forked from jimmyliu1326/SamnSero_Nextflow
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathnextflow_schema.json
More file actions
246 lines (246 loc) · 9.42 KB
/
nextflow_schema.json
File metadata and controls
246 lines (246 loc) · 9.42 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
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/SamnSero/master/nextflow_schema.json",
"title": "SamnSero pipeline parameters",
"description": "Bacterial Genomics Workflow for Infectious Disease Diagnostics and Surveillance",
"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": {
"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//usage#samplesheet-input).",
"fa_icon": "fas fa-file-csv"
},
"out_dir": {
"type": "string",
"description": "Path to the output directory where the results will be saved.",
"default": "./results",
"fa_icon": "fas fa-folder-open",
"format": "directory-path"
},
"watchdir": {
"type": "string",
"fa_icon": "fas fa-eye",
"format": "directory-path",
"description": "Path to the watch directory for executing the pipeline in real-time"
}
}
},
"sequencing_info": {
"title": "Sequencing Info",
"type": "object",
"description": "",
"default": "",
"properties": {
"seq_platform": {
"type": "string",
"default": "nanopore",
"description": "Sequencing platform that generated the input data.",
"enum": [
"nanopore",
"illumina"
]
},
"taxon_name": {
"type": "string",
"default": "Salmonella enterica",
"description": "Name of the target organism sequenced. Quote the string if the name contains space characters."
},
"taxon_level": {
"type": "string",
"default": "species",
"description": "Taxon rank of the target organism sequenced.",
"enum": [
"species",
"kingdom",
"phylum",
"class",
"order",
"family",
"genus",
"domain"
]
},
"meta": {
"type": "string",
"description": "Optimize assembly parameters for metagenomic samples",
"default": "off",
"enum": [
"off",
"untargeted",
"targeted"
]
},
"nanohq": {
"type": "boolean",
"description": "Input reads were basecalled using Guppy v5 SUP models"
}
},
"fa_icon": "fas fa-info-circle"
},
"data_quality_check": {
"title": "Data quality check",
"type": "object",
"description": "",
"default": "",
"properties": {
"qc": {
"type": "boolean",
"description": "Perform quality check on genome assemblies"
},
"trim": {
"type": "boolean",
"description": "Perform read trimming"
},
"centrifuge": {
"type": "string",
"default": "/mnt/e/data/reference/centrifuge/",
"description": "Path to DIRECTORY containing Centrifuge database index (required if using --qc)",
"format": "directory-path"
}
},
"fa_icon": "far fa-check-circle"
},
"genome_annotation": {
"title": "Genome annotation",
"type": "object",
"default": "",
"properties": {
"annot": {
"type": "boolean",
"description": "Annotate genome assemblies"
}
},
"fa_icon": "fas fa-search"
},
"metagenomics_options": {
"title": "Metagenomics options",
"type": "object",
"description": "",
"default": "",
"properties": {
"min_binsize": {
"type": "integer",
"default": 2000000,
"description": "Minimum bin size to output and analyze"
},
"disable_binning": {
"type": "boolean",
"description": "Disable metagenomic binning on metagenome assembly"
},
"mmseqs_db": {
"type": "string",
"default": "/mnt/e/data/reference/mmseqs2_bacteria",
"description": "MMSeqs2 taxonomic database DIRECTORY path",
"format": "file-path"
},
"lca_rank": {
"type": "string",
"default": "genus",
"description": "Restrict sequence analysis to contigs assigned at this lowest LCA rank (only applies when using --meta targeted and --disable_binning)",
"enum": [
"species",
"kingdom",
"phylum",
"class",
"order",
"family",
"genus",
"domain"
]
}
}
},
"gpu_acceleration": {
"title": "GPU acceleration",
"type": "object",
"description": "",
"default": "",
"properties": {
"gpu": {
"type": "boolean",
"description": "Accelerate specific processes that utilize GPU computing. Must have NVIDIA Container Toolkit installed to enable GPU computing"
},
"medaka_batchsize": {
"type": "integer",
"default": 100,
"description": "Medaka batch size (smaller value reduces memory use)"
}
},
"fa_icon": "fas fa-tachometer-alt"
},
"slurm_hpc": {
"title": "Slurm HPC",
"type": "object",
"description": "",
"default": "",
"properties": {
"account": {
"type": "string",
"description": "Slurm group account"
}
},
"fa_icon": "fas fa-server",
"help_text": ""
},
"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
},
"version": {
"type": "boolean",
"description": "Print pipeline version"
},
"noreport": {
"type": "boolean",
"description": "Do not generate interactive reports"
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/input_output_options"
},
{
"$ref": "#/definitions/sequencing_info"
},
{
"$ref": "#/definitions/data_quality_check"
},
{
"$ref": "#/definitions/genome_annotation"
},
{
"$ref": "#/definitions/metagenomics_options"
},
{
"$ref": "#/definitions/gpu_acceleration"
},
{
"$ref": "#/definitions/slurm_hpc"
},
{
"$ref": "#/definitions/generic_options"
}
]
}