-
Notifications
You must be signed in to change notification settings - Fork 21
/
Copy pathnextflow_schema.json
401 lines (401 loc) · 18.5 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
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
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/CFIA-NCFAD/nf-flu/master/nextflow_schema.json",
"title": "CFIA-NCFAD/nf-flu pipeline parameters",
"description": "Influenza genome assembly with IRMA and consensus sequence analysis",
"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.",
"properties": {
"input": {
"type": "string",
"fa_icon": "fas fa-file-csv",
"description": "Sample sheet with sample names and paths to reads."
},
"platform": {
"type": "string",
"fa_icon": "fas fa-hdd",
"description": "NGS platform used to sequence the samples.",
"enum": [
"illumina",
"nanopore"
]
},
"ref_db": {
"type": "string",
"fa_icon": "fas fa-hdd",
"description": "Provide fasta database of interesting reference sequences",
"default": ""
},
"outdir": {
"type": "string",
"description": "The output directory where the results will be saved.",
"default": "./results",
"fa_icon": "fas fa-folder-open"
},
"save_ncbi_db": {
"type": "boolean",
"description": "Save the NCBI Influenza database FASTA and metadata CSV to the output directory.",
"default": false,
"fa_icon": "fas fa-database"
},
"save_blastdb": {
"type": "boolean",
"description": "Save the BLAST database to the output directory.",
"default": false,
"fa_icon": "fas fa-database"
}
},
"required": [
"input"
]
},"variant_calling_options": {
"title": "Variant calling options",
"type": "object",
"description": "Various options for the variant calling branch of the pipeline.",
"default": "",
"properties": {
"variant_caller": {
"type": "string",
"description": "Variant caller (Clair3 or Medaka)",
"default": "clair3",
"fa_icon": "fas fa-dna"
},
"medaka_variant_model": {
"type": "string",
"description": "[Medaka](https://github.com/nanoporetech/medaka) Medaka model for final variant calling from phased reads",
"default": "r941_prom_hac_variant_g507",
"fa_icon": "fas fa-dna"
},
"medaka_snp_model": {
"type": "string",
"description": "[Medaka](https://github.com/nanoporetech/medaka) Medaka model for initial SNP calling from mixed reads prior to phasing",
"default": "r941_prom_hac_snp_g507",
"fa_icon": "fas fa-dna"
},
"clair3_variant_model": {
"type": "string",
"description": "[Clair3](https://github.com/HKU-BAL/Clair3) Clair3 variant model",
"default": "r941_prom_sup_g5014",
"fa_icon": "fas fa-dna"
},
"clair3_user_variant_model": {
"type": "string",
"description": "User specific model path",
"default": "",
"fa_icon": "fas fa-dna"
},
"minor_allele_fraction": {
"type": "number",
"minimum": 0,
"maximum": 1.0,
"default": 0.25,
"description": "Minor variant allele frequency/fraction.",
"fa_icon": "fas fa-compress-alt"
},
"major_allele_fraction": {
"type": "number",
"minimum": 0,
"maximum": 1.0,
"default": 0.75,
"description": "Major variant allele frequency/fraction. Only major variant alleles are used for generating a consensus sequence.",
"fa_icon": "fas fa-expand-alt"
},
"low_coverage": {
"type": "integer",
"minimum": 0,
"default": 10,
"description": "Low coverage depth threshold. Consensus sequence positions with less than this coverage depth will be masked with `N`."
}
},
"fa_icon": "fas fa-dna"
},
"nanopore_options": {
"title": "Nanopore options",
"type": "object",
"description": "Options exclusive to running the pipeline on Nanopore data using the ARTIC fieldbioinformatics pipeline.",
"default": "",
"fa_icon": "fas fa-truck-loading",
"properties": {
"min_sample_reads": {
"type": "integer",
"default": 100,
"description": "Minimum number of raw reads required per sample in order to be considered for the downstream processing steps.",
"fa_icon": "fas fa-hand-paper"
}
}
},
"irma_assembly_options": {
"title": "IRMA assembly options",
"type": "object",
"description": "",
"default": "",
"properties": {
"irma_module": {
"type": "string",
"default": "",
"fa_icon": "fas fa-cube",
"description": "IRMA module to use for analysis.",
"enum": [
"FLU",
"FLU-utr",
"FLU-alt",
"FLU-avian",
"FLU-lowQC",
"FLU-pacbio",
"FLU-ref",
"FLU-secondary",
"FLU",
"FLU-avian-residual",
"FLU-fast",
"FLU-minion",
"FLU-pgm",
"FLU-roche",
"FLU-sensitive"
]
},
"keep_ref_deletions": {
"type": "boolean",
"default": "true",
"fa_icon": "fas fa-trash-alt",
"description": "Set \"DEL_TYPE=NNN\" to keep deletions to reference sequence as N characters in consensus."
},
"skip_irma_subtyping_report": {
"type": "boolean",
"default": "true",
"fa_icon": "fas fa-trash-alt",
"description": "Skip the output of subtyping report generated by IRMA consensus sequences."
}
},
"fa_icon": "fas fa-cogs"
},"nanopore_illumina_options": {
"title": "Nanopore/Illumina options",
"type": "object",
"description": "Options common to both the Nanopore and Illumina workflows in the pipeline.",
"default": "",
"properties": {
"skip_mosdepth": {
"type": "boolean",
"default": false,
"fa_icon": "fas fa-fast-forward",
"description": "Skip genome-wide and amplicon coverage plot generation from mosdepth output."
},
"output_unmapped_reads": {
"type": "boolean",
"default": false,
"fa_icon": "fas fa-dna",
"description": "Keep unmapped reads in BAM output. BAM output sizes without unmapped reads may be drastically smaller."
}
},
"fa_icon": "fas fa-retweet"
},"mismatch_report_option": {
"title": "Mistmatch report options",
"type": "object",
"description": "Reporting option.",
"default": "",
"properties": {
"min_aln_length": {
"type": "integer",
"default": 700,
"description": "Minimum alignment length of nucleotide BLAST results to consider for getting mismatch report from BLAST result against reference database. We normally set this number around the smallest genome segment (Segment 8).",
"fa_icon": "fas fa-balance-scale-right",
"minimum": 0
}
},
"fa_icon": "fas fa-retweet"
},
"h_n_subtyping_options": {
"title": "H/N subtyping options",
"type": "object",
"description": "Hemaglutinin and neuraminase subtype prediction options",
"default": "",
"properties": {
"pident_threshold": {
"type": "number",
"default": 0.85,
"description": "Minimum % identity of nucleotide BLAST results to consider for determining H/N subtypes.",
"fa_icon": "fas fa-balance-scale-left",
"minimum": 0,
"maximum": 1
},
"max_top_blastn": {
"type": "integer",
"default": 3,
"description": "Maximum of top blastn result reported",
"fa_icon": "fas fa-balance-scale-right",
"minimum": 1
},
"ncbi_influenza_fasta": {
"type": "string",
"default": "https://api.figshare.com/v2/file/download/41415330",
"description": "Path/URL to Zstandard compressed NCBI Influenza virus sequences FASTA file.",
"fa_icon": "fas fa-file-alt"
},
"ncbi_influenza_metadata": {
"type": "string",
"default": "https://api.figshare.com/v2/file/download/41415333",
"description": "Path/URL to Zstandard compressed NCBI Influenza virus sequences metadata CSV file.",
"fa_icon": "fas fa-file-csv"
}
},
"fa_icon": "fas fa-virus"
},
"annotation_options": {
"title": "Annotation options",
"type": "object",
"description": "Options for genome annotation",
"properties": {
"vadr_model_targz": {
"type": "string",
"default": "https://zenodo.org/records/13261208/files/vadr-models-flu-1.6.3-2.tar.gz",
"description": "Path/URL to the VADR model tarball (.tar.gz) to use for annotation",
"fa_icon": "fas fa-file-import"
}
}
},
"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"
]
},
"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."
},
"tracedir": {
"type": "string",
"description": "Directory to keep pipeline Nextflow logs and reports.",
"default": "${params.outdir}/pipeline_info",
"fa_icon": "fas fa-cogs",
"hidden": true
},
"singularity_pull_docker_container": {
"type": "boolean",
"description": "Instead of directly downloading Singularity images for use with Singularity, force the workflow to pull and convert Docker containers instead.",
"hidden": true,
"fa_icon": "fas fa-toolbox"
},
"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."
}
}
},
"slurm_scheduler_options": {
"title": "Slurm scheduler options",
"type": "object",
"description": "",
"default": "",
"properties": {
"slurm_queue": {
"type": "string",
"description": "Slurm queue/partition to submit pipeline jobs to",
"fa_icon": "fas fa-road"
},
"slurm_queue_size": {
"type": "integer",
"default": 100,
"description": "Slurm queue size. Max number of jobs to queue at once.",
"fa_icon": "fas fa-arrows-alt-v"
}
},
"fa_icon": "far fa-clock"
},
"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*)+$",
"hidden": true,
"help_text": "Use to set an upper-limit for the time requirement for each process. Should be a string in the format integer-unit e.g. `--max_time '2.h'`"
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/input_output_options"
},
{
"$ref": "#/definitions/irma_assembly_options"
},
{
"$ref": "#/definitions/h_n_subtyping_options"
},
{
"$ref": "#/definitions/generic_options"
},
{
"$ref": "#/definitions/slurm_scheduler_options"
},
{
"$ref": "#/definitions/max_job_request_options"
}
]
}