-
Notifications
You must be signed in to change notification settings - Fork 11
/
Copy pathnextflow_schema.json
640 lines (640 loc) · 32.3 KB
/
nextflow_schema.json
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
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/epi2me-labs/wf-somatic-variation/master/nextflow_schema.json",
"title": "epi2me-labs/wf-somatic-variation",
"workflow_title": "Somatic variation workflow",
"description": "Nextflow workflow to identify somatic variation.",
"demo_url": "https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-somatic-variation/wf-somatic-variation-demo.tar.gz",
"aws_demo_url": "https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-somatic-variation/wf-somatic-variation-demo/aws.nextflow.config",
"url": "https://github.com/epi2me-labs/wf-somatic-variation",
"type": "object",
"definitions": {
"workflow": {
"title": "Workflow Options",
"type": "object",
"fa_icon": "fas fa-arrow-right",
"description": "Select which sub-workflows of wf-human-variation you wish to run. Parameters for each sub-workflow can be changed using the sections below.",
"properties": {
"snv": {
"title": "SNV: Short variants",
"type": "boolean",
"description": "Call for somatic small variants.",
"help_text": "If this option is selected, small variant calling will be carried out using ClairS.",
"default": false
},
"sv": {
"title": "SV: Structural variants",
"type": "boolean",
"description": "Call for somatic structural variants.",
"help_text": "If this option is selected, the workflow will call somatic structural variants using severus.",
"default": false
},
"mod": {
"title": "MOD: Differential modifications",
"type": "boolean",
"description": "Enable output of differentially modified sites and differentially modified regions [requires input BAMs with ML and MM tags].",
"help_text": "If this option is selected, modified bases will be aggregated with modkit and differential modifications will be computed with DSS.",
"default": false
}
},
"anyOf": [
{
"required": [
"sv"
]
},
{
"required": [
"snv"
]
},
{
"required": [
"mod"
]
}
]
},
"input": {
"title": "Main options",
"type": "object",
"fa_icon": "fas fa-arrow-right",
"description": "Primary options for the data analysis.",
"properties": {
"sample_name": {
"title": "Sample name",
"type": "string",
"default": "SAMPLE",
"description": "Sample name to be displayed in workflow outputs.",
"help_text": "The sample name will be used from the workflow to correctly name output files."
},
"bam_normal": {
"title": "Normal BAM",
"type": "string",
"format": "path",
"description": "BAM or unaligned BAM (uBAM) files for the normal sample to use in the analysis.",
"help_text": "This accepts one of two cases: (i) the path to a single BAM file; (ii) the path to a top-level directory containing BAM files. A sample name can be supplied with `--sample`."
},
"bam_tumor": {
"title": "Tumor BAM",
"type": "string",
"format": "path",
"description": "BAM or unaligned BAM (uBAM) files for the tumor sample to use in the analysis.",
"help_text": "This accepts one of two cases: (i) the path to a single BAM file; (ii) the path to a top-level directory containing BAM files. A sample name can be supplied with `--sample`."
},
"ref": {
"title": "Reference genome file",
"type": "string",
"format": "file-path",
"description": "Path to a reference FASTA file.",
"help_text": "Reference against which to compare reads for variant calling."
},
"bed": {
"title": "Target region BED file",
"type": "string",
"format": "file-path",
"description": "An optional BED file enumerating regions to process for variant calling.",
"help_text": ""
},
"tr_bed": {
"title": "Tandem repeat BED file",
"type": "string",
"format": "file-path",
"description": "An optional BED file enumerating simple repeat regions.",
"help_text": "This command provides a bed file specifying the location of the simple repetitive elements in the genome of choice. This file should be a standard bed file, as described in the [UCSC specification](https://genome.ucsc.edu/FAQ/FAQformat.html#format1)."
},
"out_dir": {
"title": "Output directory",
"type": "string",
"default": "output",
"format": "directory-path",
"description": "Directory for output of all workflow results."
},
"annotation": {
"type": "boolean",
"default": true,
"description": "Perform SnpEff annotation.",
"help_text": "If this option is deselected, VCFs will not be annotated with [SnpEff](https://pcingola.github.io/SnpEff/)."
},
"include_all_ctgs": {
"title": "Include all contigs",
"type": "boolean",
"default": false,
"description": "Call for variants on all sequences in the reference, otherwise small variants will only be called on chr{1..22,X,Y,MT}.",
"help_text": "Enabling this option will call for variants on all contigs of the input reference sequence. Typically this option is not required as standard human reference sequences contain decoy and unplaced contigs that are usually omitted for the purpose of variant calling. This option might be useful for non-standard reference sequence databases."
},
"igv": {
"title": "Show in IGV",
"type": "boolean",
"default": false,
"description": "Visualize outputs in the EPI2ME IGV visualizer.",
"help_text": "Enabling this option will visualize the output VCF files in the EPI2ME desktop app IGV visualizer."
}
},
"required": [
"ref",
"bam_tumor"
]
},
"qc_options": {
"title": "Quality Control Options",
"type": "object",
"fa_icon": "fas fa-vials",
"description": "Parameters that relate to the quality control of the reads.",
"properties": {
"depth_intervals": {
"title": "Depth intervals",
"type": "boolean",
"default": false,
"description": "Output a bedGraph file with entries for each genomic interval featuring homogeneous depth.",
"help_text": "The output [bedGraph](https://genome.ucsc.edu/goldenPath/help/bedgraph.html) file will have an entry for each genomic interval in which all positions have the same alignment depth. By default this workflow outputs summary depth information from your aligned reads. Per-base depth outputs are slower to generate but may be required for some downstream applications."
},
"depth_window_size": {
"type": "number",
"default": 50000,
"hidden": true,
"description": "Coverage window size in bp.",
"help_text": "This options specify the window size to use when computing the coverage along the genome."
},
"tumor_min_coverage": {
"title": "Tumor minimum coverage",
"type": "number",
"default": 20,
"hidden": false,
"description": "Minimum read coverage for the tumor sample required to run analysis.",
"help_text": "A tumor BAM below this coverage value will fail the coverage threshold, and will not be processed in downstream analyses."
},
"normal_min_coverage": {
"title": "Normal minimum coverage",
"type": "number",
"default": 20,
"hidden": false,
"description": "Minimum read coverage for the normal sample required to run analysis.",
"help_text": "A normal BAM below this coverage value will fail the coverage threshold, and will not be processed in downstream analyses."
}
}
},
"snv_options": {
"title": "Small variant calling options",
"type": "object",
"description": "Options specific to the small variant calling subworkflow.",
"properties": {
"ctg_name": {
"type": "string",
"default": "EMPTY",
"description": "The name of the sequence to be processed.",
"hidden": true
},
"hybrid_mode_vcf": {
"type": "string",
"format": "file-path",
"description": "Enable hybrid calling mode that combines the *de novo* calling results and genotyping results at the positions in the VCF file given."
},
"genotyping_mode_vcf": {
"type": "string",
"format": "file-path",
"description": "VCF file input containing candidate sites to be genotyped. Variants will only be called at the sites in the VCF file if provided."
},
"normal_vcf": {
"title": "Pre-computed normal VCF",
"type": "string",
"format": "file-path",
"description": "VCF file input containing normal sites for the given sample.",
"help_text": "Pointing to a pre-computed normal VCF file will prevent the workflow from calling the germline sites for the normal sample, reducing processing time."
},
"skip_haplotype_filter": {
"title": "Skip haplotype filtering",
"type": "boolean",
"default": false,
"description": "Skip haplotype filtering of variants.",
"help_text": "Setting this will skip haplotype filtering of variants."
},
"fast_mode": {
"title": "Fast mode",
"type": "boolean",
"default": false,
"description": "Fast germline variants calling in Clair3 (does not emit germline calls).",
"help_text": "Setting this will speed up the germline calling from Clair3 by relaxing the variant calling parameters; this matches ClairS default behaviour, and therefore will not emit germline VCFs."
},
"snv_min_af": {
"type": "number",
"default": 0.05,
"description": "Minimum SNP AF required for a candidate variant.",
"hidden": true
},
"min_contig_size": {
"type": "number",
"default": 0.0,
"description": "Contigs with contig size < min_contig_size are filtered.",
"hidden": true
},
"min_qual": {
"type": "number",
"default": 8.0,
"description": "Variants with QUAL < min_qual are soft filtered.",
"hidden": true
},
"min_cov": {
"type": "number",
"default": 4.0,
"description": "Minimum coverage required to call somatic variants.",
"hidden": true
},
"min_bq": {
"type": "number",
"description": "Minimum base quality for candidate somatic variants calling.",
"hidden": true
},
"indel_min_af": {
"type": "number",
"default": 0.05,
"description": "Minimum somatic indel allelic frequency (if the model is r9, this will be automatically set to 1.00).",
"hidden": true
},
"clair3_min_mq": {
"type": "number",
"default": 5.0,
"description": "Minimum map quality to call germline variants.",
"hidden": true
},
"clair3_ref_pct_full": {
"type": "number",
"default": 0.1,
"description": "Expected percentage of low quality 0/0 variants called in the pileup mode for full-alignment mode calling.",
"hidden": true
},
"clair3_var_pct_full": {
"type": "number",
"default": 0.7,
"description": "Expected percentage of low quality 0/1 and 1/1 variants called in the pileup mode for full-alignment mode calling.",
"hidden": true
},
"clair3_base_err": {
"type": "number",
"default": 0.001,
"hidden": true,
"description": "Estimated base error rate when enabling GVCF option (experimental).",
"help_text": "Relevant only if running Clair3 in GVCF mode."
},
"clair3_gq_bin_size": {
"type": "number",
"default": 5,
"hidden": true,
"description": "Default gq bin size for merge non-variant block when enabling GVCF option (experimental).",
"help_text": "Relevant only if running Clair3 in GVCF mode."
},
"germline": {
"type": "boolean",
"title": "Call germline sites",
"default": true,
"description": "The workflow will perform germline calling and tumor phasing as default; set to false to disable this (greatly speeds up execution)."
},
"phase_normal": {
"title": "Phase normal sample",
"type": "boolean",
"default": false,
"description": "Phase and tag the normal, in addition to the tumor dataset."
},
"clair3_phase_vcf": {
"type": "boolean",
"default": false,
"hidden": true,
"description": "Enable to output phasing information in the output VCF.",
"help_text": "By default the final VCF output by the workflow is not phased, although some intermediates are approximately phased."
},
"print_germline_calls": {
"type": "boolean",
"default": false,
"hidden": true,
"description": "Save germline calls in the VCF file."
},
"print_ref_calls": {
"type": "boolean",
"default": false,
"hidden": true,
"description": "Save the homozygote reference calls in the VCF file."
},
"use_longphase_intermediate": {
"type": "boolean",
"default": true,
"hidden": true,
"description": "Use longphase in intermediate phasing steps."
},
"use_longphase": {
"type": "boolean",
"default": true,
"hidden": true,
"description": "Use longphase in phasing steps."
},
"use_longphase_haplotag": {
"type": "boolean",
"default": true,
"hidden": true,
"description": "Use longphase in haplotagging step."
},
"use_normal_hets_for_phasing": {
"type": "boolean",
"default": true,
"hidden": true,
"description": "Use normal heterozygote sites for variant phasing",
"help_text": "As of version 0.2.0, ClairS uses the normal sites to perform the variant phasing"
},
"use_tumor_hets_for_phasing": {
"type": "boolean",
"default": false,
"hidden": true,
"description": "Use normal heterozygote sites for variant phasing",
"help_text": "As of version 0.2.0, ClairS uses the normal sites to perform the variant phasing; to revert to use the tumor sites, set this variable to true"
},
"use_het_indels_for_phasing": {
"type": "boolean",
"default": true,
"hidden": true,
"description": "Use heterozygote indels sites for variant phasing",
"help_text": "As of version 0.2.0, ClairS uses the heterozygot indels sites to perform the variant phasing as default; to disable this behaviour, set this variable to false"
},
"liquid_tumor": {
"type": "boolean",
"default": false,
"description": "The sample is a liquid tumor",
"help_text": "Setting this to true will have ClairS to use specific presets and model (where available) for liquid tumors, increasing accuracy."
},
"clairs_debug": {
"type": "boolean",
"hidden": true,
"default": false,
"description": "Run ClairS in debug mode."
},
"clairs_to_min_bq": {
"type": "number",
"default": 20.0,
"description": "Minimum base quality for ClairS-TO candidate selection.",
"hidden": true
},
"clairs_to_qual": {
"type": "integer",
"hidden": true,
"default": 12,
"description": "Minimum quality for intermediate steps in ClairS-TO."
},
"qual_cutoff_phaseable_region": {
"type": "integer",
"hidden": true,
"default": 14,
"description": "Quality cut-off for phaseable regions in intermediate steps of ClairS-TO."
},
"qual_cutoff_unphaseable_region": {
"type": "integer",
"hidden": true,
"default": 20,
"description": "Quality cut-off for unphaseable regions in intermediate steps of ClairS-TO."
},
"vcf_fn": {
"type": "string",
"default": "EMPTY",
"description": "Candidate sites VCF file input, variants will only be called at the sites in the VCF file if provided.",
"hidden": true
}
}
},
"sv_calling": {
"title": "Somatic structural variant calling options",
"type": "object",
"fa_icon": "fas fa-arrow-left",
"description": "Parameters for tweaking the run of the SV module.",
"properties": {
"min_sv_length": {
"title": "Minimum SV size",
"type": "integer",
"default": 50,
"description": "Minimum SV size to call.",
"help_text": "Provide the minimum size of the structural variants to call with severus."
},
"min_support": {
"title": "Minimum read support",
"type": "integer",
"default": 3,
"minimum": 0,
"hidden": true,
"description": "Call a site if there are at least this many reads supporting the SV.",
"help_text": "If a site has more at least this many reads supporting the variant, the site is called by `Severus`."
},
"vaf_threshold": {
"title": "Variant allele frequency threshold",
"type": "number",
"minimum": 0,
"maximum": 1,
"hidden": true,
"description": "Somatic SVs with a variant allele frequency (VAF) below this value are filtered out.",
"help_text": "If a site has a VAF below this value, then `Severus` will not report it in the output VCF."
},
"severus_args": {
"title": "Severus additional arguments",
"type": "string",
"description": "The additional options for `Severus`.",
"hidden": true,
"help_text": "This is an advanced option to allow running `Severus` with custom [settings](https://github.com/KolmogorovLab/Severus?tab=readme-ov-file#inputs-and-parameters). The arguments specified in this option will fully override all options set by the workflow. To provide custom arguments to `Severus` from command line proceed as follow: `--severus_args=\"--preset traditional\"`"
}
}
},
"mod_options": {
"title": "Methylation calling options",
"type": "object",
"description": "Options specific to the methyl calling subworkflow.",
"properties": {
"force_strand": {
"title": "Force strand",
"type": "boolean",
"default": false,
"description": "Require modkit to call strand-aware modifications.",
"help_test": "By default strand calls are collapsed (strand reported as '.'). Enabling this will force stranding to be considered when calling modifications, creating one output per modification per strand and the report will be tabulated by both modification and strand."
},
"diff_mod": {
"title": "Run differential modified base analysis",
"type": "boolean",
"default": true,
"description": "Detect differentially modified loci and regions with DSS.",
"help_test": "By default the workflow will run DSS to detect differentially modified loci and regions. DSS can be computationally intensive and can therefore be disabled by setting this to false."
},
"modkit_args": {
"title": "Modkit additional arguments",
"type": "string",
"description": "The additional options for modkit.",
"hidden": true,
"help_text": "This is an advanced option to allow running modkit with custom settings. The arguments specified in this option will fully override all options set by the workflow. To provide custom arguments to `modkit` from command line proceed as follow: `--modkit_args=\"--preset traditional\"`"
}
}
},
"multiprocessing_options": {
"title": "Multiprocessing Options",
"type": "object",
"fa_icon": "far fa-gauge-high",
"description": "Options for configuring the common processes across the different subworkflows.",
"help_text": "These options do not need to be changed for typical use, but allow fine tuning of workflows for users who want more control over the workflow.",
"properties": {
"ubam_map_threads": {
"type": "integer",
"default": 8,
"description": "Set max number of threads to use for aligning reads from uBAM (limited by config executor cpus)."
},
"ubam_sort_threads": {
"type": "integer",
"default": 3,
"description": "Set max number of threads to use for sorting and indexing aligned reads from uBAM (limited by config executor cpus)."
},
"ubam_bam2fq_threads": {
"type": "integer",
"default": 1,
"description": "Set max number of threads to use for uncompressing uBAM and generating FASTQ for alignment (limited by config executor cpus)."
},
"severus_threads": {
"type": "integer",
"default": 8,
"minimum": 4,
"description": "Total number of threads to use for `Severus` (minimum of 4 and limited by config executor cpus)."
},
"dss_threads": {
"type": "integer",
"default": 1,
"maximum": 4,
"description": "Total number of threads to use in the DSS differential modification analysis (limited by config executor cpus).",
"help_test": "The DSS R Package step identifies differentially modified loci and regions, a computationally intensive step. Increasing this parameter speeds up the analysis, at the cost of significantly increased memory requirements."
},
"modkit_threads": {
"type": "integer",
"default": 4,
"description": "Total number of threads to use in modkit modified base calling (limited by config executor cpus)."
},
"haplotype_filter_threads": {
"type": "integer",
"default": 4,
"description": "Set max number of threads to use for the haplotype filtering stage in SNV workflow (limited by config executor cpus)."
}
}
},
"advanced_options": {
"title": "Advanced Options",
"type": "object",
"fa_icon": "far fa-question-circle",
"description": "Advanced options for configuring processes inside the workflow.",
"help_text": "These advanced options do not need to be changed for typical use, but allow fine tuning of workflows for users who want more control over the workflow.",
"properties": {
"GVCF": {
"type": "boolean",
"default": false,
"hidden": true,
"description": "Enable to output a gVCF file in addition to the VCF outputs (experimental).",
"help_text": "By default the the workflow outputs a VCF file containing only records where a variant has been detected. Enabling this option will output additionally a gVCF with records spanning all reference positions regardless of whether a variant was detected in the sample."
},
"override_basecaller_cfg": {
"title": "Basecaller configuration",
"type": "string",
"description": "Name of the model to use for converting signal and selecting a small variant calling model.",
"help_text": "The workflow will attempt to find the basecaller model from the headers of your input data, providing a value for this option will override the model found in the data. If the model cannot be found in the header, it must be provided with this option as the basecaller model is required for small variant calling. The basecaller model is used to automatically select the appropriate small variant calling model. The model list shows all models that are compatible for small variant calling with this workflow. You should select 'custom' to override the basecaller_cfg with clair3_model_path.",
"enum": [
"dna_r9.4.1_450bps_hac",
"dna_r9.4.1_450bps_hac_prom"
]
}
}
},
"misc": {
"title": "Miscellaneous Options",
"type": "object",
"description": "Everything else.",
"default": "",
"properties": {
"disable_ping": {
"type": "boolean",
"default": false,
"description": "Enable to prevent sending a workflow ping."
},
"help": {
"type": "boolean",
"description": "Display help text.",
"fa_icon": "fas fa-question-circle",
"default": false,
"hidden": true
},
"version": {
"type": "boolean",
"description": "Display version and exit.",
"fa_icon": "fas fa-question-circle",
"default": false,
"hidden": true
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/workflow"
},
{
"$ref": "#/definitions/input"
},
{
"$ref": "#/definitions/snv_options"
},
{
"$ref": "#/definitions/sv_calling"
},
{
"$ref": "#/definitions/mod_options"
},
{
"$ref": "#/definitions/advanced_options"
},
{
"$ref": "#/definitions/multiprocessing_options"
},
{
"$ref": "#/definitions/qc_options"
},
{
"$ref": "#/definitions/sv_calling"
},
{
"$ref": "#/definitions/misc"
}
],
"properties": {
"aws_image_prefix": {
"type": "string",
"hidden": true
},
"aws_queue": {
"type": "string",
"hidden": true
},
"monochrome_logs": {
"type": "boolean"
},
"validate_params": {
"type": "boolean",
"default": true
},
"show_hidden_params": {
"type": "boolean"
}
},
"resources": {
"recommended": {
"cpus": 64,
"memory": "256GB"
},
"minimum": {
"cpus": 16,
"memory": "48GB"
},
"run_time": "Variable depending on sequencing modality (targeted or whole genome sequencing), as well as coverage and the individual analyses requested. For instance, a complete analysis of a 60X/30X Tumor/Normal pair with default settings takes approximately 6h 30m using the recommended requirements.",
"arm_support": false
}
}