str += '-2 HelT2 ProT2 Roll2'
help_str += ' (note that we assume such an order)'
parser_t.add_argument('-2', '--2ndorder', required=False, type=str,
dest='shape_second_order', action='store', nargs=3,
default=[], help=help_str)
parser_t.add_argument('-n', '--scaled', required=False, dest='scaled',
action='store_true', default=False,
help='Scale DNAshape values in [0, 1]')
help_str = 'Extension to be considered around TFBSs with DNAshapes'
help_str += ' (default:0).'
parser_t.add_argument('-e', '--extension', required=False, type=int,
dest='extension', action='store', default=0,
help=help_str)
parser_t.set_defaults(func=custom_train_and_validate_classifier)
help_str = 'Type of feature vector to construct\n'
help_str += '(0 = seq_and_dna_shape| 1 = dna_shape_only | 2 = dna_shape_and_flexibility)'
help_str += ' (default : 0).'
parser_t.add_argument('-q', '--feature_vector_type', required=False, type=int,
dest='feature_vector_type', action='store', default=0,
help=help_str)
help_str = 'Type of DNA sequence feature to consider\n'
help_str += '(0 = PSSM | 1 = TFFM | 2 = 4bit)'
help_str += ' (default : 0).'
parser_t.add_argument('-s', '--seq_feature', required=False, type=int,
dest='seq_feature', action='store', default=0,
help=help_str)
help_str = 'Are we evaluating flexibility with a wrapper function?\n'
help_str += '(0 = False | 1 = True)'
help_str += ' (default : 0).'
parser_t.add_argument('-E', '--is_eval_f', required=False, type=bool,
dest='is_eval_f', action='store', default=False,
help=help_str)
help_str = 'Optional experiment name (prepended to cumulative csvs)'
parser_t.add_argument('-N', '--exp_name', required=False, type=str,
dest='exp_name', action='store', default='',
help=help_str)
parser_t.set_defaults(func=custom_train_and_validate_classifier)
help_str = 'Optional background name (prepended to cumulative csvs)'
parser_t.add_argument('-Q', '--back_type', required=False, type=str,
dest='background_type', action='store', default='',
help=help_str)
help_str = 'Optional protein name (-o value will be used if not specified)'
parser_t.add_argument('-P', '--protein', required=False, type=str,
dest='protein', action='store', default='',
help=help_str)
parser_t.set_defaults(func=custom_train_and_validate_classifier)
def arg_parsing():
""" Parse the subcommand along with its arguments. """
descr = '''
Train or apply the DNAshape-based classifiers to a set of fasta sequences.
'''
import argparse
parser = argparse.ArgumentParser(
description=descr,
formatter_class=argparse.RawDescriptionHelpFormatter)
subparsers = parser.add_subparsers(
help='Train or apply a PSSM/TFFM/4-bits + DNA shape classifier',
title='Subcommands', description='Valid subcommands')
tffm_train_args_parsing(subparsers)
tffm_apply_args_parsing(subparsers)
pssm_train_args_parsing(subparsers)
pssm_apply_args_parsing(subparsers)
binary_train_args_parsing(subparsers)
binary_apply_args_parsing(subparsers)
custom_train_args_parsing(subparsers)
custom_apply_args_parsing(subparsers)
custom_train_and_validate_args_parsing(subparsers)
argu = parser.parse_args()
return argu