generated from CDCgov/template
-
Notifications
You must be signed in to change notification settings - Fork 19
/
nextflow_schema.json
executable file
·296 lines (296 loc) · 17 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
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/cdcgov/phoenix/main/nextflow_schema.json",
"title": "cdcgov/phoenix pipeline parameters",
"description": "A short-read pipeline for healthcare-associated and antimicrobial resistant pathogens.",
"type": "object",
"definitions": {
"input_output_options": {
"title": "Required Options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Define where the pipeline should find input data and save output data.",
"required": [],
"properties": {
"input": {
"type": "string",
"format": "file-path",
"mimetype": "text/csv",
"pattern": "^\\S+\\.csv$",
"schema": "assets/schema_input.json",
"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 with 3 columns, and a header row. See [usage docs](https://nf-co.re/quaisar/usage#samplesheet-input). You use this with entries PHOENIX, CDC_PHOENIX, SCAFFOLDS, and CDC_SCAFFOLDS.",
"fa_icon": "fas fa-file-csv"
},
"kraken2db": {
"type": "string",
"fa_icon": "fas fa-database",
"description": "Path (full or relative) for where kraken2 database files are, which includes hash.k2d, taxo.k2d, opts.k2d and ktaxonomy.tsv files. You can pass a decompressed folder or in its compressed '.tar.gz' form. The database can be downloaded from https://benlangmead.github.io/aws-indexes/k2 . You must use a database created after 3/14/2023.",
"default": "null"
}
}
},
"Optional_scaffold_options": {
"title": "Options for -entry SCAFFOLDS and CDC_SCAFFOLDS",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Define where the pipeline should find input scaffolds.",
"properties": {
"indir": {
"type": "string",
"description": "Path to a input directory to search for assemblies. Files with the extention '*.filtered.scaffolds.fa.gz' and '*.renamed.scaffolds.fa.gz' will be ignored. Can be a full or relative path. Alternatively, you can pass a samplesheet (columns should be 'sample,assembly') with the --input argument.",
"default": "null",
"fa_icon": "fas fa-folder-open"
},
"scaffold_ext": {
"type": "string",
"fa_icon": "fas fa-keyboard",
"description": "String that is the FULL extension of the scaffolds files you wish to input. For example, use if your file names are `<sample_id>.fa.gz` use `--scaffolds_ext '.fa.gz'` and if you want to look through subdirectories for files with the name `<sample_id>.fa.gz` then use `--scaffolds_ext '/*.fa.gz'` A regrex of this extension (ex. *.scaffolds.fa.gz) will then be used as default. Assemblies must end in '.fa.gz' or '.fasta.gz'.",
"default": ".scaffolds.fa.gz"
}
}
},
"Required_sra_options": {
"title": "Options for -entry SRA and CDC_SRA",
"type": "object",
"fa_icon": "fas fa-file-csv",
"description": "Define where the pipeline should find input scaffolds.",
"properties": {
"input_sra": {
"type": "string",
"description": "Path to a csv file that has one SRR number per line.",
"default": "null",
"fa_icon": "fas fa-folder-open"
},
"use_sra": {
"type": "boolean",
"description": "Pass this argument if you want to keep samples named by SRA number rather than sample name found in NCBI metadata.",
"default": "False",
"fa_icon": "fas fa-keyboard"
}
}
},
"Optional_options": {
"title": "Optional options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Define where the pipeline should find input data and save output data.",
"properties": {
"outdir": {
"type": "string",
"description": "Path to the output directory where the results will be saved. Can be a full or relative path.",
"default": "${launchDir}/phx_output",
"fa_icon": "fas fa-folder-open"
},
"coverage": {
"type": "string",
"description": "If you want to increase the coverage cut off >30x use --coverage (ex. --coverage 40)",
"default": "30",
"fa_icon": "fas fa-hashtag"
},
"busco_db_path": {
"type": "string",
"fa_icon": "fas fa-keyboard",
"description": "Path (full or relative) for where BUSCO files are if you want to run in offline mode. The database is ~250GB if you download it from https://busco-data.ezlab.org/v5/data/lineages/ . Use only with -entry CDC_PHOENIX, CDC_SCAFFOLDS or CDC_SRA.",
"default": "Doesn't run in offline mode and connects to the V5 BUSCO database at https://busco-data.ezlab.org/v5/data/lineages/ ."
},
"create_ncbi_sheet": {
"type": "boolean",
"fa_icon": "fas fa-keyboard",
"description": "Pass this argument to generate partially filled out excel sheets required for NCBI upload. This should still be reviewed PRIOR to upload. Only use with -entry CDC_PHOENIX and -entry PHOENIX. As a reminder, please do not submit raw sequencing data to the CDC HAI-Seq BioProject (531911) unless you are a state public health laboratory, a CDC partner or have been directed to do so by DHQP. The BioProject accession IDs in this file are specifically designated for domestic HAI bacterial pathogen sequencing data, including from the Antimicrobial Resistance Laboratory Network (AR Lab Network), state public health labs, surveillance programs, and outbreaks. For inquiries about the appropriate BioProject location for your data, please contact [email protected].",
"default": "False"
},
"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})$"
},
"multiqc_title": {
"type": "string",
"description": "MultiQC report title. Printed as page header, used for filename if not otherwise specified.",
"fa_icon": "fas fa-file-signature"
},
"publish_dir_mode": {
"type": "string",
"default": "copy"
},
"singularity_pull_docker_container": {
"type": "string",
"default": "false"
}
}
},
"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": "main",
"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,
"help_text": "If you're running offline, Nextflow will not be able to fetch the institutional config files from the internet. If you don't need them, then this is not a problem. If you do need them, you should download the files from the repo and tell Nextflow where to find them with this parameter.",
"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"
},
"config_profile_contact": {
"type": "string",
"description": "Institutional config contact information.",
"hidden": true,
"fa_icon": "fas fa-users-cog"
},
"config_profile_url": {
"type": "string",
"description": "Institutional config URL link.",
"hidden": true,
"fa_icon": "fas fa-users-cog"
}
}
},
"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",
"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$",
"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*)+$",
"help_text": "Use to set an upper-limit for the time requirement for each process. Should be a string in the format integer-unit e.g. `--max_time '2.h'`"
}
}
},
"generic_options": {
"title": "Generic options",
"type": "object",
"fa_icon": "fas fa-file-import",
"description": "Less common options for the pipeline, typically set in a config file.",
"help_text": "These options are common to all nf-core pipelines and allow you to customise some of the core preferences for how the pipeline runs.\n\nTypically these options would be set in a Nextflow config file loaded for all pipeline runs, such as `~/.nextflow/config`.",
"properties": {
"help": {
"type": "boolean",
"description": "Display help text.",
"fa_icon": "fas fa-question-circle",
"hidden": true
},
"email_on_fail": {
"type": "string",
"description": "Email address for completion summary, only when pipeline fails.",
"fa_icon": "fas fa-exclamation-triangle",
"pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$",
"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
},
"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$",
"default": "25.MB",
"fa_icon": "fas fa-file-upload",
"hidden": true
},
"monochrome_logs": {
"type": "boolean",
"description": "Do not use coloured log outputs.",
"fa_icon": "fas fa-palette",
"hidden": true
},
"multiqc_config": {
"type": "string",
"description": "Custom config file to supply to MultiQC.",
"fa_icon": "fas fa-cog",
"hidden": true
},
"tracedir": {
"type": "string",
"description": "Directory to keep pipeline Nextflow logs and reports.",
"default": "${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/institutional_config_options"
},
{
"$ref": "#/definitions/max_job_request_options"
},
{
"$ref": "#/definitions/generic_options"
}
]
}