forked from nf-core/smrnaseq
-
Notifications
You must be signed in to change notification settings - Fork 0
/
nextflow_schema.json
416 lines (416 loc) · 23.3 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
411
412
413
414
415
416
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/nf-core/smrnaseq/master/nextflow_schema.json",
"title": "nf-core/smrnaseq pipeline parameters",
"description": "Small RNA-Seq Best Practice Analysis 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"
],
"properties": {
"input": {
"type": "string",
"fa_icon": "fas fa-dna",
"description": "Input FastQ files.",
"help_text": "Use this to specify the location of your input FastQ files. For example:\n\n```bash\n--input 'path/to/data/sample_*.fastq'\n```\n\nPlease note the following requirements:\n\n1. The path must be enclosed in quotes\n2. The path must have at least one `*` wildcard character\n\n> NB: **This pipeline does not support paired-end data.**\n> If you have paired-end data, please just pass the _Read 1_ files to the pipeline."
},
"protocol": {
"type": "string",
"default": "illumina",
"fa_icon": "fas fa-vial",
"description": "Protocol for constructing smRNA-seq libraries.",
"help_text": "Presets for trimming parameters and 3' adapter sequence with a specified protocol.\n\n| Protocol | Library Prep Kit | Trimming Parameter | 3' Adapter Sequence |\n| :------------ | :-------------------------------------- | :-------------------------------------- | :--------------------- |\n| illumina | Illumina TruSeq Small RNA | `clip_r1 = 0` `three_prime_clip_r1 = 0` | `TGGAATTCTCGGGTGCCAAGG` |\n| nextflex | BIOO SCIENTIFIC NEXTFLEX Small RNA-Seq | `clip_r1 = 4` `three_prime_clip_r1 = 4` | `TGGAATTCTCGGGTGCCAAGG` |\n| qiaseq | QIAGEN QIAseq miRNA | `clip_r1 = 0` `three_prime_clip_r1 = 0` | `AACTGTAGGCACCATCAAT` |\n| cats | Diagenode CATS Small RNA-seq | `clip_r1 = 3` `three_prime_clip_r1 = 0` | `AAAAAAAAAAA` + `GATCGGAAGAGCACACGTCTG` (only polyA is used for trimming) |\n| custom | user defined | user defined | user defined |\n\n> NB: When running `--protocol custom` the user ***must define the 3' Adapter Sequence***.\n> If trimming parameters aren't provided the pipeline will deafult to `clip_R1 = 0` and `three_prime_clip_R1 = 0` (i.e. no extra clipping).",
"enum": [
"illumina",
"nextflex",
"qiaseq",
"cats",
"custom"
]
},
"outdir": {
"type": "string",
"description": "The output directory where the results will be saved.",
"default": "./results",
"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})$"
}
}
},
"reference_genome_options": {
"title": "Reference genome options",
"type": "object",
"fa_icon": "fas fa-dna",
"description": "Options for the reference genome indices used to align reads.",
"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."
},
"mirtrace_species": {
"type": "string",
"description": "Species for miRTrace.",
"help_text": "This is automatically set when using `--genome`. Example values: `hsa`, `mmu`...",
"fa_icon": "fas fa-journal-whills"
},
"fasta": {
"type": "string",
"fa_icon": "fas fa-font",
"description": "Path to reference genome FASTA genome file.",
"help_text": "If you have no genome reference available, the pipeline can build one using a FASTA file. This requires additional time and resources, so it's better to use a pre-build index if possible."
},
"mirna_gtf": {
"type": "string",
"description": "GFF/GTF file with coordinates positions of precursor and miRNAs.",
"help_text": "miRBase `.gff3` file, typically downloadedfrom [`ftp://mirbase.org/pub/mirbase/CURRENT/genomes/`](ftp://mirbase.org/pub/mirbase/CURRENT/genomes/)\n\nIf using iGenomes with `--genome` this file will be downloaded from miRBase automatically during the pipeline run.\n\n",
"fa_icon": "fas fa-address-book"
},
"mature": {
"type": "string",
"description": "Path to FASTA file with mature miRNAs.",
"fa_icon": "fas fa-wheelchair",
"help_text": "Typically this will be the `mature.fa` file from miRBase. Can be given either as a plain text `.fa` file or a compressed `.gz` file.\n\nDefaults to the current miRBase release URL, from which the file will be downloaded.",
"default": "ftp://mirbase.org/pub/mirbase/CURRENT/mature.fa.gz"
},
"hairpin": {
"type": "string",
"description": "Path to FASTA file with miRNAs precursors.",
"fa_icon": "fab fa-cuttlefish",
"help_text": "Typically this will be the `mature.fa` file from miRBase. Can be given either as a plain text `.fa` file or a compressed `.gz` file.\n\nDefaults to the current miRBase release URL, from which the file will be downloaded.",
"default": "ftp://mirbase.org/pub/mirbase/CURRENT/hairpin.fa.gz"
},
"bt_index": {
"type": "string",
"description": "Path to the Bowtie 1 reference genome index.",
"fa_icon": "fas fa-indent"
},
"references_parsed": {
"type": "string",
"description": "Path to the parsed reference folder containing the files for the miRDeep2.",
"fa_icon": "fas fa-align-left"
},
"save_reference": {
"type": "boolean",
"default": true,
"description": "Save generated reference genome files to results.",
"help_text": "Saving generated references means that you can use them for future pipeline runs, reducing processing times.",
"fa_icon": "fas fa-save"
},
"igenomes_base": {
"type": "string",
"description": "Directory / URL base for iGenomes references.",
"default": "s3://ngi-igenomes/igenomes",
"fa_icon": "fas fa-cloud-download-alt",
"hidden": true
},
"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`."
},
"bt_indices": {
"type": "array",
"description": "List of bowtie index files"
}
}
},
"trimming_options": {
"title": "Trimming options",
"type": "object",
"description": "",
"default": "",
"fa_icon": "fas fa-cut",
"properties": {
"min_length": {
"type": "integer",
"default": 17,
"description": "Discard reads that are shorter than this after quality / adapter trimming.",
"fa_icon": "fas fa-ruler"
},
"clip_r1": {
"type": "integer",
"fa_icon": "fas fa-cut",
"description": "Bp to remove from the 5' end of read 1"
},
"three_prime_clip_r1": {
"type": "integer",
"fa_icon": "fas fa-cut",
"description": "Bp to remove from the 3' end of read 1 AFTER adapter/quality trimming has been performed"
},
"three_prime_adapter": {
"type": "string",
"default": "TGGAATTCTCGGGTGCCAAGG",
"fa_icon": "fas fa-text-width",
"description": "Sequencing adapter sequence to search for and remove."
},
"mirtrace_protocol": {
"type": "string",
"default": "illumina",
"description": "protocol to be used for the mirtrace process",
"enum": [
"illumina",
"cats",
"qiaseq",
"nextflex"
]
},
"trim_galore_max_length": {
"type": "integer",
"default": 40,
"description": "trimgalore max-length parameter"
}
}
},
"skipping_pipeline_steps": {
"title": "Skipping pipeline steps",
"type": "object",
"description": "",
"default": "",
"fa_icon": "fas fa-fast-forward",
"properties": {
"skip_qc": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip all QC steps"
},
"skip_fastqc": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip FastQC"
},
"skip_mirdeep": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip miRDeep"
},
"skip_multiqc": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip MultiQC"
}
}
},
"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.",
"hidden": true,
"fa_icon": "fas fa-question-circle"
},
"publish_dir_mode": {
"type": "string",
"default": "copy",
"hidden": true,
"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"
]
},
"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
},
"seq_center": {
"type": "string",
"description": "Text about sequencing center which will be added in the header of output bam files.",
"fa_icon": "fas fa-fingerprint"
},
"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})$",
"hidden": true,
"help_text": "This works exactly as with `--email`, except emails are only sent if the workflow is not successful."
},
"plaintext_email": {
"type": "boolean",
"description": "Send plain-text email instead of HTML.",
"fa_icon": "fas fa-remove-format",
"hidden": true,
"help_text": "Set to receive plain-text e-mails instead of HTML formatted."
},
"max_multiqc_email_size": {
"type": "string",
"description": "File size limit when attaching MultiQC reports to summary emails.",
"default": "25.MB",
"fa_icon": "fas fa-file-upload",
"hidden": true,
"help_text": "If file generated by pipeline exceeds the threshold, it will not be attached."
},
"monochrome_logs": {
"type": "boolean",
"description": "Do not use coloured log outputs.",
"fa_icon": "fas fa-palette",
"hidden": true,
"help_text": "Set to disable colourful command line output and live life in monochrome."
},
"multiqc_config": {
"type": "string",
"description": "Custom config file to supply to MultiQC.",
"fa_icon": "fas fa-cog",
"hidden": true
},
"tracedir": {
"type": "string",
"description": "Directory to keep pipeline Nextflow logs and reports.",
"default": "${params.outdir}/pipeline_info",
"fa_icon": "fas fa-cogs",
"hidden": true
},
"show_hidden_params": {
"type": "boolean",
"fa_icon": "far fa-eye-slash",
"description": "Show all params when using `--help`",
"hidden": true,
"help_text": "By default, parameters set as _hidden_ in the schema are not shown on the command line when a user runs with `--help`. Specifying this option will tell the pipeline to show all parameters."
}
}
},
"max_job_request_options": {
"title": "Max job request options",
"type": "object",
"fa_icon": "fab fa-acquisitions-incorporated",
"description": "Set the top limit for requested resources for any single job.",
"help_text": "If you are running on a smaller system, a pipeline step requesting more resources than are available may cause the Nextflow to stop the run with an error. These options allow you to cap the maximum resources requested by any single job so that the pipeline will run on your system.\n\nNote that you can not _increase_ the resources requested by any job using these options. For that you will need your own configuration file. See [the nf-core website](https://nf-co.re/usage/configuration) for details.",
"properties": {
"max_cpus": {
"type": "integer",
"description": "Maximum number of CPUs that can be requested for any single job.",
"default": 16,
"fa_icon": "fas fa-microchip",
"hidden": true,
"help_text": "Use to set an upper-limit for the CPU requirement for each process. Should be an integer e.g. `--max_cpus 1`"
},
"max_memory": {
"type": "string",
"description": "Maximum amount of memory that can be requested for any single job.",
"default": "128.GB",
"fa_icon": "fas fa-memory",
"pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
"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|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'`"
}
}
},
"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",
"help_text": "Provide git commit id for custom Institutional configs hosted at `nf-core/configs`. This was implemented for reproducibility purposes. Default: `master`.\n\n```bash\n## Download and use config file with following git commit id\n--custom_config_version d52db660777c4bf36546ddb188ec530c3ada1b96\n```"
},
"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 the `custom_config_base` option. For example:\n\n```bash\n## Download and unzip the config files\ncd /path/to/my/configs\nwget https://github.com/nf-core/configs/archive/master.zip\nunzip master.zip\n\n## Run the pipeline\ncd /path/to/my/data\nnextflow run /path/to/pipeline/ --custom_config_base /path/to/my/configs/configs-master/\n```\n\n> Note that the nf-core/tools helper package has a `download` command to download all required pipeline files + singularity containers + institutional configs in one go for you, to make this process easier.",
"fa_icon": "fas fa-users-cog"
},
"hostnames": {
"type": "string",
"description": "Institutional configs hostname.",
"hidden": true,
"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"
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/input_output_options"
},
{
"$ref": "#/definitions/reference_genome_options"
},
{
"$ref": "#/definitions/trimming_options"
},
{
"$ref": "#/definitions/skipping_pipeline_steps"
},
{
"$ref": "#/definitions/generic_options"
},
{
"$ref": "#/definitions/max_job_request_options"
},
{
"$ref": "#/definitions/institutional_config_options"
}
]
}