-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathnextflow_schema.json
More file actions
426 lines (426 loc) · 18.2 KB
/
nextflow_schema.json
File metadata and controls
426 lines (426 loc) · 18.2 KB
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
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/number-25/LongTranscriptomics/refs/heads/dev/nextflow_schema.json",
"title": "number-25/LongTranscriptomics pipeline parameters",
"description": "Analysis pipeline for ONT directRNA sequencing data",
"type": "object",
"$defs": {
"reference_genome_options": {
"title": "Reference genome options",
"type": "object",
"description": "Options for reference genome and transcriptome files and indices.",
"default": "",
"properties": {
"genome_fasta": {
"type": "string",
"description": "Path to reference genome fasta."
},
"genome_fasta_index": {
"type": "string",
"description": "Path to reference genome index."
},
"genome_fasta_sizes": {
"type": "string",
"description": "Path to reference genome sizes."
},
"genome_minimap2_index": {
"type": "string",
"description": "Path to reference genome minimap2 index."
},
"transcriptome_mapping": {
"type": "boolean",
"description": "Map to reference transcriptome instead of genome."
},
"transcriptome_fasta": {
"type": "string",
"description": "Path to transcriptome fasta sequence."
},
"transcriptome_fasta_index": {
"type": "string",
"description": "Path to transcriptome fasta index."
},
"transcriptome_minimap2_index": {
"type": "string",
"description": "Path to transcriptome minimap2 index."
},
"annotation_gtf": {
"type": "string",
"description": "Path to reference transcriptome annotation."
},
"skip_prepare_reference": {
"type": "boolean",
"description": "Skip the preparation of the reference files."
}
},
"required": ["genome_fasta", "transcriptome_fasta", "annotation_gtf"],
"fa_icon": "fas fa-book-open"
},
"input_output_options": {
"title": "Input/output options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Define where the pipeline should find input data and save output data.",
"required": ["input", "outdir", "sequencing_type"],
"properties": {
"input": {
"type": "string",
"format": "file-path",
"exists": true,
"schema": "assets/schema_input.json",
"mimetype": "text/csv",
"pattern": "^\\S+\\.csv$",
"description": "Path to comma-separated file containing information about the samples in the experiment.",
"help_text": "You will need to create a 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.",
"fa_icon": "fas fa-file-csv",
"default": "assets/samplesheet.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",
"default": "outputs"
},
"help": {
"type": "boolean",
"description": "Show the help message for the pipeline.",
"fa_icon": "fas fa-question-circle",
"help_text": "Welcome to LongTranscriptomics, I see you are seeking help, these are a list of basic parameters."
},
"sequencing_type": {
"type": "string",
"default": "ont-drna",
"description": "Type of Oxford Nanopore library.",
"help_text": "Type of Oxford nanopore library. Either 'ont-drna' or 'ont-cdna'.",
"fa_icon": "fas fa-font"
}
}
},
"multiqc_options": {
"title": "MultiQC options",
"type": "object",
"description": "",
"default": "",
"properties": {
"multiqc_config": {
"type": "string",
"description": "Custom config file to supply to MultiQC."
},
"multiqc_logo": {
"type": "string",
"description": "Custom logo file to supply to MultiQC. File name must also be set in the MultiQC config file."
},
"multiqc_methods_description": {
"type": "string",
"description": "Custom MultiQC yaml file containing HTML including a methods description."
},
"multiqc_title": {
"type": "string",
"description": "MultiQC report title. Printed as page header, used for filename if not otherwise specified."
}
}
},
"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
},
"email": {
"type": "string",
"fa_icon": "fas fa-envelope",
"description": "Email address for completion summary."
},
"plaintext_email": {
"type": "boolean",
"description": "Send plain-text email instead of HTML.",
"fa_icon": "fas fa-remove-format"
},
"monochrome_logs": {
"type": "boolean",
"description": "Do not use coloured log outputs.",
"fa_icon": "fas fa-palette"
},
"publish_dir_mode": {
"type": "string",
"default": "copy",
"fa_icon": "fas fa-copy",
"description": "Method used to save pipeline results to output directory."
},
"hook_url": {
"type": "string",
"description": "Incoming Webhook URL for messaging service."
},
"config_profile_description": {
"type": "string",
"description": "Institutional config description."
},
"config_profile_name": {
"type": "string",
"description": "Institutional config name."
},
"custom_config_version": {
"type": "string",
"default": "dev",
"description": "Git commit id for Institutional configs"
},
"custom_config_base": {
"type": "string",
"description": "Base directory for Institutional configs.",
"default": "conf/base.config"
},
"config_profile_contact": {
"type": "string",
"description": "Institutional config contact information.",
"default": "deancombio@pm.me"
},
"config_profile_url": {
"type": "string",
"description": "Institutional config URL link."
}
}
},
"module_specific_options": {
"title": "Module specific options",
"type": "object",
"description": "",
"default": "",
"properties": {
"bam_input": {
"type": "boolean",
"description": "Input files are prealigned in BAM format."
},
"skip_qc": {
"type": "boolean",
"description": "Skip initial fastq QC.",
"help_text": "This skips all of the initial fastq QC, and is typically not recommended to skip."
},
"skip_nanoq": {
"type": "boolean",
"description": "Skip nano fastq QC."
},
"skip_sequali": {
"type": "boolean",
"description": "Skip sequali fastq QC."
},
"skip_bam_qc": {
"type": "boolean",
"description": "Skip alignment QC."
},
"skip_alfred": {
"type": "boolean",
"description": "Skip alred alignment QC."
},
"skip_samtools_flagstat": {
"type": "boolean",
"description": "Skip samtools alignment QC."
},
"skip_cramino": {
"type": "boolean",
"description": "Skip cramino alignment QC."
},
"cramino_min_length": {
"type": "integer",
"default": 0,
"description": "Minimum length of alignments considered by cramino."
},
"skip_ngs_bits": {
"type": "boolean",
"description": "Skip ngs bits alignment QC."
},
"ngs_bits_skip_contamination": {
"type": "boolean",
"description": "Skip ngs bit contamination detection."
},
"ngs_bits_build": {
"type": "string",
"default": "hg38",
"description": "Ngs bits genome build (hg38)."
},
"skip_mapping": {
"type": "boolean",
"description": "Skip mapping to reference genome."
},
"skip_bam_to_bigwig": {
"type": "boolean",
"description": "Skip creation of bigWig alignment files for viewing in genome browsers."
},
"skip_flair": {
"type": "boolean",
"description": "Skip FLAIR transcript reconstruction."
},
"skip_flair_correct": {
"type": "boolean",
"description": "Skip FLAIR correct module.",
"default": true
},
"extra_flair_correct_options": {
"type": "string",
"description": "Additional options for FLAIR correct."
},
"skip_flair_collapse": {
"type": "boolean",
"description": "Skip FLAIR collapse module."
},
"extra_flair_collapse_options": {
"type": "string",
"description": "Additional options for FLAIR collapse."
},
"skip_bambu": {
"type": "boolean",
"description": "Skip bambu transcript reconstruction."
},
"extra_bambu_options": {
"type": "string",
"description": "Additional options for bambu."
},
"skip_stringtie": {
"type": "boolean",
"description": "Skip StringTie transcript reconstruction."
},
"extra_stringtie_options": {
"type": "string",
"description": "Additional options for StringTie."
},
"skip_isoquant": {
"type": "boolean",
"description": "Skip IsoQuant transcript reconstruction."
},
"skip_isoquant_correction": {
"type": "boolean",
"description": "Skip IsoQuant read correction."
},
"extra_isoquant_options": {
"type": "string",
"description": "Additional options for IsoQuant."
},
"skip_jaccard": {
"type": "boolean",
"description": "Skip calculation of jaccard statistic."
},
"skip_gffcompare": {
"type": "boolean",
"description": "Skip gffcompare transcirptome assessment."
},
"extra_gffcompare_options": {
"type": "string",
"description": "Additional gffcompare options."
},
"skip_sqanti_all": {
"type": "boolean",
"description": "Skip all of SQANTI modules."
},
"skip_sqanti_qc": {
"type": "boolean",
"description": "Skip SQANTI QC module."
},
"sqanti_qc_reference": {
"type": "string",
"default": "human",
"description": "Reference genome name for SQANTI QC.",
"help_text": "Only supports 'human' currently."
},
"sqanti_qc_cage": {
"type": "boolean",
"default": true,
"description": "Use CAGE data with SQANTI QC."
},
"sqanti_qc_cage_path": {
"type": "string",
"description": "Path to SQANTI QC CAGE data."
},
"sqanti_qc_polyA_sites": {
"type": "boolean",
"default": true,
"description": "Use polyA sites data with SQANTI QC."
},
"sqanti_qc_polyA_sites_path": {
"type": "string",
"description": "Path to SQANTI QC polyA sites data."
},
"sqanti_qc_polyA_motif": {
"type": "boolean",
"default": true,
"description": "Use polyA motif data with SQANTI QC."
},
"sqanti_qc_polyA_motif_path": {
"type": "string",
"description": "Path to SQANTI QC polyA motif data."
},
"sqanti_qc_intron_junctions": {
"type": "boolean",
"default": true,
"description": "Use intron junction data with SQANTI QC."
},
"sqanti_qc_intron_path": {
"type": "string",
"description": "Path to SQANTI QC intron site data."
},
"extra_sqanti_qc_options": {
"type": "string",
"description": "Additional options for SQANTI QC."
},
"skip_jaffal": {
"type": "boolean",
"description": "Skip JAFFAL fusion gene detection.",
"default": true
},
"skip_jaffal_download": {
"type": "boolean",
"description": "Skip download of JAFFAL reference (recommended).",
"default": true
},
"jaffal_reference": {
"type": "string",
"description": "Path to JAFFAL reference directory."
},
"skip_transcript_quantification": {
"type": "boolean",
"description": "Skip all transcript quantification."
},
"skip_oarfish": {
"type": "boolean",
"description": "Skip OARFISH transcript quantification."
},
"sylph_database": {
"type": "string",
"default": "data/gtdb-r226-c1000-dbv1.syldb",
"description": "Path to sylph prebuilt database used for downloads - from https://sylph-docs.github.io/pre%E2%80%90built-databases/ ."
},
"skip_sylph": {
"type": "boolean",
"description": "Skip sylph profiling of unmapped reads."
},
"sylph_database_name": {
"type": "string",
"default": "GTDB_r226",
"description": "Name of sylph database, must be identical to those given in https://sylph-docs.github.io/pre%E2%80%90built-databases/ , with spaces replaced with underscores."
}
}
}
},
"allOf": [
{
"$ref": "#/$defs/reference_genome_options"
},
{
"$ref": "#/$defs/input_output_options"
},
{
"$ref": "#/$defs/multiqc_options"
},
{
"$ref": "#/$defs/generic_options"
},
{
"$ref": "#/$defs/module_specific_options"
}
]
}