-
Notifications
You must be signed in to change notification settings - Fork 0
/
nextflow_schema.json
398 lines (398 loc) · 21.6 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
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/birneylab/flexlmm/master/nextflow_schema.json",
"title": "birneylab/flexlmm pipeline parameters",
"description": "Flexible linear mixed model framework for Genome Wide Association Studies",
"type": "object",
"definitions": {
"genotype_options": {
"title": "Genotype options",
"type": "object",
"description": "Different format options for the input genotypes.",
"default": "",
"properties": {
"vcf": {
"type": "string",
"fa_icon": "fas fa-file",
"description": "Input genotypes in vcf format. Can be bgzip compressed.",
"pattern": ".*.[vcf,vcf.gz]",
"format": "file-path"
},
"bcf": {
"type": "string",
"description": "Input genotypes in bcf format. Can be bgzip compressed.",
"fa_icon": "fas fa-file"
},
"bgen": {
"type": "string",
"description": "Input genotypes in Oxford bgen format. Requires also gen and sample files to be specified..",
"fa_icon": "fas fa-file"
},
"sample": {
"type": "string",
"description": "sample file for Oxford bgen input format",
"fa_icon": "fas fa-file"
},
"bed": {
"type": "string",
"description": "Input genotypes in bed format. Requires also bim and fam files to be specified.",
"fa_icon": "fas fa-file"
},
"bim": {
"type": "string",
"description": "bim file for bed input format",
"fa_icon": "fas fa-file"
},
"fam": {
"type": "string",
"description": "fam file for bed input format",
"fa_icon": "fas fa-file"
},
"ped": {
"type": "string",
"description": "Input genotypes in ped format. Requires also map_f files to be specified.",
"fa_icon": "fas fa-file"
},
"map_f": {
"type": "string",
"description": "map file for ped input format",
"fa_icon": "fas fa-file"
},
"pgen": {
"type": "string",
"description": "Input genotypes in pgen format. Requires also pvar and psam files to be specified.",
"fa_icon": "fas fa-file"
},
"psam": {
"type": "string",
"description": "psam file for pgen input format",
"fa_icon": "fas fa-file"
},
"pvar": {
"type": "string",
"description": "pvar file for pgen input format",
"fa_icon": "fas fa-file"
}
},
"help_text": "Only one combination among the following is allowed:\nvcf\nbcf\nbgen, gen, sample\npgen, pvar, pvar\nbed, bim, fam\nped, map"
},
"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": ["outdir", "pheno"],
"properties": {
"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"
},
"pheno": {
"type": "string",
"description": "Phenotype file in PLINK2 format",
"format": "file-path",
"mimetype": "text/tsv",
"fa_icon": "fas fa-file",
"help_text": "The first columns must be either FID/IID or just IID (in which case the FID is assumed to be 0). A primary header line is required and it should begin with 'FID', '#FID', 'IID', or '#IID'). Differently from the plink2 format, additional header lines (beginning with '#', not immediately followed by 'FID'/'IID') are NOT permitted before the primary header line. \n\nIID must match sample names in `vcf`. FID is tolerated but not used. Missing values should be specified as NA and not following plink2 conventions (i.e. -9 is NOT seen as missing).\n\nSee an [example file](../assets/test_data/tsv/pheno.tsv)"
},
"covar": {
"type": "string",
"description": "Categorical covariates. Same format as `pheno`.",
"format": "file-path",
"mimetype": "text/tsv",
"fa_icon": "fas fa-file",
"help_text": "Columns cannot be named 'x', 'y', 'ID', '#ID', 'FID', or '#FID', or have the same name of columns in `qcovar` .\n\nSee an [example file](../assets/test_data/tsv/covar.tsv)"
},
"qcovar": {
"type": "string",
"fa_icon": "fas fa-file",
"description": "Quantitative covariates. Same format as `pheno`.",
"format": "file-path",
"mimetype": "text/tsv",
"help_text": "Columns cannot be named 'x', 'y', 'ID', '#ID', 'FID', or '#FID', or have the same name of columns in `covar` .\n\nSee an [example file](../assets/test_data/tsv/qcovar.tsv)"
},
"freq": {
"type": "string",
"fa_icon": "fas fa-file",
"description": "plink2-type frequency file for GRM calculations",
"format": "file-path",
"help_text": "Can be obtained with plink2 with the command `--freq`. Variants included should all be biallelic and have IDs matching the ones in the main genome file provided."
},
"maf_min": {
"type": "number",
"fa_icon": "fas fa-check",
"description": "Exclude from the analysis genetic variants with a Minor Allele Frequency (MAF) under this value",
"minimum": 0,
"maximum": 0.5
},
"use_dosage": {
"type": "boolean",
"default": true,
"fa_icon": "fas fa-check",
"description": "Should genotype dosages be used or hard calls?",
"help_text": "If set to true, the genotype dosages are converted to hard calls without missingness. If you want to use more advanced conversion criteria use the ext.args* slot of the VCF_TO_PGEN and FIT_MODEL processes."
},
"select_chr": {
"type": "string",
"fa_icon": "fas fa-question",
"description": "Restrict analysis to a set of chromosomes",
"help_text": "Comma-separated string of chromosome names in `vcf`. If not specified all chromosomes are used. If a chromosome is specified still the rest of the genome is used to evaluate the LOCO relatedness matrix.\n\nExample: '1,2,3'"
},
"select_pheno": {
"type": "string",
"fa_icon": "fas fa-question",
"description": "Restrict analysis to a set of phenotypes",
"help_text": "Comma-separated string of column names in `pheno` to be used as phenotypes. If not specified all the columns of `pheno` are used.\n\nExample: 'pheno1,pheno2'"
},
"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})$"
}
}
},
"statistical_parameters": {
"title": "Statistical parameters",
"type": "object",
"description": "",
"default": "",
"fa_icon": "fas fa-signal",
"properties": {
"quantile_normalise": {
"type": "boolean",
"fa_icon": "fas fa-check",
"description": "Should the phenotypes be quantile normalised?",
"help_text": "Forces phenotypes to a N(0, 1) distribution."
},
"standardise": {
"type": "boolean",
"fa_icon": "fas fa-check",
"description": "Should the phenotypes be mean-centered and variance-scaled?"
},
"null_model_formula": {
"type": "string",
"fa_icon": "fas fa-arrow-right",
"description": "R-style formula for the outer model that you want to use as a baseline.",
"help_text": "A string like 'y ~ cov1'. Here 'y' can be used to refer to the phenotype, and 'x' can be used to refer to the genotype. Column names in `covar` and `qcovar` can also be used. See https://www.rdocumentation.org/packages/stats/versions/3.6.2/topics/formula for more information on R formulas."
},
"model_formula": {
"type": "string",
"fa_icon": "fas fa-arrow-right",
"description": "R-style formula for the nested model that includes the variable of interest",
"help_text": "Similar to `null_model_formula`. Must contain all the terms in `null_model_formula` plus at least an extra one. You can also include GxE terms (es. 'y ~ x + x:cov1 + cov1'), and dominance terms ('y ~ x + I(x == 1) + cov1'). Arithmetic operations such as 'I(x == 1)' must be encapsulated in I() for proper evaluation."
},
"permutations": {
"type": "integer",
"default": 10,
"fa_icon": "fas fa-list-ol",
"description": "Number of permutations to be performed"
},
"p_thr": {
"type": "number",
"default": 0.05,
"fa_icon": "fas fa-arrow-right",
"description": "Nominal significance threshold"
}
},
"required": ["null_model_formula", "model_formula"]
},
"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": [
{
"$ref": "#/definitions/genotype_options"
},
{
"$ref": "#/definitions/input_output_options"
},
{
"$ref": "#/definitions/statistical_parameters"
},
{
"$ref": "#/definitions/institutional_config_options"
},
{
"$ref": "#/definitions/max_job_request_options"
},
{
"$ref": "#/definitions/generic_options"
}
],
"properties": {
"maf_min_grm": {
"type": "number",
"default": 0.1
}
}
}