-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathnextflow_schema.json
316 lines (316 loc) · 15.9 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
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/nf-core/drugresponseeval/master/nextflow_schema.json",
"title": "nf-core/drugresponseeval pipeline parameters",
"description": "This pipeline evaluates drug response models in various settings on a variety of datasets.",
"type": "object",
"$defs": {
"model_options": {
"title": "Model options",
"type": "object",
"fa_icon": "fa-solid fa-laptop-code",
"description": "Define the models and baselines to be tested.",
"required": ["models", "baselines"],
"properties": {
"models": {
"type": "string",
"description": "Model to be tested.",
"help_text": "Model to be tested."
},
"baselines": {
"type": "string",
"description": "Baselines to be tested.",
"help_text": "Baselines to be tested."
}
}
},
"input_output_options": {
"title": "Input/output options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Define where the pipeline should find input data and save output data.",
"required": ["run_id", "dataset_name", "outdir"],
"properties": {
"run_id": {
"type": "string",
"description": "Run ID for the pipeline.",
"help_text": "You will need to set a run identifier for the pipeline. This is used to create a unique output directory for each run."
},
"dataset_name": {
"type": "string",
"description": "Name of the dataset.",
"help_text": "Name of the dataset used for the pipeline. Allowed values are GDSC1, GDSC2, and Custom."
},
"outdir": {
"type": "string",
"format": "directory-path",
"description": "The output directory where the results will be saved. Default is results/",
"fa_icon": "fas fa-folder-open"
},
"email": {
"type": "string",
"description": "Email address for completion summary.",
"fa_icon": "fas fa-envelope",
"help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
"pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
}
}
},
"mode_options": {
"title": "Mode options (LPO/LCO/LDO)",
"type": "object",
"fa_icon": "fa-solid fa-table-cells-column-lock",
"description": "Define the mode in which the pipeline will be run.",
"required": ["test_mode"],
"properties": {
"test_mode": {
"type": "string",
"description": "Run the pipeline in test mode LPO (Leave-random-Pairs-Out), LCO (Leave-Cell-line-Out), or LDO (Leave-Drug-Out).",
"default": "LPO",
"help_text": "Which tests to run (LPO=Leave-random-Pairs-Out, LCO=Leave-Cell-line-Out, LDO=Leave-Drug-Out). Can be a list of test runs e.g. 'LPO LCO LDO' to run all tests. Default is LPO."
}
}
},
"randomization_options": {
"title": "Randomization options",
"type": "object",
"fa_icon": "fa-solid fa-dice",
"description": "Options for randomization.",
"properties": {
"randomization_mode": {
"type": "string",
"description": "Randomization mode for the pipeline.",
"help_text": "Which randomization tests to run, additionally to the normal run. Default is None which means no randomization tests are run. Modes: SVCC, SVRC, SVCD, SVRD. Can be a list of randomization tests e.g. 'SCVC SCVD' to run two tests. Default is None. SVCC: Single View Constant for Cell Lines: in this mode, one experiment is done for every cell line view the model uses (e.g. gene expression, mutation, ..). For each experiment one cell line view is held constant while the others are randomized. SVRC Single View Random for Cell Lines: in this mode, one experiment is done for every cell line view the model uses (e.g. gene expression, mutation, ..)."
},
"randomization_type": {
"type": "string",
"default": "permutation",
"description": "Randomization type for the pipeline.",
"help_text": "type of randomization to use. Choose from \"permutation\", \"invariant\". Default is \"permutation"
}
}
},
"robustness_options": {
"title": "Robustness options",
"type": "object",
"fa_icon": "fa-solid fa-repeat",
"description": "Options for robustness.",
"properties": {
"n_trials_robustness": {
"type": "integer",
"default": 0,
"description": "Number of trials to run for the robustness test",
"help_text": "Number of trials to run for the robustness test. Default is 0, which means no robustness test is run. The robustness test is a test where the model is trained with varying seeds. This is done multiple times to see how stable the model is."
}
}
},
"data_options": {
"title": "Data options",
"type": "object",
"fa_icon": "fa-solid fa-database",
"description": "Options for data input.",
"properties": {
"path_data": {
"type": "string",
"format": "directory-path",
"description": "Path to the data directory.",
"help_text": "Path to the data directory."
},
"cross_study_datasets": {
"type": "string",
"description": "Datasets for cross-study prediction.",
"help_text": "List of datasets to use to evaluate predictions across studies. Default is empty string which means no cross-study datasets are used."
}
}
},
"additional_options": {
"title": "Additional options",
"type": "object",
"fa_icon": "fas fa-cogs",
"description": "Additional options for the pipeline.",
"properties": {
"curve_curator": {
"type": "boolean",
"description": "Run the curve curator.",
"help_text": "Whether to run \" \"CurveCurator \" \"to sort out \" \"non-reactive \" \"curves"
},
"save_datasets": {
"type": "boolean",
"description": "If this is true, intermediate datasets are saved.",
"help_text": "This includes the pickled response/cross validation datasets, the pickled CV splits, the hyperparameter split yamls, the pickled predictions of each trained model, the best hyperparameters, and the randomization test view yamls. Consider this more of a debug flag."
},
"optim_metric": {
"type": "string",
"description": "Optimization metric for the pipeline.",
"default": "RMSE",
"help_text": "Optimization metric for the pipeline. Default is RMSE."
},
"n_cv_splits": {
"type": "integer",
"default": 10,
"description": "Number of cross-validation splits.",
"help_text": "Number of cross-validation splits. Default is 5."
},
"response_transformation": {
"type": "string",
"description": "Response transformation",
"help_text": "Transformation to apply to the response variable possible values: standard, minmax, robust"
},
"model_checkpoint_dir": {
"type": "string",
"description": "Model checkpoint directory",
"default": "TEMPORARY",
"help_text": "Directory to save model checkpoints."
}
}
},
"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})$",
"help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
"hidden": true
},
"plaintext_email": {
"type": "boolean",
"description": "Send plain-text email instead of HTML.",
"fa_icon": "fas fa-remove-format",
"hidden": true
},
"monochrome_logs": {
"type": "boolean",
"description": "Do not use coloured log outputs.",
"fa_icon": "fas fa-palette",
"hidden": true
},
"hook_url": {
"type": "string",
"description": "Incoming hook URL for messaging service",
"fa_icon": "fas fa-people-group",
"help_text": "Incoming hook URL for messaging service. Currently, MS Teams and Slack are supported.",
"hidden": true
},
"validate_params": {
"type": "boolean",
"description": "Boolean whether to validate parameters against the schema at runtime",
"default": true,
"fa_icon": "fas fa-check-square",
"hidden": true
},
"pipelines_testdata_base_path": {
"type": "string",
"fa_icon": "far fa-check-circle",
"description": "Base URL or local path to location of pipeline test dataset files",
"default": "https://raw.githubusercontent.com/nf-core/test-datasets/",
"hidden": true
},
"trace_report_suffix": {
"type": "string",
"fa_icon": "far calendar",
"description": "Suffix to add to the trace report filename. Default is the date and time in the format yyyy-MM-dd_HH-mm-ss.",
"hidden": true
}
}
}
},
"allOf": [
{
"$ref": "#/$defs/model_options"
},
{
"$ref": "#/$defs/input_output_options"
},
{
"$ref": "#/$defs/mode_options"
},
{
"$ref": "#/$defs/randomization_options"
},
{
"$ref": "#/$defs/data_options"
},
{
"$ref": "#/$defs/robustness_options"
},
{
"$ref": "#/$defs/additional_options"
},
{
"$ref": "#/$defs/institutional_config_options"
},
{
"$ref": "#/$defs/generic_options"
}
]
}