forked from epi2me-labs/wf-artic
-
Notifications
You must be signed in to change notification settings - Fork 1
/
nextflow_schema.json
351 lines (351 loc) · 12.3 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
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/./master/nextflow_schema.json",
"title": "artic-network/artic-mpxv-nf",
"workflow_title": "Artic Network MPXV Analysis",
"description": "Run the ARTIC fieldbioinformatics workflow on multiplexed MPXV ONT data",
"demo_url": "",
"aws_demo_url": "",
"url": "https://github.com/artic-network/artic-mpxv-nf",
"type": "object",
"definitions": {
"input": {
"title": "Input Options",
"type": "object",
"fa_icon": "fas fa-arrow-right",
"description": "Parameters for finding and handling input data for analysis.",
"properties": {
"fastq": {
"type": "string",
"title": "FASTQ",
"format": "path",
"description": "FASTQ files to use in the analysis.",
"help_text": "This accepts one of three cases: (i) the path to a single FASTQ file; (ii) the path to a top-level directory containing FASTQ files; (iii) the path to a directory containing one level of sub-directories which in turn contain FASTQ files. In the first and second case, a sample name can be supplied with `--sample`. In the last case, the data is assumed to be multiplexed with the names of the sub-directories as barcodes. In this case, a sample sheet can be provided with `--sample_sheet`."
},
"analyse_unclassified": {
"type": "boolean",
"default": false,
"description": "Analyse unclassified reads from input directory. By default the workflow will not process reads in the unclassified directory.",
"help_text": "If selected and if the input is a multiplex directory the workflow will also process the unclassified directory."
}
},
"required": [
"fastq"
]
},
"primer_scheme_selection": {
"title": "Primer Scheme Selection",
"type": "object",
"fa_icon": "fas fa-code",
"description": "Reference genome related files and options required for the workflow.",
"properties": {
"scheme_name": {
"type": "string",
"default": "MPXV",
"description": "Primer scheme name.",
"help_text": "This should be set to `MPXV`"
},
"scheme_version": {
"type": "string",
"default": "artic-inrb-mpox/v1.0.0-cladeia",
"description": "Primer scheme version.",
"help_text": "Version of the primer scheme to use, `yale-mpox/v1.0.0-cladeI` and `yale-mpox/v1.0.0-cladeII` are the same scheme but use separate reference fastas.",
"enum": [
"artic-inrb-mpox/v1.0.0-cladeia",
"artic-inrb-mpox/v1.0.0-cladeib",
"artic-inrb-mpox/v1.0.0-cladeiia",
"artic-inrb-mpox/v1.0.0-cladeiib",
"yale-mpox/v1.0.0-cladeI",
"yale-mpox/v1.0.0-cladeII",
"rigshospitalet/v1.0.0",
"artic-mpox/v1.1.1-cladeI",
"artic-mpox/v1.1.1-cladeII",
"bccdc-mpox/v2.3.0-cladeI",
"bccdc-mpox/v2.3.0-cladeII"
]
},
"custom_scheme": {
"type": "string",
"format": "path",
"description": "Path to a custom scheme.",
"help_text": "If you have a custom primer scheme you can enter the details here. This must be the full path to the directory containing your appropriately named scheme bed and fasta files; primer.bed and reference.fasta. More details [here](https://labs.epi2me.io/ont-midnight-scheme-update/)."
}
}
},
"samples": {
"title": "Sample Options",
"type": "object",
"fa_icon": "fas fa-vials",
"description": "Parameters that relate to samples such as sample sheets and sample names.",
"properties": {
"sample_sheet": {
"type": "string",
"format": "file-path",
"description": "A CSV file used to map barcodes to sample aliases. The sample sheet can be provided when the input data is a directory containing sub-directories with FASTQ files.",
"help_text": "The sample sheet is a CSV file with, minimally, columns named `barcode` and `alias`. Extra columns are allowed. A `type` column is required for certain workflows and should have the following values; `test_sample`, `positive_control`, `negative_control`, `no_template_control`."
},
"sample": {
"type": "string",
"description": "A single sample name for non-multiplexed data. Permissible if passing a single .fastq(.gz) file or directory of .fastq(.gz) files."
}
}
},
"output": {
"title": "Output Options",
"type": "object",
"fa_icon": "fas fa-arrow-left",
"description": "Parameters for saving and naming workflow outputs.",
"properties": {
"out_dir": {
"type": "string",
"default": "output",
"format": "directory-path",
"description": "Directory for output of all workflow results."
}
}
},
"squirrel_options": {
"title": "Squirrel Options",
"type": "object",
"description": "Options related to MPXV",
"properties": {
"clade": {
"type": "string",
"title": "Clade",
"description": "Specify whether the sequencing run is primarily `cladeI` or `cladeII`.",
"enum": [
"cladei",
"cladeia",
"cladeib",
"cladeii",
"cladeiia",
"cladeiib"
],
"help_text": ""
},
"squirrel_threads": {
"type": "number",
"description": "Number of CPU threads to use per squirrel task.",
"help_text": "The total CPU resource used by the workflow is constrained by the executor configuration.",
"minimum": 1,
"default": 4
},
"skip_squirrel": {
"type": "boolean",
"default": false,
"description": "Skip Squirrel QC and alignment."
},
"squirrel_options": {
"type": "string",
"hidden": "true",
"description": "Pass options to Squirrel, for example \"--clade cladeii\"."
}
},
"required": [
"clade"
],
"fa_icon": "fas fa-address-card",
"help_text": "Options specific to the MPXV workflow."
},
"advanced_options": {
"title": "Advanced Options",
"type": "object",
"fa_icon": "far fa-question-circle",
"description": "Advanced options for configuring processes inside the workflow.",
"help_text": "These advanced options do not need to be changed for typical use, but allow fine tuning of workflows for users who want more control over the workflow.",
"properties": {
"artic_threads": {
"type": "number",
"description": "Number of CPU threads to use per artic task.",
"help_text": "The total CPU resource used by the workflow is constrained by the executor configuration.",
"minimum": 1,
"default": 4
},
"list_schemes": {
"type": "boolean",
"default": false,
"description": "List primer schemes and exit without running analysis."
},
"min_reads": {
"type": "number",
"title": "Minimum number of reads",
"description": "Ignore samples with fewer reads than this value.",
"default": 1000
},
"min_len": {
"type": "number",
"title": "Minimum read length",
"minimum": 50,
"maximum": 10000,
"description": "Minimum read length (default: set by scheme)."
},
"max_len": {
"type": "number",
"title": "Maximum read length",
"minimum": 50,
"maximum": 10000,
"description": "Maximum read length (default: set by scheme)."
},
"max_softclip_length": {
"type": "integer",
"title": "Maximum soft clip length",
"description": "Remove reads with alignments showing large soft clipping"
},
"normalise": {
"type": "integer",
"default": 200,
"description": "Depth ceiling for depth of coverage normalisation"
},
"override_model": {
"type": "string",
"title": "Override clair3 model selection",
"description": "Override auto-detected basecaller model that processed the signal data; used to select an appropriate Clair3 model.",
"help_text": "Per default, the workflow tries to determine the basecall model from the input data. This parameter can be used to override the detected value (or to provide a model name if none was found in the inputs). However, users should only do this if they know for certain which model was used as selecting the wrong option might give sub-optimal results. A list of recent models can be found here: https://github.com/nanoporetech/dorado#DNA-models.",
"enum": [
"r1041_e82_260bps_fast_g632",
"r1041_e82_400bps_fast_g632",
"r1041_e82_400bps_sup_g615",
"r1041_e82_260bps_hac_g632",
"r1041_e82_400bps_hac_g615",
"r1041_e82_400bps_sup_v400",
"r1041_e82_260bps_hac_v400",
"r1041_e82_400bps_hac_g632",
"r1041_e82_400bps_sup_v410",
"r1041_e82_260bps_hac_v410",
"r1041_e82_400bps_hac_v400",
"r1041_e82_400bps_sup_v420",
"r1041_e82_260bps_sup_g632",
"r1041_e82_400bps_hac_v410",
"r1041_e82_400bps_sup_v430",
"r1041_e82_260bps_sup_v400",
"r1041_e82_400bps_hac_v420",
"r1041_e82_400bps_sup_v500",
"r1041_e82_260bps_sup_v410",
"r1041_e82_400bps_hac_v430",
"r104_e81_hac_g5015",
"r1041_e82_400bps_hac_v500",
"r104_e81_sup_g5015",
"r941_prom_sup_g5014",
"r941_prom_hac_g360+g422"
]
}
}
},
"misc": {
"title": "Miscellaneous Options",
"type": "object",
"description": "Everything else.",
"default": "",
"properties": {
"lab_id": {
"type": "string",
"title": "Laboratory identifier",
"description": "Laboratory identifier, used in reporting."
},
"testkit": {
"type": "string",
"title": "Test kit identifier",
"description": "Test kit identifier, used in reporting."
},
"disable_ping": {
"type": "boolean",
"default": false,
"description": "Enable to prevent sending a workflow ping."
},
"help": {
"type": "boolean",
"default": false,
"description": "Display help text.",
"fa_icon": "fas fa-question-circle",
"hidden": true
},
"version": {
"type": "boolean",
"default": false,
"description": "Display version and exit.",
"fa_icon": "fas fa-question-circle",
"hidden": true
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/input"
},
{
"$ref": "#/definitions/primer_scheme_selection"
},
{
"$ref": "#/definitions/samples"
},
{
"$ref": "#/definitions/output"
},
{
"$ref": "#/definitions/squirrel_options"
},
{
"$ref": "#/definitions/advanced_options"
},
{
"$ref": "#/definitions/misc"
}
],
"properties": {
"aws_image_prefix": {
"type": "string",
"hidden": true
},
"aws_queue": {
"type": "string",
"hidden": true
},
"_scheme_version": {
"type": "string",
"hidden": true
},
"_scheme_name": {
"type": "string",
"hidden": true
},
"_min_len": {
"type": "string",
"hidden": true
},
"_max_len": {
"type": "string",
"hidden": true
},
"_max_softclip_length": {
"type": "string",
"hidden": true
},
"_squirrel_options": {
"type": "string",
"hidden": true
},
"monochrome_logs": {
"type": "boolean"
},
"validate_params": {
"type": "boolean",
"default": true
},
"show_hidden_params": {
"type": "boolean"
}
},
"resources": {
"recommended": {
"cpus": 4,
"memory": "8GB"
},
"minimum": {
"cpus": 2,
"memory": "4GB"
},
"run_time": "5 minutes per sample",
"arm_support": false
}
}