-
Notifications
You must be signed in to change notification settings - Fork 4
/
nextflow_schema.json
316 lines (316 loc) · 18.1 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
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/nf-core/createtaxdb/master/nextflow_schema.json",
"title": "nf-core/createtaxdb pipeline parameters",
"description": "Parallelised and automated creation of metagenomic classifier databases of different tools",
"type": "object",
"$defs": {
"input_output_options": {
"title": "Input/output options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Define where the pipeline should find input data and save output data.",
"required": ["input", "outdir", "dbname"],
"properties": {
"input": {
"type": "string",
"format": "file-path",
"exists": true,
"schema": "assets/schema_input.json",
"mimetype": "text/csv",
"pattern": "^\\S+\\.csv$",
"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 reference genomes you wish to build into a metagenomic profiling database. Use this parameter to specify its location. It has to be a comma-separated file with 4 columns, and a header row. See [usage docs](https://nf-co.re/createtaxdb/usage#samplesheet-input).",
"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"
},
"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"
},
"dbname": {
"type": "string",
"description": "Specify name that resulting databases will be prefixed with.",
"fa_icon": "fas fa-id-badge"
},
"accession2taxid": {
"type": "string",
"description": "NCBI-style four-column accession to taxonomy ID map file",
"help_text": "\nAn NCBI four column file tab-separated file with `accession`, `accession.version`, `taxid` and `gi` number. The first refers to an accession ID in each FASTA entry header. The second refers to the accession ID but with the accession version number appended to the end (e.g. `.1`). The third refers to the taxonomy ID of the organism the sequence belongs to, as listed in `nodes.dmp`. The fourth refers to the old-style NCBI gi number of the sequence.\n\nIf building with typical NCBI data, the most typical file is the `nucl_gb.accession2taxid` file from the [NCBI taxonomy FTP server](https://ftp.ncbi.nlm.nih.gov/pub/taxonomy/accession2taxid/.",
"fa_icon": "fas fa-address-book",
"format": "file-path"
},
"prot2taxid": {
"type": "string",
"format": "path",
"exists": true,
"fa_icon": "fas fa-address-card",
"help_text": "A two column file tab-separated file with `accession.version` and `taxid`. The first refers to an accession ID in each FASTA entry header. The second refers to the taxonomy ID of the organism the sequence belongs to, as listed in `nodes.dmp`.",
"description": "Two column protein sequence accession ID to taxonomy map file."
},
"nucl2taxid": {
"type": "string",
"format": "file-path",
"exists": true,
"fa_icon": "far fa-address-card",
"description": "Two column nucleotide sequence accession ID to taxonomy map file.",
"help_text": "A two column file tab-separated file with `accession.version` and `taxid`. The first refers to an accession ID in each FASTA entry header. The second refers to the taxonomy ID of the organism the sequence belongs to, as listed in `nodes.dmp`."
},
"nodesdmp": {
"type": "string",
"format": "file-path",
"exists": true,
"fa_icon": "fas fa-circle",
"description": "Path to NCBI-style taxonomy node dmp file.",
"help_text": "A tab/pipe/tab separated table file. See nodes.dmp section of [NCBI taxdump README](https://ftp.ncbi.nlm.nih.gov/pub/taxonomy/new_taxdump/taxdump_readme.txt) for column file structure."
},
"namesdmp": {
"type": "string",
"format": "file-path",
"exists": true,
"fa_icon": "fas fa-tag",
"description": "Path to NCBI-style taxonomy names dmp file.",
"help_text": "A tab/pipe/tab separated table file. See names.dmp section of [NCBI taxdump README](https://ftp.ncbi.nlm.nih.gov/pub/taxonomy/new_taxdump/taxdump_readme.txt) for column file structure."
},
"malt_mapdb": {
"type": "string",
"format": "file-path",
"exists": true,
"description": "Path to MEGAN6/MALT mapping db file",
"help_text": "A mapping DB file containing taxonomy information for building MALT databases. This file can be downloaded from the [MEGAN6 website](https://software-ab.cs.uni-tuebingen.de/download/megan6/welcome.html). Can be zipped (the pipeline will unzip this for you if necessary). Typically the `megan-nucl-Feb2022.db.zip` is used with MALT.",
"fa_icon": "fas fa-database"
},
"save_concatenated_fastas": {
"type": "boolean",
"description": "Save concatenated input FASTAs",
"help_text": "Some tools require a single input FASTA of all reference genomes. The pipeline will do this concatenation for you, and by supplying this flag you can save the resulting single fasta for you in the results directory under `cat/`. ",
"fa_icon": "fas fa-save"
}
}
},
"database_building_options": {
"title": "Database Building Options",
"type": "object",
"description": "",
"default": "",
"properties": {
"build_bracken": {
"type": "boolean",
"fa_icon": "fas fa-save",
"description": "Turn on extending of Kraken2 database to include Bracken files. Requires nucleotide FASTA File input.",
"help_text": "Bracken2 databases are simply just a Kraken2 database with two additional files.\n\nNote however this requires a Kraken2 database _with_ intermediate files still in it, thus can result in large database directories."
},
"build_centrifuge": {
"type": "boolean",
"description": "Turn on building of Centrifuge database. Requires nucleotide FASTA file input.",
"fa_icon": "fas fa-toggle-on"
},
"build_diamond": {
"type": "boolean",
"fa_icon": "fas fa-toggle-on",
"description": "Turn on building of DIAMOND database. Requires amino-acid FASTA file input."
},
"build_kaiju": {
"type": "boolean",
"description": "Turn on building of Kaiju database. Requires amino-acid FASTA file input.",
"fa_icon": "fas fa-toggle-on"
},
"build_malt": {
"type": "boolean",
"fa_icon": "fas fa-toggle-on",
"description": "Turn on building of MALT database. Requires nucleotide FASTA file input."
},
"malt_sequencetype": {
"type": "string",
"default": "DNA",
"description": "Specify type of input sequence being given to MALT",
"enum": ["DNA", "Protein"],
"help_text": "Use to specify whether the reference sequences are DNA or Protein sequences. (For RNA sequences, use the DNA setting) - from [MALT manual](https://software-ab.cs.uni-tuebingen.de/download/malt/).\n\n> Modifies tool(s) parameter(s)\n> - malt-build: `--sequenceType` ",
"fa_icon": "fas fa-dna"
},
"build_kraken2": {
"type": "boolean",
"description": "Turn on building of Kraken2 database. Requires nucleotide FASTA file input.",
"fa_icon": "fas fa-toggle-on"
},
"kraken2_keepintermediate": {
"type": "boolean",
"fa_icon": "fas fa-save",
"description": "Retain intermediate Kraken2 build files for inspection."
},
"build_krakenuniq": {
"type": "boolean",
"fa_icon": "fas fa-toggle-on",
"description": "Turn on building of KrakenUniq database. Requires nucleotide FASTA file input."
}
},
"fa_icon": "fas fa-database"
},
"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"
}
}
},
"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
},
"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$",
"default": "25.MB",
"fa_icon": "fas fa-file-upload",
"hidden": true
},
"monochrome_logs": {
"type": "boolean",
"description": "Do not use coloured log outputs.",
"fa_icon": "fas fa-palette",
"hidden": true
},
"hook_url": {
"type": "string",
"description": "Incoming hook URL for messaging service",
"fa_icon": "fas fa-people-group",
"help_text": "Incoming hook URL for messaging service. Currently, MS Teams and Slack are supported.",
"hidden": true
},
"multiqc_config": {
"type": "string",
"format": "file-path",
"description": "Custom config file to supply to MultiQC.",
"fa_icon": "fas fa-cog",
"hidden": true
},
"multiqc_logo": {
"type": "string",
"description": "Custom logo file to supply to MultiQC. File name must also be set in the MultiQC config file",
"fa_icon": "fas fa-image",
"hidden": true
},
"multiqc_methods_description": {
"type": "string",
"description": "Custom MultiQC yaml file containing HTML including a methods description.",
"fa_icon": "fas fa-cog"
},
"validate_params": {
"type": "boolean",
"description": "Boolean whether to validate parameters against the schema at runtime",
"default": true,
"fa_icon": "fas fa-check-square",
"hidden": true
},
"pipelines_testdata_base_path": {
"type": "string",
"fa_icon": "far fa-check-circle",
"description": "Base URL or local path to location of pipeline test dataset files",
"default": "https://raw.githubusercontent.com/nf-core/test-datasets/",
"hidden": true
}
}
}
},
"allOf": [
{
"$ref": "#/$defs/input_output_options"
},
{
"$ref": "#/$defs/database_building_options"
},
{
"$ref": "#/$defs/institutional_config_options"
},
{
"$ref": "#/$defs/generic_options"
}
]
}