-
Notifications
You must be signed in to change notification settings - Fork 5
/
nextflow_schema.json
410 lines (410 loc) · 24.7 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
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/nf-core/pathogensurveillance/master/nextflow_schema.json",
"title": "nf-core/pathogensurveillance pipeline parameters",
"description": "Surveillance of pathogens using high-throughput sequencing",
"type": "object",
"$defs": {
"input_output_options": {
"title": "Input/output options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Define where the pipeline should find input data and save output data.",
"required": ["sample_data", "outdir"],
"properties": {
"sample_data": {
"type": "string",
"format": "file-path",
"exists": true,
"schema": "assets/schema_input.json",
"mimetype": "text/csv",
"pattern": "^\\S+\\.[ct]sv$",
"description": "Path to comma-separated file containing information about samples.",
"help_text": "This CSV has one row per samples and contains information such as the location of input files, sample ID, labels, etc. Use this parameter to specify its location. See [the documentaion](https://github.com/grunwaldlab/pathogensurveillance?tab=readme-ov-file#input-format) for details on formatting this file.",
"fa_icon": "fas fa-file-csv"
},
"reference_data": {
"type": "string",
"format": "file-path",
"mimetype": "text/csv",
"pattern": "^\\S+\\.[ct]sv$",
"schema": "assets/schema_input.json",
"description": "Path to comma-separated file containing information about samples.",
"help_text": "This CSV has one row per reference and contains information such as the location of input files, reference ID, labels, etc. Use this parameter to specify its location. See [the documentaion](https://github.com/grunwaldlab/pathogensurveillance?tab=readme-ov-file#input-format) for details on formatting this file.",
"fa_icon": "fas fa-file-csv"
},
"outdir": {
"type": "string",
"format": "directory-path",
"description": "The output directory where the results will be saved. You have to use absolute paths to storage if running on Cloud infrastructure.",
"fa_icon": "fas fa-folder-open"
},
"temp_dir": {
"type": "string",
"format": "directory-path",
"description": "The location to save temporary files for processes. This is only used for some processes that produce large temporary files such as PICARD_SORTSAM.",
"fa_icon": "fas fa-folder-open"
},
"data_dir": {
"type": "string",
"default": "path_surveil_data",
"format": "directory-path",
"description": "The location to save downloaded files for later use. This is seperate from the cached data (usually stored in the 'work' directory), so that the cache can be cleared without having to repeat many large downloads.",
"fa_icon": "fas fa-folder-open"
},
"email": {
"type": "string",
"description": "Email address for completion summary.",
"fa_icon": "fas fa-envelope",
"help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
"pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
},
"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"
},
"bakta_db": {
"type": "string",
"description": "The path to the Bakta database folder. This or --download_bakta_db must be included.",
"fa_icon": "fas fa-folder-open",
"format": "directory-path"
},
"download_bakta_db": {
"type": "boolean",
"description": "Download the database required for running Bakta. This or --bakta_db must be included. Note that this will download gigabytes of information, so if you are planning to do repeated runs without --resume it would be better to download the database manually according to the bakta documentaion and specify it with --bakta_db.",
"fa_icon": "fas fa-download"
},
"bakta_db_type": {
"type": "string",
"pattern": "light|full",
"description": "Which type of the Bakta database to download. Must be 'light' (~2Gb) or 'full' (~40Gb).",
"default":"light"
},
"cache_type": {
"type": "string",
"pattern": "lenient|deep|false|true",
"description": "Which type of caching to perform. Possible values include 'lenient', 'deep', 'true', and 'false'. 'lenient' caching does not take into account file modifications times and 'deep' takes into account file content. See https://www.nextflow.io/docs/latest/process.html#process-cache for more information.",
"default":"true"
}
}
},
"analysis_parameters": {
"title": "Analysis parameters",
"type": "object",
"description": "Parmaters that modify the analysis done by the pipleine.",
"default": "",
"properties": {
"max_depth": {
"type": "number",
"default": 100,
"description": "Maximum depth of reads to be used for all analses. Samples with more reads are subsampled to this depth.",
"fa_icon": "fas fa-align-center"
},
"only_latin_binomial_refs": {
"type": "boolean",
"description": "When selecting references automatically, only consider references with names that appear to be standard latin bionomials (i.e. no numbers or symbols in the first two words).",
"fa_icon": "fas fa-download",
"default": false
},
"n_ref_strains": {
"type": "number",
"default": 30,
"description": "The maximum number/percentage of references representing unique subspecies to download from RefSeq for each sample. Samples with similar initial indentifications will usually use the same references, so the total number of references downloaded for a goup of samples will depend on the taxonomic diversity of the samples.",
"fa_icon": "fas fa-download"
},
"n_ref_species": {
"type": "number",
"default": 20,
"description": "The maximum number/percentage of references representing unique species to download from RefSeq for each sample. Samples with similar initial indentifications will usually use the same references, so the total number of references downloaded for a goup of samples will depend on the taxonomic diversity of the samples.",
"fa_icon": "fas fa-download"
},
"n_ref_genera": {
"type": "number",
"default": 10,
"description": "The maximum number/percentage of references representing unique genera to download from RefSeq for each sample. Samples with similar initial indentifications will usually use the same references, so the total number of references downloaded for a goup of samples will depend on the taxonomic diversity of the samples.",
"fa_icon": "fas fa-download"
},
"n_ref_closest": {
"type": "number",
"default": 3,
"description": "The number of references most similar to each sample based on estimated ANI to include in phyogenetic anlyses.",
"fa_icon": "fas fa-download"
},
"n_ref_closest_named": {
"type": "number",
"default": 2,
"description": "Same as the 'n_ref_closest' option except that it only applies to referneces with what apppear to be standard latin binomaial names (i.e. two words with no numbers or symbols). This is intended to ensure that a refernece with an informative name is present even if it is not the most similar.",
"fa_icon": "fas fa-download"
},
"n_ref_context": {
"type": "number",
"default": 7,
"description": "The number of references representing the entire range of ANI relative to each sample. These are meant to provide context for more similar references. For a group of samples, the fewest total references will be selected that satisify this count for each sample.",
"fa_icon": "fas fa-download"
},
"phylo_min_genes": {
"type": "number",
"default": 10,
"description": "The minimum number of genes needed to conduct a core gene phylogeny. Samples and references will be removed (as allowed by the `min_core_samps` and `min_core_refs` options) until this minimum is met.",
"fa_icon": "fas fa-align-center"
},
"phylo_max_genes": {
"type": "number",
"default": 200,
"description": "The maximum number of genes used to conduct a core gene phylogeny.",
"fa_icon": "fas fa-align-center"
},
"ref_min_ani": {
"type": "number",
"default": 0.85,
"description": "The minimum ANI between a sample and potential reference for that reference to be used for mapping reads from that sample. To force all the samples in a report group to use the same reference, set this value very low.",
"fa_icon": "fas fa-align-center"
}
}
},
"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": "64.GB",
"fa_icon": "fas fa-memory",
"pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
"hidden": true,
"help_text": "Use to set an upper-limit for the memory requirement for each process. Should be a string in the format integer-unit e.g. `--max_memory '8.GB'`"
},
"max_time": {
"type": "string",
"description": "Maximum amount of time that can be requested for any single job.",
"default": "240.h",
"fa_icon": "far fa-clock",
"pattern": "^(\\d+\\.?\\s*(s|m|h|day)\\s*)+$",
"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'`"
},
"max_total_cpus": {
"type": "integer",
"description": "Maximum number of CPUs that can be requested for all jobs combined. Should be an integer e.g. `--max_total_cpus 1`. Only applies if running the pipeline in a personal computer.",
"fa_icon": "fas fa-microchip",
"hidden": true,
"help_text": "Use to set an upper-limit for the CPU requirement for all jobs combined. Should be an integer e.g. `--max_total_cpus 1`"
},
"max_total_memory": {
"type": "string",
"description": "Maximum amount of memory that can be requested for all jobs combined. Should be a string in the format integer-unit e.g. `--max_total_memory '8.GB'`. Only applies if running the pipeline in a personal computer.",
"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 all jobs combined. Should be a string in the format integer-unit e.g. `--max_total_memory '8.GB'`"
},
"max_total_jobs": {
"type": "integer",
"description": "Maximum number of jobs that can run at once. Should be an integer e.g. `--max_total_jobs 1`",
"fa_icon": "fas fa-microchip",
"hidden": true,
"help_text": "Use to set an upper-limit for the jobs to schedule at once. Should be an integer e.g. `--max_total_jobs 1`"
}
}
},
"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": {
"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
},
"copymode": {
"type": "string",
"default": "medium",
"description": "Designates which files are copied from work/ directory",
"help_text": "Sets `publishDir` mode for individual files. Storage footprint of the pipeline can be quite large, and files can be saved twice: both within the work/ directory and within the published output directory. By default, this parameter is set so that intermediate files will be linked from the published directory to their location in the work/ directory instead of being stored twice.",
"fa_icon": "fas fa-copy",
"enum": ["high", "medium", "low", "none"],
"hidden": false
},
"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$",
"default": "25.MB",
"fa_icon": "fas fa-file-upload",
"hidden": true
},
"monochrome_logs": {
"type": "boolean",
"description": "Do not use coloured log outputs.",
"fa_icon": "fas fa-palette",
"hidden": true
},
"hook_url": {
"type": "string",
"description": "Incoming hook URL for messaging service",
"fa_icon": "fas fa-people-group",
"help_text": "Incoming hook URL for messaging service. Currently, MS Teams and Slack are supported.",
"hidden": true
},
"multiqc_config": {
"type": "string",
"format": "file-path",
"description": "Custom config file to supply to MultiQC.",
"fa_icon": "fas fa-cog",
"hidden": true
},
"multiqc_logo": {
"type": "string",
"description": "Custom logo file to supply to MultiQC. File name must also be set in the MultiQC config file",
"fa_icon": "fas fa-image",
"hidden": true
},
"multiqc_methods_description": {
"type": "string",
"description": "Custom MultiQC yaml file containing HTML including a methods description.",
"fa_icon": "fas fa-cog"
},
"trace_dir": {
"type": "string",
"description": "Directory to keep pipeline Nextflow logs and reports.",
"default": "${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"
},
"hpc_queue": {
"type": "string",
"default": "",
"description": "Name of queue in HPC environment to run jobs.",
"hidden": true,
"fa_icon": "fas fa-cogs"
},
"pipelines_testdata_base_path": {
"type": "string",
"fa_icon": "far fa-check-circle",
"description": "Base URL or local path to location of pipeline test dataset files",
"default": "https://raw.githubusercontent.com/nf-core/test-datasets/",
"hidden": true
}
}
}
},
"allOf": [
{
"$ref": "#/$defs/input_output_options"
},
{
"$ref": "#/$defs/institutional_config_options"
},
{
"$ref": "#/$defs/generic_options"
}
]
}