-
Notifications
You must be signed in to change notification settings - Fork 5
/
nextflow_schema.json
449 lines (449 loc) · 18.9 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
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/plant-food-research-open/genepal/master/nextflow_schema.json",
"title": "plant-food-research-open/genepal pipeline parameters",
"description": "A Nextflow pipeline for consensus, phased and pan-genome annotation.",
"type": "object",
"$defs": {
"input_output_options": {
"title": "Input/output options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "",
"required": ["input", "protein_evidence", "outdir"],
"properties": {
"input": {
"type": "string",
"format": "file-path",
"mimetype": "text/csv",
"schema": "assets/schema_input.json",
"pattern": "^\\S+\\.csv$",
"description": "Target assemblies listed in a CSV sheet",
"fa_icon": "fas fa-file-csv"
},
"protein_evidence": {
"type": "string",
"description": "Protein evidence provided as a fasta file or multiple fasta files listed in a plain txt file",
"format": "file-path",
"pattern": "^\\S+\\.(txt|fa|faa|fna|fsa|fas|fasta)(\\.gz)?$",
"fa_icon": "far fa-file-alt"
},
"eggnogmapper_db_dir": {
"type": "string",
"description": "Eggnogmapper database directory",
"format": "directory-path",
"fa_icon": "fas fa-folder-open"
},
"eggnogmapper_tax_scope": {
"type": "integer",
"description": "Eggnogmapper taxonomy scopre. Eukaryota: 2759, Viridiplantae: 33090, Archaea: 2157, Bacteria: 2, root: 1",
"minimum": 1,
"default": 1,
"fa_icon": "fas fa-hashtag"
},
"rna_evidence": {
"type": "string",
"format": "file-path",
"mimetype": "text/csv",
"schema": "assets/schema_rna.json",
"pattern": "^\\S+\\.csv$",
"fa_icon": "fas fa-file-csv",
"description": "FASTQ/BAM samples listed in a CSV sheet"
},
"liftoff_annotations": {
"type": "string",
"format": "file-path",
"mimetype": "text/csv",
"schema": "assets/schema_liftoff.json",
"pattern": "^\\S+\\.csv$",
"description": "Reference annotations listed in a CSV sheet",
"fa_icon": "fas fa-file-csv"
},
"orthofinder_annotations": {
"type": "string",
"format": "file-path",
"mimetype": "text/csv",
"schema": "/assets/schema_orthofinder.json",
"pattern": "^\\S+\\.csv$",
"description": "Additional annotations for orthology listed in a CSV sheet",
"fa_icon": "fas fa-file-csv"
},
"outdir": {
"type": "string",
"format": "directory-path",
"description": "The output directory where the results will be saved",
"fa_icon": "fas fa-folder-open"
},
"email": {
"type": "string",
"description": "Email address for completion summary.",
"fa_icon": "fas fa-envelope",
"pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$",
"hidden": true
}
}
},
"repeat_annotation_options": {
"title": "Repeat annotation options",
"type": "object",
"description": "",
"default": "",
"properties": {
"repeat_annotator": {
"type": "string",
"default": "repeatmodeler",
"enum": ["edta", "repeatmodeler"],
"description": "'edta' or 'repeatmodeler'",
"fa_icon": "fas fa-tasks"
},
"save_annotated_te_lib": {
"type": "boolean",
"description": "Save annotated TE library or not?",
"fa_icon": "fas fa-question-circle"
},
"edta_is_sensitive": {
"type": "boolean",
"description": "Use '--sensitive 1' flag with EDTA or not?",
"fa_icon": "fas fa-question-circle"
},
"repeatmasker_save_outputs": {
"type": "boolean",
"description": "Save the repeat-masked genome or not?",
"fa_icon": "fas fa-question-circle"
}
},
"fa_icon": "fab fa-adn"
},
"rnaseq_pre_processing_options": {
"title": "RNASeq pre-processing options",
"type": "object",
"description": "",
"default": "",
"properties": {
"fastqc_skip": {
"type": "boolean",
"description": "Skip FASTQC or not?",
"fa_icon": "fas fa-question-circle",
"default": true
},
"fastp_skip": {
"type": "boolean",
"description": "Skip trimming by FASTQP or not?",
"fa_icon": "fas fa-question-circle"
},
"min_trimmed_reads": {
"type": "integer",
"default": 10000,
"description": "Exclude a sample if its reads after trimming are below this number",
"minimum": 0,
"fa_icon": "fas fa-hashtag"
},
"fastp_extra_args": {
"type": "string",
"description": "Extra FASTP arguments",
"fa_icon": "fas fa-terminal"
},
"save_trimmed": {
"type": "boolean",
"description": "Save FASTQ files after trimming or not?",
"fa_icon": "fas fa-question-circle"
},
"remove_ribo_rna": {
"type": "boolean",
"description": "Remove Ribosomal RNA or not?",
"fa_icon": "fas fa-question-circle"
},
"save_non_ribo_reads": {
"type": "boolean",
"description": "Save FASTQ files after Ribosomal RNA removal or not?",
"fa_icon": "fas fa-question-circle"
},
"ribo_database_manifest": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"default": "${projectDir}/assets/rrna-db-defaults.txt",
"fa_icon": "fas fa-database",
"description": "Ribosomal RNA fastas listed in a text sheet"
}
},
"fa_icon": "fas fa-cut"
},
"rnaseq_alignment_options": {
"title": "RNASeq alignment options",
"type": "object",
"description": "",
"default": "",
"properties": {
"star_max_intron_length": {
"type": "integer",
"default": 16000,
"minimum": 0,
"description": "Maximum intron length for STAR alignment",
"fa_icon": "fas fa-hashtag"
},
"star_align_extra_args": {
"type": "string",
"description": "EXTRA arguments for STAR",
"fa_icon": "fas fa-terminal"
},
"star_save_outputs": {
"type": "boolean",
"description": "Save BAM files from STAR or not?",
"fa_icon": "fas fa-question-circle"
},
"save_cat_bam": {
"type": "boolean",
"description": "SAVE a concatenated BAM file per assembly or not?",
"fa_icon": "fas fa-question-circle"
}
},
"fa_icon": "fas fa-align-center"
},
"annotation_options": {
"title": "Annotation options",
"type": "object",
"description": "",
"default": "",
"properties": {
"braker_extra_args": {
"type": "string",
"description": "Extra arguments for BRAKER",
"fa_icon": "fas fa-terminal"
},
"liftoff_coverage": {
"type": "number",
"default": 0.9,
"minimum": 0,
"maximum": 1,
"description": "Liftoff coverage parameter",
"fa_icon": "fas fa-hashtag"
},
"liftoff_identity": {
"type": "number",
"default": 0.9,
"description": "Liftoff identity parameter",
"fa_icon": "fas fa-hashtag"
},
"eggnogmapper_evalue": {
"type": "number",
"default": 1e-5,
"description": "Only report alignments below or equal the e-value threshold",
"fa_icon": "fas fa-hashtag"
},
"eggnogmapper_pident": {
"type": "integer",
"default": 35,
"description": "Only report alignments above or equal to the given percentage of identity (0-100)",
"minimum": 0,
"maximum": 100,
"fa_icon": "fas fa-hashtag"
}
},
"fa_icon": "fab fa-adn"
},
"post_annotation_filtering_options": {
"title": "Post-annotation filtering options",
"type": "object",
"description": "",
"default": "",
"fa_icon": "fas fa-filter",
"properties": {
"allow_isoforms": {
"type": "boolean",
"default": true,
"description": "Allow multiple isoforms for gene models",
"fa_icon": "fas fa-question-circle"
},
"enforce_full_intron_support": {
"type": "boolean",
"default": true,
"fa_icon": "fas fa-question-circle",
"description": "Require every model to have external evidence for all its introns"
},
"filter_liftoff_by_hints": {
"type": "boolean",
"default": true,
"fa_icon": "fas fa-question-circle",
"description": "Use BRAKER hints to filter Liftoff models"
},
"eggnogmapper_purge_nohits": {
"type": "boolean",
"description": "Purge transcripts which do not have a hit against eggnog",
"fa_icon": "fas fa-question-circle"
},
"filter_genes_by_aa_length": {
"type": "integer",
"default": 24,
"fa_icon": "fas fa-hashtag",
"description": "Filter genes with open reading frames shorter than the specified number of amino acids excluding the stop codon. If set to `null`, this filter step is skipped.",
"minimum": 3
}
}
},
"annotation_output_options": {
"title": "Annotation output options",
"type": "object",
"description": "",
"default": "",
"fa_icon": "fas fa-download",
"properties": {
"braker_save_outputs": {
"type": "boolean",
"description": "Save BRAKER files",
"fa_icon": "fas fa-question-circle"
},
"add_attrs_to_proteins_cds_fastas": {
"type": "boolean",
"description": "Add gff attributes to proteins/cDNA/CDS fasta",
"fa_icon": "fas fa-question-circle"
}
}
},
"evaluation_options": {
"title": "Evaluation options",
"type": "object",
"description": "",
"default": "",
"fa_icon": "fas fa-balance-scale-right",
"properties": {
"busco_skip": {
"type": "boolean",
"fa_icon": "fas fa-fast-forward",
"description": "Skip evaluation by BUSCO"
},
"busco_lineage_datasets": {
"type": "string",
"pattern": "^(\\w+_odb10\\s)*\\w+_odb10$",
"fa_icon": "fas fa-tree",
"description": "BUSCO lineages as a space-separated list: 'fungi_odb10 microsporidia_odb10'",
"default": "eukaryota_odb10"
}
}
},
"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,
"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"
}
}
},
"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.",
"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})$",
"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$",
"default": "25.MB",
"fa_icon": "fas fa-file-upload",
"hidden": true
},
"monochrome_logs": {
"type": "boolean",
"description": "Do not use coloured log outputs.",
"fa_icon": "fas fa-palette",
"hidden": true
},
"hook_url": {
"type": "string",
"description": "Incoming hook URL for messaging service",
"fa_icon": "fas fa-people-group",
"hidden": true
}
}
}
},
"allOf": [
{
"$ref": "#/$defs/input_output_options"
},
{
"$ref": "#/$defs/repeat_annotation_options"
},
{
"$ref": "#/$defs/rnaseq_pre_processing_options"
},
{
"$ref": "#/$defs/rnaseq_alignment_options"
},
{
"$ref": "#/$defs/annotation_options"
},
{
"$ref": "#/$defs/post_annotation_filtering_options"
},
{
"$ref": "#/$defs/annotation_output_options"
},
{
"$ref": "#/$defs/evaluation_options"
},
{
"$ref": "#/$defs/institutional_config_options"
},
{
"$ref": "#/$defs/generic_options"
}
]
}