-
Notifications
You must be signed in to change notification settings - Fork 5
/
Copy pathnextflow_schema.json
279 lines (279 loc) · 14.5 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
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/fmalmeida/ngs-preprocess/master/nextflow_schema.json",
"title": "fmalmeida/ngs-preprocess pipeline parameters",
"description": "Nextflow pipeline for NGS preprocessing",
"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",
"properties": {
"output": {
"type": "string",
"help_text": "Where to place results?",
"fa_icon": "fas fa-folder"
},
"sra_ids": {
"type": "string",
"fa_icon": "fas fa-file"
},
"shortreads": {
"type": "string",
"description": "Input short reads",
"fa_icon": "fas fa-copy",
"help_text": "Set path to your input short reads (paired or single end). For paired, users must use the following notation: \"path/to/dir/pattern*_{1,2}.fastq\".\n\nIt can be gzipped or not. The *_{1,2}* regex is required so that nextflow can properly load the exact read pairs. Read more [in their manual](https://www.nextflow.io/docs/latest/channel.html#fromfilepairs)."
},
"shortreads_type": {
"type": "string",
"description": "Short reads are paired or single?",
"help_text": "Which is the sequencing library used for your input reads? 'paired' or 'single'?\n\nNote: single notation is used for unpaired data.",
"enum": [
"paired",
"single"
],
"fa_icon": "fas fa-question-circle"
},
"nanopore_fastq": {
"type": "string",
"description": "Input nanopore longreads",
"fa_icon": "fas fa-file",
"help_text": "Path to your nanopore reads. It can be gzipped or not."
},
"pacbio_bam": {
"type": "string",
"description": "Input pacbio subreads (.bam)",
"fa_icon": "fas fa-file",
"help_text": "Path to pacbio subreads in bam format. This applies to the majority of pacbio sequencers and chemistries."
},
"pacbio_h5": {
"type": "string",
"description": "Folder with pacbio reads (.h5)",
"fa_icon": "fas fa-folder",
"help_text": "Set path to the directory containing your pacbio reads in legacy (.h5) format. This applies to old/legacy pacbio sequencers and chemistries."
}
},
"required": [
"output"
]
},
"computational_options": {
"title": "Computational options",
"type": "object",
"fa_icon": "fab fa-acquisitions-incorporated",
"description": "Set the top limit of resources for pipeline",
"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",
"default": 4,
"description": "Max amount of threads to use"
},
"max_memory": {
"type": "string",
"default": "6.GB",
"description": "Max amount of memory to use"
},
"max_time": {
"type": "string",
"default": "40.h",
"description": "Max amount of time for a job"
}
}
},
"long_reads_parameters": {
"title": "Long reads parameters",
"type": "object",
"fa_icon": "fas fa-file-import",
"description": "Additional / Optional parameters",
"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": {
"lreads_min_length": {
"type": "integer",
"description": "Min. length for long reads",
"help_text": "It uses nanofilt to filter nanopore and pacbio long reads by a min. length threshold.",
"fa_icon": "fas fa-ruler-horizontal",
"default": 500
},
"lreads_min_quality": {
"type": "integer",
"description": "Min. quality for long reads",
"help_text": "It uses nanofilt to filter nanopore and pacbio long reads by a min. quality threshold.",
"fa_icon": "fas fa-filter",
"default": 5
},
"use_porechop_abi": {
"type": "boolean",
"fa_icon": "fas fa-barcode",
"description": "Do you want to use ab initio porechop implementation?",
"help_text": "Incompatible with demultiplexing."
},
"nanopore_is_barcoded": {
"type": "boolean",
"fa_icon": "fas fa-barcode",
"description": "Nanopore reads are barcoded?",
"help_text": "You have barcoded nanopore reads? When using this paremeter the pipeline triggers porechop to demultiplex the data."
},
"nanopore_sequencing_summary": {
"type": "string",
"description": "Path to nanopore sequencing summary",
"help_text": "Optional. Path to nanopore sequencing summary. If given, the pipeline will trigger pycoQC to calculate nanopore long reads statistics.\n\npycoQC reports will be saved using the files basename, so please, use meaningful basename, such as: sample1.txt, sample2.txt, etc.",
"fa_icon": "fas fa-file"
},
"pacbio_barcodes": {
"type": "string",
"fa_icon": "fas fa-barcode",
"description": "Path to pacbio barcodes",
"help_text": "You have barcoded pacbio reads? This parameter sets path the your pacbio barcodes in fasta or xml. It will use this barcodes to demultiplex the data."
},
"pacbio_barcode_design": {
"type": "string",
"description": "Pacbio barcode design",
"help_text": "For demultiplexing you can choose how to associate the barcodes: same, different or any type of combination. By default, only reads with 'same' barcodes in both ends are demultiplexed.",
"fa_icon": "fas fa-question-circle",
"enum": [
"same",
"different",
"any"
],
"default": "same"
},
"pacbio_get_hifi": {
"type": "boolean",
"description": "Try to obtain hifi reads?",
"help_text": "This parameter will trigger pacbio ccs software to produce high fidelity reads. Not all chemistry and sequencers are compatible. If not compatible the pipeline will throw an error.",
"fa_icon": "fas fa-question-circle"
}
}
},
"short_reads_parameters": {
"title": "Short reads parameters",
"type": "object",
"description": "Additional / Optional parameters",
"default": "",
"fa_icon": "fas fa-file-import",
"properties": {
"fastp_average_quality": {
"type": "integer",
"default": 20,
"help_text": "Fastp will calculate the average quality of reads and filter out those not passing the threshold. If you want to filter low quality bases from the ends, please read the fastp manual and add the proper parameters to the pipeline with --fastp_additional_parameters."
},
"fastp_merge_pairs": {
"type": "boolean",
"help_text": "Fastp will try to merge read pairs. It works only with paired end reads."
},
"fastp_correct_pairs": {
"type": "boolean",
"help_text": "Fastp will perform an overlap-based correction step in paired end reads to fix some low quality bases."
},
"fastp_additional_parameters": {
"type": "string",
"help_text": "Pass any additional parameter that you want to fastp. See https://github.com/OpenGene/fastp."
}
}
},
"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"
},
"get_config": {
"type": "boolean",
"description": "Download template config for parameters",
"fa_icon": "fas fa-question-circle"
},
"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."
}
}
},
"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": "master",
"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"
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/input_output_options"
},
{
"$ref": "#/definitions/computational_options"
},
{
"$ref": "#/definitions/long_reads_parameters"
},
{
"$ref": "#/definitions/short_reads_parameters"
},
{
"$ref": "#/definitions/generic_options"
},
{
"$ref": "#/definitions/institutional_config_options"
}
]
}