-
Notifications
You must be signed in to change notification settings - Fork 4
/
Copy pathnextflow_schema.json
286 lines (286 loc) · 15.3 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
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/Arcadia-Science/noveltree/master/nextflow_schema.json",
"title": "Arcadia-Science/noveltree pipeline parameters",
"description": "taking proteomes from diverse organisms and inferring orthology, gene-family trees, and a species tree",
"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",
"mcl_inflation",
"outdir",
"min_num_spp_per_og",
"min_prop_spp_for_spptree",
"min_num_grp_per_og",
"max_copy_num_spp_tree",
"max_copy_num_gene_trees"
],
"properties": {
"input": {
"type": "string",
"format": "file-path",
"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 design 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.",
"fa_icon": "fas fa-file-csv"
},
"mcl_inflation": {
"type": "string",
"description": "Array of MCL inflation values, expressed as a comma-separated string (ie 1.5,3.0,4.5), or a single numerical value (ie 1.5).",
"fa_icon": "fas fa-file-signature"
},
"outdir": {
"type": "string",
"format": "directory-path",
"description": "The output directory where the results will be saved. Use absolute paths when specifying S3 URIs. No trailing / please.",
"fa_icon": "fas fa-folder-open"
},
"busco_lineages_path": {
"type": "string",
"format": "file-path",
"description": "Optional path to where BUSCO lineage datasets are stored remotely (e.g. on S3).",
"fa_icon": "fas fa-file-csv"
},
"min_num_seq_per_og": {
"type": "integer",
"default": 4,
"description": "The minimum number of sequences within a gene family required for retention of that family for phylogenetic inference."
},
"min_num_spp_per_og": {
"type": "integer",
"default": 4,
"description": "Minimum number of species included in orthogroup required for inference of MSA, gene family tree, and inclusion in species tree inference."
},
"min_prop_spp_for_spptree": {
"type": "number",
"default": 0.25,
"description": "Minimum proportion of all species in orthogroup for inclusion in species tree inference."
},
"min_num_grp_per_og": {
"type": "integer",
"default": 1,
"description": "Minimum number of higher-level taxonomic groups included in orthogroup required for inference of MSA, gene family tree, and inclusion in species tree inference."
},
"max_copy_num_spp_tree": {
"type": "integer",
"default": 5,
"description": "Maximum mean per-species orthogroup gene copy allowed for species tree inference."
},
"max_copy_num_gene_trees": {
"type": "integer",
"default": 10,
"description": "Maximum mean per-species orthogroup gene copy allowed for gene family tree / species tree reconciliation."
},
"aligner": {
"type": "string",
"default": "witch",
"description": "Option specifying the method used to infer multiple sequence alignments. Either WITCH ('witch') or MAFFT ('mafft'). Additional params for either method should be provided in modules.config."
},
"msa_trimmer": {
"type": "string",
"default": "none",
"description": "Option specifying the method used to trim/clean multiple sequence alignments prior to phylogenetic inference. Either CIAlign ('cialign') or ClipKIT ('clipkit'). Additional params for either method should be provided in modules.config."
},
"min_ungapped_length": {
"type": "integer",
"default": 20,
"description": "Option specifying the minimum ungapped length of cleaned/trimmed multiple sequence alignments. Prevents ClipKIT from removing all non-gap characters. Specify as null (no quotes) if you do not want to remove short sequences with CIAlign."
},
"tree_method": {
"type": "string",
"default": "fasttree",
"description": "Method used to infer phylogenies from trimmed and cleaned MSAs. Default is fasttree, alternative is iqtree."
},
"tree_model": {
"type": "string",
"default": "LG+F+G4",
"description": "AA substitution model used by IQ-TREE for gene family tree inference. Default model is generally applicable, but may be specified by the user. Not used if running FastTree."
},
"tree_model_pmsf": {
"type": "string",
"default": "none",
"description": "Optional posterior mean site frequency (PMSF) approximation model for IQ-TREE. Conducts a second round of phylogenetic inference, using a guide tree inferred using the \"tree_model\" parameter specification."
},
"outgroups": {
"type": "string",
"default": "none",
"description": "If provided, these taxa will be used to manually root the species tree inferred using Asteroid. This tree (with branch lengths inferred using SpeciesRax) will be used in GeneRax analyses. This should be a comma-separated string of sample/species IDs corresponding to the samplesheet. Example: \"Genus_species1,Genus_species2\""
},
"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})$"
}
}
},
"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'`"
}
},
"required": [
"max_cpus",
"max_memory"
]
},
"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.",
"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.",
"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"
],
"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})$",
"help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
"hidden": true
},
"plaintext_email": {
"type": "boolean",
"description": "Send plain-text email instead of HTML.",
"fa_icon": "fas fa-remove-format",
"hidden": true
},
"monochrome_logs": {
"type": "boolean",
"description": "Do not use coloured log outputs.",
"fa_icon": "fas fa-palette",
"hidden": true
},
"hook_url": {
"type": "string",
"description": "Incoming hook URL for messaging service",
"fa_icon": "fas fa-people-group",
"help_text": "Incoming hook URL for messaging service. Currently, only MS Teams is supported.",
"hidden": true
},
"tracedir": {
"type": "string",
"description": "Directory to keep pipeline Nextflow logs and reports.",
"default": "${params.outdir}/pipeline_info",
"fa_icon": "fas fa-cogs",
"hidden": true
},
"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."
},
"enable_conda": {
"type": "boolean",
"description": "Run this workflow with Conda. You can also use '-profile conda' instead of providing this parameter.",
"hidden": true,
"fa_icon": "fas fa-bacon"
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/input_output_options"
},
{
"$ref": "#/definitions/max_job_request_options"
},
{
"$ref": "#/definitions/generic_options"
}
],
"properties": {
"custom_config_version": {
"type": "string",
"default": "master"
},
"custom_config_base": {
"type": "string",
"default": "https://raw.githubusercontent.com/nf-core/configs/master"
},
"config_profile_description": {
"type": "string",
"default": "None"
},
"config_profile_contact": {
"type": "string",
"default": "None"
},
"config_profile_url": {
"type": "string",
"default": "None"
},
"config_profile_name": {
"type": "string",
"default": "None"
}
}
}