-
Notifications
You must be signed in to change notification settings - Fork 36
/
plugin_setup.py
527 lines (513 loc) · 30.5 KB
/
plugin_setup.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
# ----------------------------------------------------------------------------
# Copyright (c) 2016-2023, QIIME 2 development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file LICENSE, distributed with this software.
# ----------------------------------------------------------------------------
import importlib
import qiime2.plugin
from q2_types.per_sample_sequences import (
SequencesWithQuality, PairedEndSequencesWithQuality)
from q2_types.sample_data import SampleData
from q2_types.feature_data import FeatureData, Sequence
from q2_types.feature_table import FeatureTable, Frequency
import q2_dada2
from q2_dada2 import DADA2Stats, DADA2StatsFormat, DADA2StatsDirFmt
import q2_dada2._examples as ex
_POOL_OPT = {'pseudo', 'independent'}
_CHIM_OPT = {'pooled', 'consensus', 'none'}
plugin = qiime2.plugin.Plugin(
name='dada2',
version=q2_dada2.__version__,
website='http://benjjneb.github.io/dada2/',
package='q2_dada2',
description=('This QIIME 2 plugin wraps DADA2 and supports '
'sequence quality control for single-end and paired-end '
'reads using the DADA2 R library.'),
short_description='Plugin for sequence quality control with DADA2.',
citations=qiime2.plugin.Citations.load('citations.bib', package='q2_dada2')
)
plugin.methods.register_function(
function=q2_dada2.denoise_single,
inputs={'demultiplexed_seqs': SampleData[SequencesWithQuality |
PairedEndSequencesWithQuality]},
parameters={'trunc_len': qiime2.plugin.Int,
'trim_left': qiime2.plugin.Int,
'max_ee': qiime2.plugin.Float,
'trunc_q': qiime2.plugin.Int,
'pooling_method': qiime2.plugin.Str %
qiime2.plugin.Choices(_POOL_OPT),
'chimera_method': qiime2.plugin.Str %
qiime2.plugin.Choices(_CHIM_OPT),
'min_fold_parent_over_abundance': qiime2.plugin.Float,
'allow_one_off': qiime2.plugin.Bool,
'n_threads': qiime2.plugin.Threads,
'n_reads_learn': qiime2.plugin.Int,
'hashed_feature_ids': qiime2.plugin.Bool,
'retain_all_samples': qiime2.plugin.Bool},
outputs=[('table', FeatureTable[Frequency]),
('representative_sequences', FeatureData[Sequence]),
('denoising_stats', SampleData[DADA2Stats])],
input_descriptions={
'demultiplexed_seqs': ('The single-end demultiplexed sequences to be '
'denoised.')
},
parameter_descriptions={
'trunc_len': ('Position at which sequences should be truncated due to '
'decrease in quality. This truncates the 3\' end of the '
'of the input sequences, which will be the bases that '
'were sequenced in the last cycles. Reads that are '
'shorter than this value will be discarded. If 0 is '
'provided, no truncation or length filtering will be '
'performed'),
'trim_left': ('Position at which sequences should be trimmed due to '
'low quality. This trims the 5\' end of the '
'of the input sequences, which will be the bases that '
'were sequenced in the first cycles.'),
'max_ee': ('Reads with number of expected errors higher than this '
'value will be discarded.'),
'trunc_q': ('Reads are truncated at the first instance of a quality '
'score less than or equal to this value. If the resulting '
'read is then shorter than `trunc_len`, it is discarded.'),
'pooling_method': (
'The method used to pool samples for denoising. '
'"independent": Samples are denoised independently. '
'"pseudo": The pseudo-pooling method is used to '
'approximate pooling of samples. In short, samples '
'are denoised independently once, ASVs detected '
'in at least 2 samples are recorded, and samples '
'are denoised independently a second time, but '
'this time with prior knowledge of the recorded '
'ASVs and thus higher sensitivity to those ASVs.'
),
'chimera_method': ('The method used to remove chimeras. '
'"none": No chimera removal is performed. '
'"pooled": All reads are pooled prior to chimera '
'detection. "consensus": Chimeras are detected in '
'samples individually, and sequences found '
'chimeric in a sufficient fraction of samples are '
'removed.'),
'min_fold_parent_over_abundance': (
'The minimum abundance of potential parents of a sequence being '
'tested as chimeric, expressed as a fold-change versus the '
'abundance of the sequence being tested. Values should be greater '
'than or equal to 1 (i.e. parents should be more abundant than '
'the sequence being tested). This parameter has no effect if '
'chimera_method is "none".'),
'allow_one_off': (
'Bimeras that are one-off from exact are also '
'identified if the `allow_one_off` argument is True.'
'If True, a sequence will be identified as bimera if it is one '
'mismatch or indel away from an exact bimera.'),
'n_threads': ('The number of threads to use for multithreaded '
'processing. If 0 is provided, all available cores will '
'be used.'),
'n_reads_learn': ('The number of reads to use when training the '
'error model. Smaller numbers will result in a '
'shorter run time but a less reliable error '
'model.'),
'hashed_feature_ids': ('If true, the feature ids in the resulting '
'table will be presented as hashes of the '
'sequences defining each feature. The hash '
'will always be the same for the same sequence '
'so this allows feature tables to be merged '
'across runs of this method. You should only '
'merge tables if the exact same parameters are '
'used for each run.'),
'retain_all_samples': 'If True all samples input to dada2 will be '
'retained in the output of dada2, if false '
'samples with zero total frequency are removed '
'from the table.'
},
output_descriptions={
'table': 'The resulting feature table.',
'representative_sequences': ('The resulting feature sequences. Each '
'feature in the feature table will be '
'represented by exactly one sequence.')
},
name='Denoise and dereplicate single-end sequences',
description=('This method denoises single-end sequences, dereplicates '
'them, and filters chimeras.'),
examples={
'denoise_single': ex.denoise_single
}
)
plugin.methods.register_function(
function=q2_dada2.denoise_paired,
inputs={'demultiplexed_seqs': SampleData[PairedEndSequencesWithQuality]},
parameters={'trunc_len_f': qiime2.plugin.Int,
'trunc_len_r': qiime2.plugin.Int,
'trim_left_f': qiime2.plugin.Int,
'trim_left_r': qiime2.plugin.Int,
'max_ee_f': qiime2.plugin.Float,
'max_ee_r': qiime2.plugin.Float,
'trunc_q': qiime2.plugin.Int,
'min_overlap': qiime2.plugin.Int %
qiime2.plugin.Range(4, None),
'pooling_method': qiime2.plugin.Str %
qiime2.plugin.Choices(_POOL_OPT),
'chimera_method': qiime2.plugin.Str %
qiime2.plugin.Choices(_CHIM_OPT),
'min_fold_parent_over_abundance': qiime2.plugin.Float,
'allow_one_off': qiime2.plugin.Bool,
'n_threads': qiime2.plugin.Threads,
'n_reads_learn': qiime2.plugin.Int,
'hashed_feature_ids': qiime2.plugin.Bool,
'retain_all_samples': qiime2.plugin.Bool},
outputs=[('table', FeatureTable[Frequency]),
('representative_sequences', FeatureData[Sequence]),
('denoising_stats', SampleData[DADA2Stats])],
input_descriptions={
'demultiplexed_seqs': ('The paired-end demultiplexed sequences to be '
'denoised.')
},
parameter_descriptions={
'trunc_len_f': ('Position at which forward read sequences should be '
'truncated due to decrease in quality. This truncates '
'the 3\' end of the of the input sequences, which '
'will be the bases that were sequenced in the last '
'cycles. Reads that are shorter than this value '
'will be discarded. After this parameter is applied '
'there must still be at least a 12 nucleotide overlap '
'between the forward and reverse reads. If 0 is '
'provided, no truncation or length filtering will be '
'performed'),
'trim_left_f': ('Position at which forward read sequences should be '
'trimmed due to low quality. This trims the 5\' end '
'of the input sequences, which will be the bases that '
'were sequenced in the first cycles.'),
'trunc_len_r': ('Position at which reverse read sequences should be '
'truncated due to decrease in quality. This truncates '
'the 3\' end of the of the input sequences, which '
'will be the bases that were sequenced in the last '
'cycles. Reads that are shorter than this value '
'will be discarded. After this parameter is applied '
'there must still be at least a 12 nucleotide overlap '
'between the forward and reverse reads. If 0 is '
'provided, no truncation or length filtering will be '
'performed'),
'trim_left_r': ('Position at which reverse read sequences should be '
'trimmed due to low quality. This trims the 5\' end '
'of the input sequences, which will be the bases that '
'were sequenced in the first cycles.'),
'max_ee_f': ('Forward reads with number of expected errors higher '
'than this value will be discarded.'),
'max_ee_r': ('Reverse reads with number of expected errors higher '
'than this value will be discarded.'),
'trunc_q': ('Reads are truncated at the first instance of a quality '
'score less than or equal to this value. If the resulting '
'read is then shorter than `trunc_len_f` or `trunc_len_r` '
'(depending on the direction of the read) it is '
'discarded.'),
'min_overlap': ('The minimum length of the overlap required for '
'merging the forward and reverse reads.'),
'pooling_method': ('The method used to pool samples for denoising. '
'"independent": Samples are denoised indpendently. '
'"pseudo": The pseudo-pooling method is used to '
'approximate pooling of samples. In short, samples '
'are denoised independently once, ASVs detected '
'in at least 2 samples are recorded, and samples '
'are denoised independently a second time, but '
'this time with prior knowledge of the recorded '
'ASVs and thus higher sensitivity to those ASVs.'),
'chimera_method': ('The method used to remove chimeras. '
'"none": No chimera removal is performed. '
'"pooled": All reads are pooled prior to chimera '
'detection. "consensus": Chimeras are detected in '
'samples individually, and sequences found '
'chimeric in a sufficient fraction of samples are '
'removed.'),
'min_fold_parent_over_abundance': (
'The minimum abundance of potential parents of a sequence being '
'tested as chimeric, expressed as a fold-change versus the '
'abundance of the sequence being tested. Values should be greater '
'than or equal to 1 (i.e. parents should be more abundant than '
'the sequence being tested). This parameter has no effect if '
'chimera_method is "none".'),
'allow_one_off': (
'Bimeras that are one-off from exact are also '
'identified if the `allow_one_off` argument is True'
'If True, a sequence will be identified as bimera if it is one '
'mismatch or indel away from an exact bimera.'),
'n_threads': ('The number of threads to use for multithreaded '
'processing. If 0 is provided, all available cores will '
'be used.'),
'n_reads_learn': ('The number of reads to use when training the '
'error model. Smaller numbers will result in a '
'shorter run time but a less reliable error '
'model.'),
'hashed_feature_ids': ('If true, the feature ids in the resulting '
'table will be presented as hashes of the '
'sequences defining each feature. The hash '
'will always be the same for the same sequence '
'so this allows feature tables to be merged '
'across runs of this method. You should only '
'merge tables if the exact same parameters are '
'used for each run.'),
'retain_all_samples': 'If True all samples input to dada2 will be '
'retained in the output of dada2, if false '
'samples with zero total frequency are removed '
'from the table.'
},
output_descriptions={
'table': 'The resulting feature table.',
'representative_sequences': ('The resulting feature sequences. Each '
'feature in the feature table will be '
'represented by exactly one sequence, '
'and these sequences will be the joined '
'paired-end sequences.')
},
name='Denoise and dereplicate paired-end sequences',
description=('This method denoises paired-end sequences, dereplicates '
'them, and filters chimeras.'),
examples={
'denoise_paired': ex.denoise_paired
}
)
plugin.methods.register_function(
function=q2_dada2.denoise_pyro,
inputs={'demultiplexed_seqs': SampleData[SequencesWithQuality]},
parameters={'trunc_len': qiime2.plugin.Int,
'trim_left': qiime2.plugin.Int,
'max_ee': qiime2.plugin.Float,
'trunc_q': qiime2.plugin.Int,
'max_len': qiime2.plugin.Int,
'pooling_method': qiime2.plugin.Str %
qiime2.plugin.Choices(_POOL_OPT),
'chimera_method': qiime2.plugin.Str %
qiime2.plugin.Choices(_CHIM_OPT),
'min_fold_parent_over_abundance': qiime2.plugin.Float,
'allow_one_off': qiime2.plugin.Bool,
'n_threads': qiime2.plugin.Threads,
'n_reads_learn': qiime2.plugin.Int,
'hashed_feature_ids': qiime2.plugin.Bool,
'retain_all_samples': qiime2.plugin.Bool},
outputs=[('table', FeatureTable[Frequency]),
('representative_sequences', FeatureData[Sequence]),
('denoising_stats', SampleData[DADA2Stats])],
input_descriptions={
'demultiplexed_seqs': 'The single-end demultiplexed pyrosequencing '
'sequences (e.g. 454, IonTorrent) to be '
'denoised.'
},
parameter_descriptions={
'trunc_len': 'Position at which sequences should be truncated due to '
'decrease in quality. This truncates the 3\' end of the '
'of the input sequences, which will be the bases that '
'were sequenced in the last cycles. Reads that are '
'shorter than this value will be discarded. If 0 is '
'provided, no truncation or length filtering will be '
'performed',
'trim_left': 'Position at which sequences should be trimmed due to '
'low quality. This trims the 5\' end of the '
'of the input sequences, which will be the bases that '
'were sequenced in the first cycles.',
'max_ee': 'Reads with number of expected errors higher than this '
'value will be discarded.',
'trunc_q': 'Reads are truncated at the first instance of a quality '
'score less than or equal to this value. If the resulting '
'read is then shorter than `trunc_len`, it is discarded.',
'max_len': 'Remove reads prior to trimming or truncation which are '
'longer than this value. If 0 is provided no reads will '
'be removed based on length.',
'pooling_method': 'The method used to pool samples for denoising. '
'"independent": Samples are denoised independently. '
'"pseudo": The pseudo-pooling method is used to '
'approximate pooling of samples. In short, samples '
'are denoised independently once, ASVs detected '
'in at least 2 samples are recorded, and samples '
'are denoised independently a second time, but '
'this time with prior knowledge of the recorded '
'ASVs and thus higher sensitivity to those ASVs.',
'chimera_method': 'The method used to remove chimeras. '
'"none": No chimera removal is performed. '
'"pooled": All reads are pooled prior to chimera '
'detection. "consensus": Chimeras are detected in '
'samples individually, and sequences found '
'chimeric in a sufficient fraction of samples are '
'removed.',
'min_fold_parent_over_abundance':
'The minimum abundance of potential parents of a sequence being '
'tested as chimeric, expressed as a fold-change versus the '
'abundance of the sequence being tested. Values should be greater '
'than or equal to 1 (i.e. parents should be more abundant than '
'the sequence being tested). This parameter has no effect if '
'chimera_method is "none".',
'allow_one_off': (
'Bimeras that are one-off from exact are also '
'identified if the `allow_one_off` argument is True. '
'If True, a sequence will be identified as bimera if it is one '
'mismatch or indel away from an exact bimera.'),
'n_threads': 'The number of threads to use for multithreaded '
'processing. If 0 is provided, all available cores will '
'be used.',
'n_reads_learn': 'The number of reads to use when training the '
'error model. Smaller numbers will result in a '
'shorter run time but a less reliable error '
'model.',
'hashed_feature_ids': 'If true, the feature ids in the resulting '
'table will be presented as hashes of the '
'sequences defining each feature. The hash '
'will always be the same for the same sequence '
'so this allows feature tables to be merged '
'across runs of this method. You should only '
'merge tables if the exact same parameters are '
'used for each run.',
'retain_all_samples': 'If True all samples input to dada2 will be '
'retained in the output of dada2, if false '
'samples with zero total frequency are removed '
'from the table.'
},
output_descriptions={
'table': 'The resulting feature table.',
'representative_sequences': 'The resulting feature sequences. Each '
'feature in the feature table will be '
'represented by exactly one sequence.'
},
name='Denoise and dereplicate single-end pyrosequences',
description='This method denoises single-end pyrosequencing sequences, '
'dereplicates them, and filters chimeras.'
)
plugin.methods.register_function(
function=q2_dada2.denoise_ccs,
inputs={'demultiplexed_seqs': SampleData[SequencesWithQuality]},
parameters={'front': qiime2.plugin.Str,
'adapter': qiime2.plugin.Str,
'max_mismatch': qiime2.plugin.Int,
'indels': qiime2.plugin.Bool,
'trunc_len': qiime2.plugin.Int,
'trim_left': qiime2.plugin.Int,
'max_ee': qiime2.plugin.Float,
'trunc_q': qiime2.plugin.Int,
'min_len': qiime2.plugin.Int,
'max_len': qiime2.plugin.Int,
'pooling_method': qiime2.plugin.Str %
qiime2.plugin.Choices(_POOL_OPT),
'chimera_method': qiime2.plugin.Str %
qiime2.plugin.Choices(_CHIM_OPT),
'min_fold_parent_over_abundance': qiime2.plugin.Float,
'allow_one_off': qiime2.plugin.Bool,
'n_threads': qiime2.plugin.Threads,
'n_reads_learn': qiime2.plugin.Int,
'hashed_feature_ids': qiime2.plugin.Bool,
'retain_all_samples': qiime2.plugin.Bool},
outputs=[('table', FeatureTable[Frequency]),
('representative_sequences', FeatureData[Sequence]),
('denoising_stats', SampleData[DADA2Stats])],
input_descriptions={
'demultiplexed_seqs': 'The single-end demultiplexed PacBio CCS '
'sequences to be denoised.'
},
parameter_descriptions={
'front': 'Sequence of an adapter ligated to the 5\' end. '
'The adapter and any preceding bases are trimmed. '
'Can contain IUPAC ambiguous nucleotide codes. '
'Note, primer direction is 5\' to 3\'. '
'Primers are removed before trim and filter step. '
'Reads that do not contain the primer are discarded. '
'Each read is re-oriented if the reverse complement of '
'the read is a better match to the provided primer sequence. '
'This is recommended for PacBio CCS reads, which come in a '
'random mix of forward and reverse-complement orientations.',
'adapter': 'Sequence of an adapter ligated to the 3\' end. '
'The adapter and any preceding bases are trimmed. '
'Can contain IUPAC ambiguous nucleotide codes. '
'Note, primer direction is 5\' to 3\'. '
'Primers are removed before trim and filter step. '
'Reads that do not contain the primer are discarded.',
'max_mismatch': 'The number of mismatches to tolerate when matching '
'reads to primer sequences '
'- see http://benjjneb.github.io/dada2/ '
'for complete details.',
'indels': 'Allow insertions or deletions of bases when '
'matching adapters. Note that primer matching can '
'be significantly slower, currently about 4x slower',
'trunc_len': 'Position at which sequences should be truncated due to '
'decrease in quality. This truncates the 3\' end of the '
'of the input sequences, which will be the bases that '
'were sequenced in the last cycles. Reads that are '
'shorter than this value will be discarded. If 0 is '
'provided, no truncation or length filtering will be '
'performed. Note: Since Pacbio CCS sequences were '
'normally with very high quality scores, '
'there is no need to truncate the Pacbio CCS sequences.',
'trim_left': 'Position at which sequences should be trimmed due to '
'low quality. This trims the 5\' end of the '
'of the input sequences, which will be the bases that '
'were sequenced in the first cycles.',
'max_ee': 'Reads with number of expected errors higher than this '
'value will be discarded.',
'trunc_q': 'Reads are truncated at the first instance of a quality '
'score less than or equal to this value. If the resulting '
'read is then shorter than `trunc_len`, it is discarded.',
'min_len': 'Remove reads with length less than minLen. '
'minLen is enforced after trimming and truncation.'
' For 16S Pacbio CCS, suggest 1000.',
'max_len': 'Remove reads prior to trimming or truncation which are '
'longer than this value. If 0 is provided no reads will '
'be removed based on length. '
'For 16S Pacbio CCS, suggest 1600.',
'pooling_method': 'The method used to pool samples for denoising. '
'"independent": Samples are denoised indpendently. '
'"pseudo": The pseudo-pooling method is used to '
'approximate pooling of samples. In short, samples '
'are denoised independently once, ASVs detected '
'in at least 2 samples are recorded, and samples '
'are denoised independently a second time, but '
'this time with prior knowledge of the recorded '
'ASVs and thus higher sensitivity to those ASVs.',
'chimera_method': 'The method used to remove chimeras. '
'"none": No chimera removal is performed. '
'"pooled": All reads are pooled prior to chimera '
'detection. "consensus": Chimeras are detected in '
'samples individually, and sequences found chimeric '
'in a sufficient fraction of samples are removed.',
'min_fold_parent_over_abundance':
'The minimum abundance of potential parents of a sequence being '
'tested as chimeric, expressed as a fold-change versus the '
'abundance of the sequence being tested. Values should be greater '
'than or equal to 1 (i.e. parents should be more abundant than '
'the sequence being tested). Suggest 3.5. '
'This parameter has no effect if chimera_method is "none".',
'allow_one_off': (
'Bimeras that are one-off from exact are also '
'identified if the `allow_one_off` argument is True. '
'If True, a sequence will be identified as bimera if it is one '
'mismatch or indel away from an exact bimera.'),
'n_threads': 'The number of threads to use for multithreaded '
'processing. If 0 is provided, all available cores will '
'be used.',
'n_reads_learn': 'The number of reads to use when training the '
'error model. Smaller numbers will result in a '
'shorter run time but a less reliable error model.',
'hashed_feature_ids': 'If true, the feature ids in the resulting '
'table will be presented as hashes of the '
'sequences defining each feature. The hash '
'will always be the same for the same sequence '
'so this allows feature tables to be merged '
'across runs of this method. You should only '
'merge tables if the exact same parameters are '
'used for each run.',
'retain_all_samples': 'If True all samples input to dada2 will be '
'retained in the output of dada2, if false '
'samples with zero total frequency are removed '
'from the table.'
},
output_descriptions={
'table': 'The resulting feature table.',
'representative_sequences': 'The resulting feature sequences. Each '
'feature in the feature table will be '
'represented by exactly one sequence.'
},
name='Denoise and dereplicate single-end Pacbio CCS',
description='This method denoises single-end Pacbio CCS sequences, '
'dereplicates them, and filters chimeras. '
'Tutorial and workflow: '
'https://github.com/benjjneb/LRASManuscript'
)
plugin.register_formats(DADA2StatsFormat, DADA2StatsDirFmt)
plugin.register_semantic_types(DADA2Stats)
plugin.register_semantic_type_to_format(
SampleData[DADA2Stats], DADA2StatsDirFmt)
importlib.import_module('q2_dada2._transformer')