-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathnextflow_schema.json
420 lines (420 loc) · 23.4 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
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/birneylab/stitchimpute/master/nextflow_schema.json",
"title": "birneylab/stitchimpute pipeline parameters",
"description": "A pipeline for imputing genotypes using STITCH, evaluating imputation performance against a ground truth, optimising imputation parameters, and refining the SNP set used",
"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.",
"required": ["input", "outdir"],
"properties": {
"input": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/csv",
"pattern": "^\\S+\\.csv$",
"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. See [usage docs](https://github.com/birneylab/stitchimpute/usage#samplesheet-input).",
"fa_icon": "fas fa-file-csv"
},
"mode": {
"type": "string",
"default": "imputation",
"fa_icon": "fas fa-hand-pointer",
"description": "Which branch of the pipeline to run. Can be `imputation`, `grid_search`, or `snp_set_refinement`",
"enum": ["imputation", "grid_search", "snp_set_refinement"]
},
"outdir": {
"type": "string",
"format": "directory-path",
"description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
"fa_icon": "fas fa-folder-open"
},
"skip_chr": {
"type": "string",
"fa_icon": "fas fa-align-justify",
"help_text": "Chromosomes from the reference provided that should not be imputed. Multiple chromosomes can be separated by commas. Es. \"1,2,3\".",
"description": "Chromosomes to skip"
},
"grid_search_params": {
"type": "string",
"fa_icon": "fas fa-file-csv",
"description": "CSV files containing the values of the K and nGen parameters to be used for the grid search workflow",
"format": "file-path",
"mimetype": "text/csv",
"help_text": "Must have column names `K` and `nGen`. Each line corresponds to a combination of parameters to be tested."
},
"snp_filtering_criteria": {
"type": "string",
"fa_icon": "fas fa-file-csv",
"description": "CSV file containing the threshold for inclusion of SNPs in the iterative refinement process",
"format": "file-path",
"mimetype": "text/csv",
"help_text": "By default the `info_score` value of the SNP is used for filtering if a ground truth is not provided, and the Pearson r^2 if a ground truth is provided. This can be changed with the `filter_var` parameter."
},
"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})$"
}
}
},
"stitch_options": {
"title": "Stitch options",
"type": "object",
"description": "",
"default": "",
"properties": {
"stitch_posfile": {
"type": "string",
"help_text": "Where to find file with positions to run. File is tab seperated with no header, one row per SNP, with col 1 = chromosome, col 2 = physical position (sorted from smallest to largest), col 3 = reference base, col 4 = alternate base. Bases are capitalized. Example first row: 1\t1000\tA\tG",
"format": "file-path",
"mimetype": "text/tab-separated-values",
"fa_icon": "fas fa-file-alt",
"description": "Positions to run the imputation over"
},
"stitch_K": {
"type": "integer",
"fa_icon": "fas fa-hand-point-up",
"help_text": "See STITCH documentation for more details. Required for imputation mode.",
"minimum": 1,
"description": "Number of ancestral haplotypes"
},
"stitch_nGen": {
"type": "integer",
"fa_icon": "fas fa-hand-pointer",
"help_text": "See STITCH documentation for more details. Required for imputation mode.",
"minimum": 1,
"description": "Number of generations since founding of the population"
}
},
"required": ["stitch_posfile"],
"fa_icon": "fas fa-dna"
},
"reference_genome_options": {
"title": "Reference genome options",
"type": "object",
"fa_icon": "fas fa-dna",
"description": "Reference genome related files and options required for the workflow.",
"properties": {
"genome": {
"type": "string",
"description": "Name of iGenomes reference.",
"fa_icon": "fas fa-book",
"help_text": "If using a reference genome configured in the pipeline using iGenomes, use this parameter to give the ID for the reference. This is then used to build the full paths for all required reference genome files e.g. `--genome GRCh38`. \n\nSee the [nf-core website docs](https://nf-co.re/usage/reference_genomes) for more details."
},
"fasta": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$",
"description": "Path to FASTA genome file.",
"help_text": "This parameter is *mandatory* if `--genome` is not specified. If you don't have a BWA index available this will be generated for you automatically. Combine with `--save_reference` to save BWA index for future runs.",
"fa_icon": "far fa-file-code"
},
"igenomes_base": {
"type": "string",
"format": "directory-path",
"description": "Directory / URL base for iGenomes references.",
"default": "s3://ngi-igenomes/igenomes",
"fa_icon": "fas fa-cloud-download-alt",
"hidden": true
},
"igenomes_ignore": {
"type": "boolean",
"description": "Do not load the iGenomes reference config.",
"fa_icon": "fas fa-ban",
"hidden": true,
"help_text": "Do not load `igenomes.config` when running the pipeline. You may choose this option if you observe clashes between custom parameters and those supplied in `igenomes.config`."
}
}
},
"ground_truth": {
"title": "Ground truth",
"type": "object",
"description": "",
"default": "",
"help_text": "",
"properties": {
"ground_truth_vcf": {
"type": "string",
"fa_icon": "fas fa-file",
"description": "VCF file with ground truth calls",
"help_text": "Accepted format are vcf, vcf.gz, and bcf. Sample names must be identical to the sample names in the SM tag of the cram indicated in the samplesheet. Used to calculate correlation with the imputation results. Must contain FORMAT/DP and FORMAT/PL tags for all the variants.",
"format": "file-path"
},
"freq_vcf": {
"type": "string",
"fa_icon": "fas fa-file",
"description": "VCF file used to calculate allele frequencies. If not specified the realised frequencies in the imputation set are used.",
"help_text": "Accepted format are vcf, vcf.gz, and bcf. It is used by GLIMPSE concordance for determining MAF bins. Must contain an INFO/AF field or the field declared with --af-tag in GLIMPSE2_CONCORDANCE",
"format": "file-path"
},
"downsample_coverage": {
"type": "number",
"description": "To what average depth should the ground truth cram files be downsampled to?",
"help_text": "To what average depth should the ground truth cram files be downsampled to? If not specidied no downsampling is done. Must be a numeric value."
},
"random_seed": {
"type": "integer",
"description": "Random seed used for downsampling"
},
"filter_var": {
"type": "string",
"enum": ["info_score", "r2"],
"description": "Perfromance metric used in filtering"
},
"glimpse2_concordance_bins": {
"type": "string",
"default": "0 0.05 0.10 0.15 0.20 0.25 0.30 0.35 0.40 0.45 0.5",
"fa_icon": "far fa-check-circle",
"hidden": true,
"description": "MAF bins for calculating validation performance",
"help_text": "Allele frequency bins used for r^2 computations. By default they should as MAF bins [0-0.5], while they should take the full range [0-1] if \u2013use-ref-alt is used."
},
"glimpse2_concordance_allele_counts": {
"type": "string",
"fa_icon": "far fa-check-circle",
"hidden": true,
"help_text": "Default allele count bins used for rsquared computations. AN field must be defined in the frequency file.",
"description": "Use default allele count bins"
},
"glimpse2_concordance_ac_bins": {
"type": "string",
"fa_icon": "far fa-check-circle",
"hidden": true,
"help_text": "User-defined allele count bins used for rsquared computations.",
"description": "User-defined allele count bins"
},
"glimpse2_min_val_gl": {
"type": "integer",
"default": 0,
"fa_icon": "far fa-check-circle",
"description": "Minimum genotype likelihood probability P(G|R) in validation data [set to zero to have no filter of if using \u2013gt-validation]",
"hidden": true
},
"glimpse2_min_val_dp": {
"type": "integer",
"default": 0,
"fa_icon": "far fa-check-circle",
"description": "Minimum coverage in validation data. If FORMAT/DP is missing and \u2013minDP > 0, the program exits with an error. [set to zero to have no filter of if using \u2013gt-validation]",
"hidden": true
},
"glimpse2_groups": {
"type": "string",
"hidden": true,
"format": "file-path",
"fa_icon": "fas fa-file",
"description": "Alternative to frequency bins: group bins are user defined, provided in a file."
},
"glimpse2_samples": {
"type": "string",
"fa_icon": "fas fa-file",
"hidden": true,
"format": "file-path",
"description": "List of samples to process, one sample ID per line."
}
},
"fa_icon": "fas fa-check"
},
"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"
},
"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": 16,
"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": "128.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": "240.h",
"fa_icon": "far fa-clock",
"pattern": "^(\\d+\\.?\\s*(s|m|h|d|day)\\s*)+$",
"hidden": true,
"help_text": "Use to set an upper-limit for the time requirement for each process. Should be a string in the format integer-unit e.g. `--max_time '2.h'`"
}
}
},
"generic_options": {
"title": "Generic options",
"type": "object",
"fa_icon": "fas fa-file-import",
"description": "Less common options for the pipeline, typically set in a config file.",
"help_text": "These options are common to all nf-core pipelines and allow you to customise some of the core preferences for how the pipeline runs.\n\nTypically these options would be set in a Nextflow config file loaded for all pipeline runs, such as `~/.nextflow/config`.",
"properties": {
"help": {
"type": "boolean",
"description": "Display help text.",
"fa_icon": "fas fa-question-circle",
"hidden": true
},
"version": {
"type": "boolean",
"description": "Display version and exit.",
"fa_icon": "fas fa-question-circle",
"hidden": true
},
"publish_dir_mode": {
"type": "string",
"default": "copy",
"description": "Method used to save pipeline results to output directory.",
"help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.",
"fa_icon": "fas fa-copy",
"enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"],
"hidden": true
},
"email_on_fail": {
"type": "string",
"description": "Email address for completion summary, only when pipeline fails.",
"fa_icon": "fas fa-exclamation-triangle",
"pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$",
"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
},
"monochrome_logs": {
"type": "boolean",
"description": "Do not use coloured log outputs.",
"fa_icon": "fas fa-palette",
"hidden": true
},
"hook_url": {
"type": "string",
"description": "Incoming hook URL for messaging service",
"fa_icon": "fas fa-people-group",
"help_text": "Incoming hook URL for messaging service. Currently, MS Teams and Slack are supported.",
"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
},
"validationShowHiddenParams": {
"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."
},
"validationFailUnrecognisedParams": {
"type": "boolean",
"fa_icon": "far fa-check-circle",
"description": "Validation of parameters fails when an unrecognised parameter is found.",
"hidden": true,
"help_text": "By default, when an unrecognised parameter is found, it returns a warinig."
},
"validationLenientMode": {
"type": "boolean",
"fa_icon": "far fa-check-circle",
"description": "Validation of parameters in lenient more.",
"hidden": true,
"help_text": "Allows string values that are parseable as numbers or booleans. For further information see [JSONSchema docs](https://github.com/everit-org/json-schema#lenient-mode)."
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/input_output_options"
},
{
"$ref": "#/definitions/stitch_options"
},
{
"$ref": "#/definitions/reference_genome_options"
},
{
"$ref": "#/definitions/ground_truth"
},
{
"$ref": "#/definitions/institutional_config_options"
},
{
"$ref": "#/definitions/max_job_request_options"
},
{
"$ref": "#/definitions/generic_options"
}
]
}