-
Notifications
You must be signed in to change notification settings - Fork 3
/
Copy pathnextflow_schema.json
366 lines (366 loc) · 19.5 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
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/nf-core/pairgenomealign/master/nextflow_schema.json",
"title": "nf-core/pairgenomealign pipeline parameters",
"description": "Pairwise alignment pipeline (genome to genome or reads to genome)",
"type": "object",
"$defs": {
"input_output_options": {
"title": "Input/output options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Define where the pipeline should find input data and save output data.",
"required": ["input", "target", "outdir"],
"properties": {
"input": {
"type": "string",
"format": "file-path",
"exists": true,
"schema": "assets/schema_input.json",
"mimetype": "text/csv",
"pattern": "^\\S+\\.csv$",
"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 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://nf-co.re/pairgenomealign/usage#samplesheet-input).",
"fa_icon": "fas fa-file-csv"
},
"target": {
"type": "string",
"pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$",
"format": "file-path",
"description": "Path or URL to a FASTA genome file for the _target_ genome.",
"fa_icon": "far fa-file-code"
},
"targetName": {
"type": "string",
"default": "target",
"help_text": "By default the _target_ genome is named `target` and this name is concatenated with the sample IDs using `___` as a separator to construct alignment file names. Use this option to provide a more informative name for the target genome.",
"description": "Target genome name."
},
"outdir": {
"type": "string",
"format": "directory-path",
"description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
"fa_icon": "fas fa-folder-open"
},
"email": {
"type": "string",
"description": "Email address for completion summary.",
"fa_icon": "fas fa-envelope",
"help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
"pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
},
"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"
}
}
},
"indexing_options": {
"title": "Indexing options",
"type": "object",
"description": "",
"default": "",
"fa_icon": "fas fa-database",
"properties": {
"seed": {
"type": "string",
"enum": ["YASS", "NEAR", "MAM8", "RY128"],
"help_text": "LAST creates a database of seed sequences in the _target_ genome, and provides different ways to generate these seeds. The default (`YASS`) searches for long-and-weak similarities that allow for mismatches but not gaps. Among alternatives, there are `NEAR` for short-and-strong (near-identical) similarities with many gaps (insertions and deletions), `MAM8` to find weak similarities with high sensitivity, but low speed and high memory usage, or `RY128` that reduces run time and memory use, by only seeking seeds at ~1/128 of positions in each sequence, which is useful when the purpose of running this pipeline is only to generate whole-genome dotplots, or when sensitivity for tiny fragments may be unnecessary or undesirable. See <https://gitlab.com/mcfrith/last/-/blob/main/doc/last-seeds.rst> for details.",
"description": "Select the LAST seed to index the _target_ genome.",
"default": "YASS",
"fa_icon": "fas fa-seedling"
},
"softmask": {
"type": "string",
"enum": ["tantan", "original"],
"help_text": "In this pipeline, letters soft-masked in lowercase are excluded from indexing (`lastdb -c`). By default, the original mask is removed and a new one is made with an internal version of the “tantan” tool. Set this option to `original` to keep the original soft-masking. See <https://gitlab.com/mcfrith/last/-/blob/main/doc/lastdb.rst> for details.",
"description": "Customise the way to mask the _target_ genome.",
"default": "tantan",
"fa_icon": "fas fa-theater-masks"
}
}
},
"alignment_options": {
"title": "Alignment options",
"type": "object",
"description": "Arguments for the lastdb, last-train, lastal and last-split programs.",
"default": "",
"properties": {
"m2m": {
"type": "boolean",
"description": "Make a many to many alignment",
"help_text": "This adds time and can comsume considerable amount of space; use only if you need that data, for instance in the case of a self-alignment",
"fa_icon": "fas fa-arrows-alt"
},
"lastal_params": {
"type": "string",
"description": "Path to a file containing alignment parameters or a scoring matrix. If this option is used, `last-train` will be skipped and alignment parameters will be the same for each query.",
"fa_icon": "far fa-file-alt"
},
"lastal_args": {
"type": "string",
"default": "-C2 -D1e9",
"description": "Arguments passed to both `last-train` and `lastal`.",
"fa_icon": "fas fa-align-center"
},
"lastal_extr_args": {
"type": "string",
"description": "Arguments passed only to `lastal` (useful when they are not recognised by `last-train`).",
"fa_icon": "fas fa-align-center"
},
"last_split_mismap": {
"type": "string",
"default": 0.00001,
"fa_icon": "fas fa-cut",
"description": "Mismap probability cutoff for `last-split`."
}
},
"fa_icon": "fas fa-cogs"
},
"dotplot_parameters": {
"title": "Dotplot parameters",
"type": "object",
"description": "Customise dot-plots or skip them.",
"default": "",
"properties": {
"dotplot_options": {
"type": "string",
"description": "Extra arguments passed to `last-dotplot` to customise the output. See <https://gitlab.com/mcfrith/last/-/blob/main/doc/last-dotplot.rst>.",
"fa_icon": "fas fa-cog"
},
"skip_dotplot_o2m": {
"type": "boolean",
"description": "Do not generate the one-to-many alignment dot-plot.",
"fa_icon": "fas fa-forward"
},
"skip_dotplot_o2o": {
"type": "boolean",
"description": "Do not generate the one-to-one alignment dot-plot.",
"fa_icon": "fas fa-forward"
},
"skip_dotplot_m2o": {
"type": "boolean",
"description": "Do not generate the many-to-one alignment dot-plot.",
"fa_icon": "fas fa-forward"
},
"skip_dotplot_m2m": {
"type": "boolean",
"description": "Do not generate the many-to-many alignment dot-plot.",
"fa_icon": "fas fa-forward"
}
},
"fa_icon": "fas fa-cogs"
},
"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_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`."
},
"igenomes_base": {
"type": "string",
"format": "directory-path",
"description": "The base path to the igenomes reference files",
"fa_icon": "fas fa-ban",
"hidden": true,
"default": "s3://ngi-igenomes/igenomes/"
}
}
},
"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$",
"default": "25.MB",
"fa_icon": "fas fa-file-upload",
"hidden": true
},
"monochrome_logs": {
"type": "boolean",
"description": "Do not use coloured log outputs.",
"fa_icon": "fas fa-palette",
"hidden": true
},
"hook_url": {
"type": "string",
"description": "Incoming hook URL for messaging service",
"fa_icon": "fas fa-people-group",
"help_text": "Incoming hook URL for messaging service. Currently, MS Teams and Slack are supported.",
"hidden": true
},
"multiqc_config": {
"type": "string",
"format": "file-path",
"description": "Custom config file to supply to MultiQC.",
"fa_icon": "fas fa-cog",
"hidden": true
},
"multiqc_logo": {
"type": "string",
"description": "Custom logo file to supply to MultiQC. File name must also be set in the MultiQC config file",
"fa_icon": "fas fa-image",
"hidden": true
},
"multiqc_methods_description": {
"type": "string",
"description": "Custom MultiQC yaml file containing HTML including a methods description.",
"fa_icon": "fas fa-cog"
},
"validate_params": {
"type": "boolean",
"description": "Boolean whether to validate parameters against the schema at runtime",
"default": true,
"fa_icon": "fas fa-check-square",
"hidden": true
},
"pipelines_testdata_base_path": {
"type": "string",
"fa_icon": "far fa-check-circle",
"description": "Base URL or local path to location of pipeline test dataset files",
"default": "https://raw.githubusercontent.com/nf-core/test-datasets/",
"hidden": true
},
"trace_report_suffix": {
"type": "string",
"fa_icon": "far calendar",
"description": "Suffix to add to the trace report filename. Default is the date and time in the format yyyy-MM-dd_HH-mm-ss.",
"hidden": true
}
}
}
},
"allOf": [
{
"$ref": "#/$defs/input_output_options"
},
{
"$ref": "#/$defs/indexing_options"
},
{
"$ref": "#/$defs/alignment_options"
},
{
"$ref": "#/$defs/dotplot_parameters"
},
{
"$ref": "#/$defs/reference_genome_options"
},
{
"$ref": "#/$defs/reference_genome_options"
},
{
"$ref": "#/$defs/institutional_config_options"
},
{
"$ref": "#/$defs/generic_options"
}
]
}