-
Notifications
You must be signed in to change notification settings - Fork 5
/
Copy pathnextflow_schema.json
347 lines (347 loc) · 17 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
{
"$schema": "https://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/ebi-metagenomics/mettannotator/master/nextflow_schema.json",
"title": "ebi-metagenomics/mettannotator pipeline parameters",
"description": "ME TT assembly annotation pipeline",
"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$",
"schema": "assets/schema_input.json",
"description": "Path to comma-separated file containing information about the assemblies with the prefix to be used and the taxid.",
"help_text": "You will need to create a design file with information about the assemblies running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row.",
"fa_icon": "fas fa-file-csv"
},
"outdir": {
"type": "string",
"format": "directory-path",
"description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
"fa_icon": "fas fa-folder-open"
},
"fast": {
"type": "boolean",
"description": "Run the pipeline in fast mode. In this mode, InterProScan, UniFIRE, and SanntiS won't be executed, saving resources and speeding up the pipeline.",
"fa_icon": "fas fa-fast-forward"
},
"bakta": {
"type": "boolean",
"description": "Use Bakta instead of Prokka for CDS annotation. Prokka will still be used for archaeal genomes.",
"fa_icon": "fas fa-wrench"
},
"email": {
"type": "string",
"description": "Email address for completion summary.",
"fa_icon": "fas fa-envelope",
"help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
"pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
},
"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_databases": {
"title": "Reference databases",
"type": "object",
"description": "",
"default": "",
"properties": {
"dbs": {
"type": "string",
"format": "directory-path",
"description": "Folder for the tools' reference databases used by the pipeline for downloading. It's important to note that mixing the --dbs flag with individual database paths and versions is not allowed; they are mutually exclusive.",
"help_text": "Set this parameter to trigger the reference database download; otherwise, specify the databases individually."
},
"interproscan_db": {
"type": "string",
"format": "directory-path",
"description": "The InterProScan reference database, ftp://ftp.ebi.ac.uk/pub/software/unix/iprscan/",
"help_text": "Set this variable to the path of the uncompressed tarball for the database (obtained from the EBI FTP server)."
},
"interproscan_db_version": {
"type": "string",
"default": "5.62-94.0",
"description": "The InterProScan reference database version."
},
"interpro_entry_list": {
"type": "string",
"format": "directory-path",
"description": "TSV file listing basic InterPro entry information - the accessions, types and names, ftp://ftp.ebi.ac.uk/pub/databases/interpro/releases/94.0/entry.list",
"help_text": "Set this variable to the path of the uncompressed tarball for the database (obtained from the EBI FTP server)."
},
"interpro_entry_list_version": {
"type": "string",
"default": "94",
"description": "InterPro entry list version"
},
"eggnog_db": {
"type": "string",
"format": "directory-path",
"description": "The EggNOG reference database folder, https://github.com/eggnogdb/eggnog-mapper/wiki/eggNOG-mapper-v2.1.5-to-v2.1.12#requirements",
"help_text": "Set this variable to the path of the uncompressed tarball for the database."
},
"eggnog_db_version": {
"type": "string",
"default": "5.0.2",
"description": "The EggNOG reference database version."
},
"rfam_ncrna_models": {
"type": "string",
"format": "directory-path",
"description": "Rfam ncRNA models, ftp://ftp.ebi.ac.uk/pub/databases/metagenomics/genomes-pipeline/ncrna/",
"help_text": "Set this variable to the path of the folder that contains the Rfam models."
},
"rfam_ncrna_models_rfam_version": {
"type": "string",
"default": "14.9",
"description": "Rfam release version where the models come from.",
"help_text": "Rfam release version."
},
"amrfinder_plus_db": {
"type": "string",
"format": "directory-path",
"description": "AMRFinderPlus reference database, https://ftp.ncbi.nlm.nih.gov/pathogen/Antimicrobial_resistance/AMRFinderPlus/database/. Go to the following documentation for the db setup https://github.com/ncbi/amr/wiki/Upgrading#database-updates.",
"help_text": "Set this variable to the path of the folder that contains the AMRFinderPlus database directory."
},
"amrfinder_plus_db_version": {
"type": "string",
"default": "2024-01-31.1",
"description": "The AMRFinderPlus reference database version."
},
"defense_finder_db": {
"type": "string",
"format": "directory-path",
"description": "Defense Finder reference models, https://github.com/mdmparis/defense-finder#updating-defensefinder. The Microbiome Informatics team provides a pre-indexed version of the models for version 1.2.3 on this ftp location: ftp://ftp.ebi.ac.uk/pub/databases/metagenomics/pipelines/tool-dbs/defense-finder/defense-finder-models_1.2.3.tar.gz.",
"help_text": "Set this variable to the path of the folder that contains the Defense Finder models directory."
},
"defense_finder_db_version": {
"type": "string",
"default": "1.2.3",
"description": "The Defense Finder models version."
},
"antismash_db": {
"type": "string",
"format": "directory-path",
"description": "antiSMASH reference database, go to this documentation to do the database setup https://docs.antismash.secondarymetabolites.org/install/#installing-the-latest-antismash-release.",
"help_text": "Set this variable to the path of the folder that contains the antiSMASH indexed database directory."
},
"antismash_db_version": {
"type": "string",
"default": "7.1.0",
"description": "The antiSMASH reference database version."
},
"dbcan_db": {
"type": "string",
"format": "directory-path",
"description": "dbCAN indexed reference database, please go to the documentation for the setup https://dbcan.readthedocs.io/en/latest/. The Microbiome Informatics team provides a pre-indexed version of the database for version 4.0 on this ftp location: ftp://ftp.ebi.ac.uk/pub/databases/metagenomics/pipelines/tool-dbs/dbcan/dbcan_4.0.tar.gz",
"help_text": "Set this variable to the path of the folder that contains the dbCAN indexed database directory."
},
"dbcan_db_version": {
"type": "string",
"default": "4.1.3_V12",
"description": "The dbCAN reference database version."
},
"bakta_db": {
"type": "string",
"format": "directory-path",
"description": "Bakta reference database, please go to the documentation for the setup https://zenodo.org/records/10522951 and https://github.com/oschwengers/bakta?tab=readme-ov-file#database",
"help_text": "Set this variable to the path of the folder that contains the Bakta database directory with pre-indexed AMRFinderPlus db inside."
},
"bakta_db_version": {
"type": "string",
"default": "2024-01-19",
"description": "The Bakta reference database version."
},
"pseudofinder_db": {
"type": "string",
"format": "directory-path",
"description": "Pseudofinder reference database. Mettannotator uses SwissProt as the database for Pseudofinder.",
"help_text": "Set this variable to the path of the folder containing uniprot_sprot.fasta file to be used as the database."
},
"pseudofinder_db_version": {
"type": "string",
"default": "2024_06",
"description": "SwissProt version."
}
},
"fa_icon": "fas fa-database"
},
"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})$",
"help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
"hidden": true
},
"plaintext_email": {
"type": "boolean",
"description": "Send plain-text email instead of HTML.",
"fa_icon": "fas fa-remove-format",
"hidden": true
},
"max_multiqc_email_size": {
"type": "string",
"description": "File size limit when attaching MultiQC reports to summary emails.",
"pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
"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
},
"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)."
},
"multiqc_config": {
"type": "string",
"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"
},
"singularity_cachedir": {
"type": "string",
"fa_icon": "fab fa-docker",
"description": "The singularity/apptainer cache directory"
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/input_output_options"
},
{
"$ref": "#/definitions/reference_databases"
},
{
"$ref": "#/definitions/max_job_request_options"
},
{
"$ref": "#/definitions/generic_options"
}
]
}