-
Notifications
You must be signed in to change notification settings - Fork 9
Expand file tree
/
Copy pathnextflow_schema.json
More file actions
311 lines (311 loc) · 15 KB
/
Copy pathnextflow_schema.json
File metadata and controls
311 lines (311 loc) · 15 KB
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
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/sanger-tol/genomeassembly/master/nextflow_schema.json",
"title": "sanger-tol/genomeassembly pipeline parameters",
"description": "A bioinformatics best-practice analysis pipeline for genome assembly from PacBio CCS and HiC reads",
"type": "object",
"$defs": {
"input_output_options": {
"title": "Input/output options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Define where the pipeline should find input data and save output data.",
"required": ["genomic_data", "assembly_specs"],
"properties": {
"genomic_data": {
"type": "string",
"description": "Input YAML specifying the location of all genomic data for assembly. See the documentation for a full specification.",
"format": "file-path",
"schema": "assets/schema_genomic.json"
},
"assembly_specs": {
"type": "string",
"description": "YAML file specifying the parameters for a set of assemblies, including datasets and arguments. See the documentation for a full specification.",
"format": "file-path",
"schema": "assets/schema_assembly.json"
},
"outdir": {
"type": "string",
"format": "directory-path",
"description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
"fa_icon": "fas fa-folder-open"
},
"email": {
"type": "string",
"description": "Email address for completion summary.",
"fa_icon": "fas fa-envelope",
"help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
"pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
}
}
},
"input_preparation_options": {
"title": "Input preparation options",
"type": "object",
"description": "Options to control input preparation prior to starting assembly.",
"default": "",
"properties": {
"kmer_size": {
"type": "integer",
"default": 31,
"description": "Kmer size to use for all kmer-based subroutines in the Kmer profiling subworkflow. This parameter is overridden by the provided kmer size for a given input read set if a FastK database is provided."
},
"genomescope_args": {
"type": "string",
"description": "Optional command-line arguments to pass to genomescope2."
},
"save_fastk_databases": {
"type": "boolean",
"description": "Save the FastK databases generated by the pipeline to the output directory."
}
},
"fa_icon": "fas fa-signal"
},
"purging_options": {
"title": "Purging options",
"type": "object",
"description": "Options to contol the purging of duplicated haplotigs from an assembly.",
"default": "",
"properties": {
"purging_reads_chunk_size": {
"type": "integer",
"default": 500000,
"description": "How many reads to map in a single chunk when mapping reads to the primary assembly during purging."
},
"ont_minimap2_map_mode": {
"type": "string",
"default": "map-ont",
"description": "Which minimap2 mapping mode to use when mapping ONT? See https://lh3.github.io/minimap2/minimap2.html for a full list."
}
},
"required": ["purging_reads_chunk_size", "ont_minimap2_map_mode"]
},
"polishing_options": {
"title": "Polishing options",
"type": "object",
"description": "Options to control polishing an assembly.",
"default": "",
"properties": {
"polishing_longranger_container_path": {
"type": "string",
"description": "Path to a container with longranger to use for the longranger processes. Required for polishing to run."
},
"polishing_n_chunks_bed": {
"type": "integer",
"default": 100,
"description": "Number of chunks to split assembly into for polishing."
}
}
},
"hi_c_mapping_and_scaffolding_options": {
"title": "Hi-C mapping and scaffolding options",
"type": "object",
"description": "Options to control the mapping of Hi-C reads and scaffolding of an assembly.",
"default": "",
"properties": {
"hic_aligner": {
"type": "string",
"default": "bwamem2",
"enum": ["bwamem2", "minimap2"],
"description": "Which aligner to use to align Hi-C reads to the reference"
},
"hic_mapping_cram_chunk_size": {
"type": "integer",
"default": 10000,
"description": "Number of CRAM slices to include per CRAM file per mapping chunk. Lower values mean more Hi-C mapping jobs are spawned, but each should have a lower run time."
},
"hic_mapping_minq": {
"type": "integer",
"default": 10,
"description": "Minimum MapQ score for a Hi-C read to be retained for scaffolding."
},
"scaffolding_cool_bin_size": {
"type": "integer",
"default": 1000,
"description": "Bin size to use when building cooler contact maps."
}
}
},
"assembly_qc_options": {
"title": "Assembly QC options",
"type": "object",
"description": "Parameters to configure the assembly QC steps that run for each assembly generated.",
"default": "",
"properties": {
"busco_lineage_directory": {
"type": "string",
"description": "Path to a local directory containing pre-downloade BUSCO lineages.",
"help_text": "Lineage datasets can be downloaded using `busco --download`.",
"format": "directory-path"
}
}
},
"organelle_assembly_options": {
"title": "Organelle assembly options",
"type": "object",
"description": "",
"default": "",
"properties": {
"mitohifi_min_ref_len": {
"type": "integer",
"default": 15000,
"description": "The minimum size of a reference organellar genome to use in reference-based organelle assembly with Mitohifi"
}
},
"required": ["mitohifi_min_ref_len"]
},
"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"
}
}
},
"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": {
"version": {
"type": "boolean",
"description": "Display version and exit.",
"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})$",
"help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
"hidden": true
},
"plaintext_email": {
"type": "boolean",
"description": "Send plain-text email instead of HTML.",
"fa_icon": "fas fa-remove-format",
"hidden": true
},
"monochrome_logs": {
"type": "boolean",
"description": "Do not use coloured log outputs.",
"fa_icon": "fas fa-palette",
"hidden": true
},
"validate_params": {
"type": "boolean",
"description": "Boolean whether to validate parameters against the schema at runtime",
"default": true,
"fa_icon": "fas fa-check-square",
"hidden": true
},
"pipelines_testdata_base_path": {
"type": "string",
"fa_icon": "far fa-check-circle",
"description": "Base URL or local path to location of pipeline test dataset files",
"default": "https://raw.githubusercontent.com/nf-core/test-datasets/",
"hidden": true
},
"trace_report_suffix": {
"type": "string",
"fa_icon": "far calendar",
"description": "Suffix to add to the trace report filename. Default is the date and time in the format yyyy-MM-dd_HH-mm-ss.",
"hidden": true
},
"help": {
"type": ["boolean", "string"],
"description": "Display the help message."
},
"help_full": {
"type": "boolean",
"description": "Display the full detailed help message."
},
"show_hidden": {
"type": "boolean",
"description": "Display hidden parameters in the help message (only works when --help or --help_full are provided)."
}
}
}
},
"allOf": [
{
"$ref": "#/$defs/input_output_options"
},
{
"$ref": "#/$defs/input_preparation_options"
},
{
"$ref": "#/$defs/purging_options"
},
{
"$ref": "#/$defs/polishing_options"
},
{
"$ref": "#/$defs/hi_c_mapping_and_scaffolding_options"
},
{
"$ref": "#/$defs/assembly_qc_options"
},
{
"$ref": "#/$defs/organelle_assembly_options"
},
{
"$ref": "#/$defs/institutional_config_options"
},
{
"$ref": "#/$defs/generic_options"
}
]
}