-
Notifications
You must be signed in to change notification settings - Fork 2
/
nextflow_schema.json
363 lines (363 loc) · 13.7 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
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
{
"$schema": "http:https://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/scpca-nf/master/nextflow_schema.json",
"title": "scpca-nf pipeline parameters",
"description": "A nextflow workflow for processing single-cell RNA-seq data as part of the ScPCA project.",
"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.",
"required": ["outdir", "run_metafile", "sample_metafile"],
"properties": {
"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",
"default": "scpca_out"
},
"run_metafile": {
"type": "string",
"default": "run_metadata.tsv",
"fa_icon": "fas fa-file-alt",
"format": "file-path",
"mimetype": "text/tab-separated-values",
"description": "The input file with information for each run to be processed. See https://github.com/AlexsLemonade/scpca-nf/blob/main/external-instructions.md#prepare-the-run-metadata-file for format information."
},
"sample_metafile": {
"type": "string",
"default": "sample_metadata.tsv",
"fa_icon": "fas fa-file-alt",
"format": "file-path",
"mimetype": "text/tab-separated-values",
"description": "A sample information file. See https://github.com/AlexsLemonade/scpca-nf/blob/main/external-instructions.md#prepare-the-sample-metadata-file for information."
},
"cellhash_pool_file": {
"type": "string",
"default": "multiplex_pools.tsv",
"fa_icon": "fas fa-file-alt",
"format": "file-path",
"mimetype": "text/tab-separated-values",
"description": "A file containing information to map cellhash barcodes to samples. See https://github.com/AlexsLemonade/scpca-nf/blob/main/external-instructions.md#multiplexed-cellhash-libraries for more information."
},
"results_dir": {
"type": "string",
"default": "scpca_out/results",
"hidden": true,
"fa_icon": "fas fa-folder-minus",
"format": "directory-path",
"description": "Directory for final output files."
},
"checkpoints_dir": {
"type": "string",
"default": "scpca_out/checkpoints",
"hidden": true,
"fa_icon": "fas fa-folder-minus",
"format": "directory-path",
"description": "Directory to store checkpoint files, used when optionally skipping steps."
}
}
},
"resource_maximums": {
"title": "Resource maximums",
"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": 24,
"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": "96 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'`"
}
}
},
"processing_options": {
"title": "Processing options",
"type": "object",
"description": "Define optional settings for processing.",
"default": "",
"properties": {
"run_ids": {
"type": "string",
"default": "All",
"description": "Specify a comma-separated list of run IDs to run. Use \"All\" to run all samples in the run_metafile."
},
"project": {
"type": "string",
"description": "Run samples only from a given project ID"
},
"repeat_mapping": {
"type": "boolean",
"description": "If alevin or salmon mapping has already been performed and output files exist, mapping is skipped by default."
},
"repeat_genetic_demux": {
"type": "boolean",
"description": "If genetic demultiplexing has been performed and output files exist, genetic demux is skipped by default."
},
"skip_genetic_demux": {
"type": "boolean",
"description": "Skip genetic demultiplexing steps, even if bulk data is present."
},
"perform_celltyping": {
"type": "boolean",
"description": "Specify whether or not to incorporate cell type annotations."
},
"repeat_celltyping": {
"type": "boolean",
"description": "If cell type annotations already exist, cell type classification with `SingleR` and `CellAssign` is skipped by default."
},
"publish_fry_outs": {
"type": "boolean",
"description": "alevin-fry outputs are not published by default. Use this option to publish them to the `checkpoints` folder."
},
"merge_run_ids": {
"type": "string",
"default": "All",
"description": "Which runs to merge when using the merge.nf workflow.",
"hidden": true
}
}
},
"reference_files": {
"title": "Reference files",
"type": "object",
"description": "",
"default": "",
"properties": {
"ref_rootdir": {
"type": "string",
"default": "s3:https://scpca-references",
"format": "directory-path",
"description": "Root location for reference files."
},
"barcode_dir": {
"type": "string",
"default": "s3:https://scpca-references/barcodes/10X",
"format": "directory-path",
"description": "Directory for 10x barcode files."
},
"ref_json": {
"type": "string",
"default": "${projectDir}/references/scpca-refs.json",
"format": "file-path",
"mimetype": "application/json",
"description": "JSON file describing the locations of reference files within the root directory."
},
"celltype_ref_dir": {
"type": "string",
"default": "s3:https://scpca-references/celltype",
"format": "directory-path",
"description": "Directory of cell type reference files."
},
"singler_models_dir": {
"type": "string",
"default": "s3:https://scpca-references/celltype/singler_models",
"format": "directory-path",
"description": "Directory of `SingleR` model files."
},
"cellassign_ref_dir": {
"type": "string",
"default": "s3:https://scpca-references/celltype/cellassign_references",
"format": "directory-path",
"description": "Directory of `CellAssign` reference data."
},
"ref_metadata": {
"type": "string",
"default": "${projectDir}/references/ref-metadata.tsv",
"format": "file-path",
"mimetype": "text/tab-separated-values",
"description": "Reference metadata used in `build-index.nf`.",
"hidden": true
},
"celltype_organism": {
"type": "string",
"default": "Homo_sapiens.GRCh38.104",
"description": "Organism for cell type references, used in `build-celltype-ref.nf`.",
"hidden": true
},
"singler_references_dir": {
"type": "string",
"default": "s3:https://scpca-references/celltype/singler_references",
"format": "directory-path",
"description": "Directory of `SingleR` reference files, used in `build-celltype-ref.nf`.",
"hidden": true
},
"celltype_ref_metadata": {
"type": "string",
"default": "${projectDir}/references/celltype-reference-metadata.tsv",
"format": "file-path",
"mimetype": "text/tab-separated-values",
"description": "Cell type reference metadata, used in `build-celltype-ref.nf`.",
"hidden": true
},
"panglao_marker_genes_file": {
"type": "string",
"default": "${projectDir}/references/PanglaoDB_markers_2020-03-27.tsv",
"format": "file-path",
"mimetype": "text/tab-separated-values",
"hidden": true,
"description": "Panglao marker genes file, used in `build-celltype-ref.nf`."
}
}
},
"algorithm_parameters": {
"title": "Algorithm parameters",
"type": "object",
"description": "",
"default": "",
"properties": {
"seed": {
"type": "integer",
"default": 2021,
"description": "Random number seed"
},
"af_resolution": {
"type": "string",
"default": "cr-like-em",
"description": "alevin-fry quant resolution method.",
"enum": ["cr-like-em", "cr-like", "full", "parsimony", "trivial"]
},
"spliced_only": {
"type": "boolean",
"description": "Only count spliced RNA reads."
},
"prob_compromised_cutoff": {
"type": "number",
"default": 0.75,
"description": "Cutoff for `miQC` to keep a cell."
},
"gene_cutoff": {
"type": "integer",
"default": 200,
"description": "Minimum number of genes detected per cell."
},
"num_hvg": {
"type": "integer",
"default": 2000,
"description": "Number of highly variable genes to use for dimension reduction."
},
"num_pcs": {
"type": "integer",
"default": 50,
"description": "Number of principal components to keep from PCA."
},
"cluster_algorithm": {
"type": "string",
"default": "louvain",
"enum": ["louvain", "leiden", "walktrap"],
"description": "Cluster algorithm to use."
},
"cluster_weighting": {
"type": "string",
"default": "jaccard",
"enum": ["rank", "number", "jaccard"],
"description": "Edge weighting to use for clustering."
},
"nearest_neighbors": {
"type": "integer",
"default": 20,
"description": "Number of neighbors to use for clustering."
},
"singler_label_name": {
"type": "string",
"default": "label.ont",
"hidden": true,
"description": "Label name for `SingleR` references, used in `build-celltype-ref.nf`."
}
}
},
"containers": {
"title": "Containers",
"type": "object",
"description": "Docker containers required for workflow steps.",
"default": "",
"fa_icon": "fas fa-box-open",
"properties": {
"SCPCATOOLS_CONTAINER": {
"type": "string",
"default": "ghcr.io/alexslemonade/scpca-tools:edge"
},
"ALEVINFRY_CONTAINER": {
"type": "string",
"default": "quay.io/biocontainers/alevin-fry:0.7.0--h9f5acd7_1"
},
"BCFTOOLS_CONTAINER": {
"type": "string",
"default": "quay.io/biocontainers/bcftools:1.14--h88f3f91_0"
},
"CELLSNP_CONTAINER": {
"type": "string",
"default": "quay.io/biocontainers/cellsnp-lite:1.2.2--h22771d5_0"
},
"CONDA_CONTAINER": {
"type": "string",
"default": "continuumio/miniconda3:4.10.3p0"
},
"FASTP_CONTAINER": {
"type": "string",
"default": "quay.io/biocontainers/fastp:0.23.0--h79da9fb_0"
},
"SALMON_CONTAINER": {
"type": "string",
"default": "quay.io/biocontainers/salmon:1.9.0--h7e5ed60_1"
},
"SAMTOOLS_CONTAINER": {
"type": "string",
"default": "quay.io/biocontainers/samtools:1.14--hb421002_0"
},
"STAR_CONTAINER": {
"type": "string",
"default": "quay.io/biocontainers/star:2.7.9a--h9ee0642_0"
},
"TIDYVERSE_CONTAINER": {
"type": "string",
"default": "rocker/tidyverse:4.3.1"
},
"VIREO_CONTAINER": {
"type": "string",
"default": "ghcr.io/alexslemonade/vireo-snp:v0.5.7"
},
"CELLRANGER_CONTAINER": {
"type": "string"
},
"SPACERANGER_CONTAINER": {
"type": "string"
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/input_output_options"
},
{
"$ref": "#/definitions/resource_maximums"
},
{
"$ref": "#/definitions/processing_options"
},
{
"$ref": "#/definitions/reference_files"
},
{
"$ref": "#/definitions/algorithm_parameters"
},
{
"$ref": "#/definitions/containers"
}
]
}