-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathnextflow_schema.json
263 lines (263 loc) · 10.5 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
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/prototaxites/mgannotate/master/nextflow_schema.json",
"title": "prototaxites/mgannotate pipeline parameters",
"description": "",
"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": ["outdir"],
"properties": {
"assemblies": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/csv",
"schema": "assets/schema_assemblies.json",
"pattern": "^\\S+\\.csv$",
"description": "Path to comma-separated file containing information about the assemblies for annotation.",
"help_text": "Requires a CSV file with 3 headers.\n\nassemblyid,assembler,path",
"fa_icon": "fas fa-file-csv"
},
"reads": {
"type": "string",
"description": "Path to comma-separated file containing information about the reads to be mapped to the assemblies..",
"format": "file-path",
"schema": "assets/schema_reads.json",
"help_text": "Requires a CSV file with 4 headers:\n\nsampleid,assemblyid,forward_reads,reverse_reads"
},
"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"
},
"assemblies_are_genes": {
"type": "boolean",
"description": "If the input contigs are already gene predictions, this can be specified to skip gene prediction."
}
}
},
"database_options": {
"title": "Database options",
"type": "object",
"description": "",
"default": "",
"properties": {
"mmseqs_func_db": {
"type": "string",
"description": "Name of an MMSeqs2 database for functional annotation"
},
"mmseqs_func_db_local": {
"type": "string",
"format": "directory-path",
"description": "Path to local MMSeqs2 database for functional annotation"
},
"mmseqs_tax_db": {
"type": "string",
"description": "Name of an MMSeqs2 database for taxonomic annotation"
},
"mmseqs_tax_db_local": {
"type": "string",
"format": "directory-path",
"description": "Path to local MMSeqs2 database for taxonomic"
},
"eggnog_db": {
"type": "string",
"description": "Path to Eggnog-Mapper data directoy.",
"format": "directory-path"
},
"save_mmseqs_db": {
"type": "boolean",
"description": "Save download MMSeqs2 databases?"
},
"save_eggnog_db": {
"type": "boolean",
"description": "If the eggnog-mapper database is downloaded automatically, save the output database to the output folder."
}
}
},
"taxonomic_filtering": {
"title": "Taxonomic filtering",
"type": "object",
"description": "",
"default": "",
"properties": {
"filter_contigs": {
"type": "boolean",
"description": "Enable taxonomic filtering of contigs"
},
"filter_taxon_list": {
"type": "string",
"description": "A string defining the NCBI taxonomy nodes to keep/discard"
},
"save_filtered_assemblies_mmseqs": {
"type": "boolean",
"description": "Save filtered assemblies as mmseqs databases?",
"enum": ["fasta", "mmseqs", "none"]
},
"save_filtered_assemblies_fasta": {
"type": "boolean",
"description": "Save filtered assemblies as fasta files?"
}
}
},
"annotation": {
"title": "Annotation",
"type": "object",
"description": "",
"default": "",
"properties": {
"enable_annotation": {
"type": "boolean",
"default": true,
"description": "Enable annotation of genes"
},
"cluster_genes": {
"type": "boolean",
"description": "Concatenate all contigs across all assemblies and cluster them prior to annotation."
},
"cluster_id": {
"type": "string",
"default": "genes",
"description": "An assembly id that is applied to the clustered gene predictions. Will be used in the output filenames; useful if making multiple runs of the pipeline."
},
"mmseqs_cluster_options": {
"type": "string",
"description": "Mmseqs command-line arguments for the mmseqs cluster call.",
"default": "--min-seq-id 0.95 --cov-mode 1 -c 0.9"
}
}
},
"coverage": {
"title": "Coverage",
"type": "object",
"description": "",
"default": "",
"properties": {
"enable_coverage": {
"type": "boolean",
"default": true,
"description": "Enable calculation of coverage of genes"
},
"use_strobealign": {
"type": "boolean",
"default": true,
"description": "If using gene clustering, use strobealign to map reads to genes using CoverM. If disabled, Minimap2 is used instead."
},
"go_list": {
"type": "string",
"default": "$baseDir/assets/GOs.csv",
"description": "CSV file containing a list of Gene Orthology terms. Three columns: id,lbl,description.",
"help_text": "id should contain a GO term in the \"GO:XXXXXXXX\" format.\nlbl is the name of the GO term.\ndescription is a free-text description of the GO term."
}
}
},
"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$",
"hidden": true,
"help_text": "Use to set an upper-limit for the memory requirement for each process. Should be a string in the format integer-unit e.g. `--max_memory '8.GB'`"
},
"max_time": {
"type": "string",
"description": "Maximum amount of time that can be requested for any single job.",
"default": "240.h",
"fa_icon": "far fa-clock",
"pattern": "^(\\d+\\.?\\s*(s|m|h|d|day)\\s*)+$",
"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'`"
}
}
},
"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": {
"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
},
"validationShowHiddenParams": {
"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."
},
"validationFailUnrecognisedParams": {
"type": "boolean",
"fa_icon": "far fa-check-circle",
"description": "Validation of parameters fails when an unrecognised parameter is found.",
"hidden": true,
"help_text": "By default, when an unrecognised parameter is found, it returns a warinig."
},
"validationLenientMode": {
"type": "boolean",
"fa_icon": "far fa-check-circle",
"description": "Validation of parameters in lenient more.",
"hidden": true,
"help_text": "Allows string values that are parseable as numbers or booleans. For further information see [JSONSchema docs](https://github.com/everit-org/json-schema#lenient-mode)."
},
"publish_dir_mode": {
"type": "string",
"default": "copy",
"description": "How to stage files in the publication directory.",
"hidden": true
}
},
"required": ["publish_dir_mode"]
}
},
"allOf": [
{
"$ref": "#/definitions/input_output_options"
},
{
"$ref": "#/definitions/database_options"
},
{
"$ref": "#/definitions/taxonomic_filtering"
},
{
"$ref": "#/definitions/annotation"
},
{
"$ref": "#/definitions/coverage"
},
{
"$ref": "#/definitions/max_job_request_options"
},
{
"$ref": "#/definitions/generic_options"
}
]
}