-
Notifications
You must be signed in to change notification settings - Fork 5
/
nextflow_schema.json
615 lines (615 loc) · 28.1 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
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/beiko-lab/ARETE/master/nextflow_schema.json",
"title": "beiko-lab/ARETE pipeline parameters",
"description": "AMR/VF LGT-focused bacterial genomics workflow",
"type": "object",
"definitions": {
"input_output_options": {
"title": "Input/output options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Define where the pipeline should find input data and save output data.",
"properties": {
"input_sample_table": {
"type": "string",
"format": "file-path",
"mimetype": "text/csv",
"pattern": "^\\S+\\.csv$",
"schema": "assets/schema_input.json",
"description": "Path to comma-separated file containing information about the samples in the experiment.",
"help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row.",
"fa_icon": "fas fa-file-csv"
},
"outdir": {
"type": "string",
"description": "Path to the output directory where the results will be saved.",
"default": "./results",
"fa_icon": "fas fa-folder-open"
},
"db_cache": {
"type": "string",
"fa_icon": "fas fa-database",
"description": "Directory where the databases are located"
},
"email": {
"type": "string",
"description": "Email address for completion summary.",
"fa_icon": "fas fa-envelope",
"help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
"pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
},
"multiqc_title": {
"type": "string",
"description": "MultiQC report title. Printed as page header, used for filename if not otherwise specified.",
"fa_icon": "fas fa-file-signature"
}
}
},
"reference_genome_options": {
"title": "Reference genome options",
"type": "object",
"fa_icon": "fas fa-dna",
"description": "Reference and outgroup genome fasta files required for the workflow.",
"properties": {
"reference_genome": {
"type": "string",
"fa_icon": "fas fa-file-code",
"description": "Path to FASTA reference genome file."
}
}
},
"qc": {
"title": "QC",
"type": "object",
"description": "",
"default": "",
"fa_icon": "fas fa-eye",
"properties": {
"run_checkm": {
"type": "boolean",
"fa_icon": "fas fa-check-double",
"description": "Run CheckM QC software"
},
"apply_filtering": {
"type": "boolean",
"fa_icon": "fas fa-filter",
"description": "Filter assemblies on QC results"
},
"skip_kraken": {
"type": "boolean",
"description": "Don't run Kraken2 taxonomic classification",
"fa_icon": "fas fa-forward"
},
"min_n50": {
"type": "integer",
"default": 10000,
"description": "Minimum N50 for filtering",
"fa_icon": "fas fa-align-right"
},
"min_contigs_1000_bp": {
"type": "integer",
"default": 1,
"description": "Minimum number of contigs with >1000bp",
"fa_icon": "fas fa-ellipsis-h"
},
"min_contig_length": {
"type": "integer",
"default": 1,
"description": "Minimum average contig length",
"fa_icon": "fas fa-ruler-horizontal"
}
}
},
"annotation": {
"title": "Annotation",
"type": "object",
"description": "Parameters for the annotation subworkflow",
"default": "",
"fa_icon": "fas fa-edit",
"properties": {
"annotation_tools": {
"type": "string",
"default": "mobsuite,rgi,cazy,vfdb,iceberg,bacmet,islandpath,phispy,report",
"fa_icon": "fas fa-tools",
"description": "Comma-separated list of annotation tools to run",
"pattern": "^((rgi|mobsuite|islandpath|phispy|vfdb|cazy|bacmet|iceberg|integronfinder|report)?,?)*(?<!,)$"
},
"bakta_db": {
"type": "string",
"fa_icon": "fas fa-database",
"description": "Path to the BAKTA database"
},
"use_prokka": {
"type": "boolean",
"fa_icon": "fas fa-bacterium",
"description": "Use Prokka (not Bakta) for annotating assemblies"
},
"min_pident": {
"type": "integer",
"default": 60,
"fa_icon": "fas fa-equals",
"description": "Minimum match identity percentage for filtering"
},
"min_qcover": {
"type": "number",
"default": 0.6,
"fa_icon": "fas fa-equals",
"description": "Minimum coverage of each match for filtering"
},
"skip_profile_creation": {
"type": "boolean",
"description": "Skip annotation feature profile creation",
"fa_icon": "fas fa-forward"
},
"feature_profile_columns": {
"type": "string",
"default": "mobsuite,rgi,cazy,vfdb,iceberg,bacmet",
"fa_icon": "fas fa-columns",
"description": "Columns to include in the feature profile",
"pattern": "^((rgi|mobsuite|vfdb|cazy|bacmet|iceberg)?,?)*(?<!,)$"
},
"upset_plot_columns": {
"type": "string",
"fa_icon": "fas fa-columns",
"description": "Columns to use for making Upset plots of genome features"
}
}
},
"phylogenomics": {
"title": "Phylogenomics",
"type": "object",
"description": "Parameters for the phylogenomics subworkflow",
"default": "",
"fa_icon": "fab fa-pagelines",
"properties": {
"skip_phylo": {
"type": "boolean",
"fa_icon": "fas fa-forward",
"description": "Skip Pangenomics and Phylogenomics subworkflow"
},
"use_ppanggolin": {
"type": "boolean",
"fa_icon": "fas fa-expand",
"description": "Use ppanggolin for calculating the pangenome"
},
"use_full_alignment": {
"type": "boolean",
"description": "Use full alignment",
"fa_icon": "fas fa-align-justify"
},
"use_fasttree": {
"type": "boolean",
"description": "Use FastTree",
"fa_icon": "fas fa-tree",
"default": true
},
"feature_dispersion_columns": {
"type": "string",
"fa_icon": "fas fa-columns",
"description": "Columns from the input samplesheet to use in the feature dispersion module"
}
}
},
"poppunk": {
"title": "PopPUNK",
"type": "object",
"description": "Parameters for the lineage subworkflow",
"default": "",
"fa_icon": "fas fa-object-group",
"properties": {
"skip_poppunk": {
"type": "boolean",
"description": "Skip PopPunk",
"fa_icon": "fas fa-forward"
},
"poppunk_model": {
"type": "string",
"description": "Which PopPunk model to use (bgmm, dbscan, refine, threshold or lineage)",
"fa_icon": "fas fa-indent"
},
"run_poppunk_qc": {
"type": "boolean",
"description": "Whether to run the QC step for PopPunk",
"fa_icon": "fas fa-industry"
},
"enable_subsetting": {
"type": "boolean",
"fa_icon": "fas fa-tasks",
"description": "Enable subsetting workflow based on genome similarity"
},
"core_similarity": {
"type": "number",
"default": 99.9,
"fa_icon": "fas fa-clone",
"description": "Similarity threshold for core genomes"
},
"accessory_similarity": {
"type": "number",
"default": 99.0,
"fa_icon": "far fa-clone",
"description": "Similarity threshold for accessory genes"
}
}
},
"gene_order": {
"title": "Gene Order",
"type": "object",
"description": "Parameters for the Gene Order Subworkflow",
"default": "",
"properties": {
"run_gene_order": {
"type": "boolean",
"description": "Whether to run the Gene Order subworkflow"
},
"input_file_path": {
"type": "string",
"default": "/home/jvfe/dev/dalhousie/arete/test/gene-order/rgi_input.txt",
"hidden": true
},
"gene_order_percent_cutoff": {
"type": "number",
"default": 0.25,
"description": "Cutoff percentage of genomes a gene should be present within to be included in extraction and subsequent analysis. Should a float between 0 and 1 (e.g., 0.25 means only genes present in a minimum of 25% of genomes are kept)."
},
"gene_order_label_cols": {
"type": "string",
"default": "None",
"description": "If using annotation files predicting features, list of space separated column names to be added to the gene names"
},
"num_neighbors": {
"type": "integer",
"default": 10,
"description": "Neighborhood size to extract. Should be an even number N, such that N/2 neighbors upstream and N/2 neighbors downstream will be analyzed."
},
"inflation": {
"type": "integer",
"default": 2,
"description": "Inflation hyperparameter value for Markov Clustering Algorithm."
},
"epsilon": {
"type": "number",
"default": 0.5,
"description": "Epsilon hyperparameter value for DBSCAN clustering."
},
"minpts": {
"type": "integer",
"default": 5,
"description": "Minpts hyperparameter value for DBSCAN clustering."
},
"plot_clustering": {
"type": "boolean",
"description": "Create Clustering HTML Plots"
}
},
"fa_icon": "fas fa-sort-numeric-down"
},
"recombination": {
"title": "Recombination",
"type": "object",
"description": "Parameters for the recombination subworkflow",
"default": "",
"fa_icon": "fab fa-pagelines",
"properties": {
"run_recombination": {
"type": "boolean",
"description": "Run Recombination",
"fa_icon": "fas fa-tree"
},
"run_verticall": {
"type": "boolean",
"default": true,
"description": "Run Verticall recombination tool"
},
"run_gubbins": {
"type": "boolean",
"description": "Run Gubbins recombination tool"
}
}
},
"dynamics": {
"title": "Dynamics",
"type": "object",
"description": "",
"default": "",
"properties": {
"run_evolccm": {
"type": "boolean",
"description": "Run the community coevolution model"
},
"run_rspr": {
"type": "boolean",
"description": "Run rSPR"
},
"min_rspr_distance": {
"type": "integer",
"default": 10,
"description": "Minimum rSPR distance used to define processing groups"
},
"min_branch_length": {
"type": "integer",
"default": 0,
"description": "Minimum rSPR branch length"
},
"max_support_threshold": {
"type": "number",
"default": 0.7,
"description": "Maximum rSPR support threshold"
},
"max_approx_rspr": {
"type": "integer",
"default": -1,
"description": "Maximum approximate rSPR distance for filtering"
},
"min_heatmap_approx_rspr": {
"type": "integer",
"default": 0,
"description": "Minimum approximate rSPR distance used to generate heatmap"
},
"max_heatmap_approx_rspr": {
"type": "integer",
"default": -1,
"description": "Maximum approximate rSPR distance used to generate heatmap"
},
"min_heatmap_exact_rspr": {
"type": "integer",
"default": 0,
"description": "Minimum exact rSPR distance used to generate heatmap"
},
"max_heatmap_exact_rspr": {
"type": "integer",
"default": -1,
"description": "Maximum exact rSPR distance used to generate heatmap"
},
"core_gene_tree": {
"type": "string",
"description": "Core (or reference) genome tree. Used in the rSPR and evolCCM entries."
},
"concatenated_annotation": {
"type": "string",
"description": "TSV table of annotations for all genomes. Such as the ones generated by Bakta or Prokka in ARETE."
},
"feature_profile": {
"type": "string",
"description": "Feature profile TSV (A presence-absence matrix). Used in the evolCCM entry."
}
},
"fa_icon": "fas fa-bezier-curve"
},
"institutional_config_options": {
"title": "Institutional config options",
"type": "object",
"fa_icon": "fas fa-university",
"description": "Parameters used to describe centralised config profiles. These should not be edited.",
"help_text": "The centralised nf-core configuration profiles use a handful of pipeline parameters to describe themselves. This information is then printed to the Nextflow log when you run a pipeline. You should not need to change these values when you run a pipeline.",
"properties": {
"custom_config_version": {
"type": "string",
"description": "Git commit id for Institutional configs.",
"default": "master",
"hidden": true,
"fa_icon": "fas fa-users-cog"
},
"custom_config_base": {
"type": "string",
"description": "Base directory for Institutional configs.",
"default": "https://raw.githubusercontent.com/nf-core/configs/master",
"hidden": true,
"help_text": "If you're running offline, Nextflow will not be able to fetch the institutional config files from the internet. If you don't need them, then this is not a problem. If you do need them, you should download the files from the repo and tell Nextflow where to find them with this parameter.",
"fa_icon": "fas fa-users-cog"
},
"hostnames": {
"type": "string",
"description": "Institutional configs hostname.",
"hidden": true,
"fa_icon": "fas fa-users-cog"
},
"config_profile_name": {
"type": "string",
"description": "Institutional config name.",
"hidden": true,
"fa_icon": "fas fa-users-cog"
},
"config_profile_description": {
"type": "string",
"description": "Institutional config description.",
"hidden": true,
"fa_icon": "fas fa-users-cog"
},
"config_profile_contact": {
"type": "string",
"description": "Institutional config contact information.",
"hidden": true,
"fa_icon": "fas fa-users-cog"
},
"config_profile_url": {
"type": "string",
"description": "Institutional config URL link.",
"hidden": true,
"fa_icon": "fas fa-users-cog"
}
}
},
"max_job_request_options": {
"title": "Max job request options",
"type": "object",
"fa_icon": "fab fa-acquisitions-incorporated",
"description": "Set the top limit for requested resources for any single job.",
"help_text": "If you are running on a smaller system, a pipeline step requesting more resources than are available may cause the Nextflow to stop the run with an error. These options allow you to cap the maximum resources requested by any single job so that the pipeline will run on your system.\n\nNote that you can not _increase_ the resources requested by any job using these options. For that you will need your own configuration file. See [the nf-core website](https://nf-co.re/usage/configuration) for details.",
"properties": {
"max_cpus": {
"type": "integer",
"description": "Maximum number of CPUs that can be requested for any single job.",
"default": 72,
"fa_icon": "fas fa-microchip",
"hidden": true,
"help_text": "Use to set an upper-limit for the CPU requirement for each process. Should be an integer e.g. `--max_cpus 1`"
},
"max_memory": {
"type": "string",
"description": "Maximum amount of memory that can be requested for any single job.",
"default": "125.GB",
"fa_icon": "fas fa-memory",
"pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
"hidden": true,
"help_text": "Use to set an upper-limit for the memory requirement for each process. Should be a string in the format integer-unit e.g. `--max_memory '8.GB'`"
},
"max_time": {
"type": "string",
"description": "Maximum amount of time that can be requested for any single job.",
"default": "168.h",
"fa_icon": "far fa-clock",
"pattern": "^(\\d+\\.?\\s*(s|m|h|day)\\s*)+$",
"hidden": true,
"help_text": "Use to set an upper-limit for the time requirement for each process. Should be a string in the format integer-unit e.g. `--max_time '2.h'`"
}
}
},
"generic_options": {
"title": "Generic options",
"type": "object",
"fa_icon": "fas fa-file-import",
"description": "Less common options for the pipeline, typically set in a config file.",
"help_text": "These options are common to all nf-core pipelines and allow you to customise some of the core preferences for how the pipeline runs.\n\nTypically these options would be set in a Nextflow config file loaded for all pipeline runs, such as `~/.nextflow/config`.",
"properties": {
"help": {
"type": "boolean",
"description": "Display help text.",
"fa_icon": "fas fa-question-circle",
"hidden": true
},
"publish_dir_mode": {
"type": "string",
"default": "copy",
"description": "Method used to save pipeline results to output directory.",
"help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.",
"fa_icon": "fas fa-copy",
"enum": [
"symlink",
"rellink",
"link",
"copy",
"copyNoFollow",
"move"
],
"hidden": true
},
"email_on_fail": {
"type": "string",
"description": "Email address for completion summary, only when pipeline fails.",
"fa_icon": "fas fa-exclamation-triangle",
"pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$",
"help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
"hidden": true
},
"plaintext_email": {
"type": "boolean",
"description": "Send plain-text email instead of HTML.",
"fa_icon": "fas fa-remove-format",
"hidden": true
},
"max_multiqc_email_size": {
"type": "string",
"description": "File size limit when attaching MultiQC reports to summary emails.",
"pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
"default": "25.MB",
"fa_icon": "fas fa-file-upload",
"hidden": true
},
"monochrome_logs": {
"type": "boolean",
"description": "Do not use coloured log outputs.",
"fa_icon": "fas fa-palette",
"hidden": true
},
"multiqc_config": {
"type": "string",
"description": "Custom config file to supply to MultiQC.",
"fa_icon": "fas fa-cog",
"hidden": true
},
"tracedir": {
"type": "string",
"description": "Directory to keep pipeline Nextflow logs and reports.",
"default": "${params.outdir}/pipeline_info",
"fa_icon": "fas fa-cogs",
"hidden": true
},
"validate_params": {
"type": "boolean",
"description": "Boolean whether to validate parameters against the schema at runtime",
"default": true,
"fa_icon": "fas fa-check-square",
"hidden": true
},
"show_hidden_params": {
"type": "boolean",
"fa_icon": "far fa-eye-slash",
"description": "Show all params when using `--help`",
"hidden": true,
"help_text": "By default, parameters set as _hidden_ in the schema are not shown on the command line when a user runs with `--help`. Specifying this option will tell the pipeline to show all parameters."
},
"enable_conda": {
"type": "boolean",
"description": "Run this workflow with Conda. You can also use '-profile conda' instead of providing this parameter.",
"hidden": true,
"fa_icon": "fas fa-bacon"
},
"singularity_pull_docker_container": {
"type": "boolean",
"description": "Instead of directly downloading Singularity images for use with Singularity, force the workflow to pull and convert Docker containers instead.",
"hidden": true,
"fa_icon": "fas fa-toolbox",
"help_text": "This may be useful for example if you are unable to directly pull Singularity containers to run the pipeline due to http/https proxy issues."
},
"schema_ignore_params": {
"type": "string",
"default": "genomes,modules"
},
"multiqc_logo": {
"type": "string",
"fa_icon": "fas fa-image",
"hidden": true
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/input_output_options"
},
{
"$ref": "#/definitions/reference_genome_options"
},
{
"$ref": "#/definitions/qc"
},
{
"$ref": "#/definitions/annotation"
},
{
"$ref": "#/definitions/phylogenomics"
},
{
"$ref": "#/definitions/poppunk"
},
{
"$ref": "#/definitions/gene_order"
},
{
"$ref": "#/definitions/recombination"
},
{
"$ref": "#/definitions/dynamics"
},
{
"$ref": "#/definitions/institutional_config_options"
},
{
"$ref": "#/definitions/max_job_request_options"
},
{
"$ref": "#/definitions/generic_options"
}
]
}