forked from RSC-RP/cutandrun_nf
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathnextflow_schema.json
269 lines (269 loc) · 10.5 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
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/./master/nextflow_schema.json",
"title": "Cut&Run pipeline parameters",
"description": "",
"type": "object",
"definitions": {
"required_options": {
"title": "Required Options",
"type": "object",
"description": "",
"default": "",
"properties": {
"sample_sheet": {
"type": "string",
"default": "./test_data/test_dataset_sample_sheet.csv"
},
"queue": {
"type": "string",
"default": "paidq"
},
"project": {
"type": "string",
"default": "207f23bf-acb6-4835-8bfe-142436acb58c"
}
},
"required": [
"sample_sheet",
"queue",
"project"
]
},
"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",
"peaks_outdir"
],
"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"
},
"peaks_outdir": {
"type": "string",
"default": "./results/mouse/peaks_calls"
}
}
},
"reference_genome_options": {
"title": "Reference genome options",
"type": "object",
"fa_icon": "fas fa-dna",
"description": "Reference genome related files and options required for the workflow.",
"properties": {
"fasta": {
"type": "string",
"format": "file-path",
"exists": true,
"mimetype": "text/plain",
"pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$",
"description": "Path to target organism genome FASTA file.",
"help_text": "This parameter is *mandatory* if `--genome` is not specified. If you don't have a BWA index available this will be generated for you automatically. Combine with `--save_reference` to save BWA index for future runs.",
"fa_icon": "far fa-file-code"
},
"spike_fasta": {
"type": "string",
"default": "/gpfs/shared_data/Bowtie2/GCF_000005845.2_ASM584v2_genomic.fa",
"format": "file-path",
"description": "Path to spike-in organism genome FASTA file."
},
"build_index": {
"type": "boolean",
"description": "build new bowtie2 index from target organism FASTA."
},
"build_spike_index": {
"type": "boolean",
"description": "build new bowtie2 index from spike-in organism FASTA."
},
"index": {
"type": "string",
"default": "/gpfs/shared_data/Bowtie2/mm39_index/",
"description": "Path to pre-built bowtie2 index for target organism.",
"format": "directory-path"
},
"spike_index": {
"type": "string",
"default": "/gpfs/shared_data/Bowtie2/ecoli_index",
"description": "Path to pre-built bowtie2 index for spike-in organism.",
"format": "directory-path"
},
"chrom_sizes": {
"type": "string",
"default": "/gpfs/shared_data/Bowtie2/mm39.chrom.sizes",
"format": "file-path",
"description": "Path to target organism chromosome sizes text file."
}
},
"required": [
"fasta",
"spike_fasta",
"build_index",
"build_spike_index",
"index",
"spike_index",
"chrom_sizes"
]
},
"bowtie2_alignment_options": {
"title": "Bowtie2 Alignment options",
"type": "object",
"description": "",
"default": "",
"properties": {
"remove_dups": {
"type": "boolean",
"hidden": true,
"description": "Whether to remove duplicate reads from target aligned bam before peak calling."
},
"filter_bam": {
"type": "boolean",
"hidden": true,
"description": "Whether to filtered the target aligned bam file for mapq"
},
"mapq": {
"type": "integer",
"default": 30,
"hidden": true,
"description": "MAPQ value to retain"
},
"save_unaligned": {
"type": "boolean",
"hidden": true,
"description": "Output unaligned reads in a separate file."
}
}
},
"seacr_options": {
"title": "SEACR options",
"type": "object",
"description": "",
"default": "",
"properties": {
"scale_factor_constant": {
"type": "integer",
"default": 10000,
"hidden": true
},
"threshold": {
"type": "integer",
"default": 0,
"hidden": true
},
"spike_norm": {
"type": "boolean",
"hidden": true,
"description": "Whether to use spike-in aligned reads as normalization method."
}
}
},
"macs2_options": {
"title": "MACS2 options",
"type": "object",
"description": "",
"default": "",
"properties": {
"run_macs2": {
"type": "boolean",
"default": true,
"description": "Whether to run MACS2 peak calling.",
"hidden": true
},
"run_khmer": {
"type": "boolean",
"hidden": true,
"default": true,
"description": "Whether to calculate effective genome size from reads aligned to target genome."
},
"gsize": {
"type": "integer",
"default": 1870000000,
"hidden": true,
"description": "Effective genome size of target genome."
},
"kmer_size": {
"type": "integer",
"default": 50,
"hidden": true,
"description": "Read length for calculating effective size of target genome."
}
},
"required": [
"run_macs2",
"run_khmer"
]
},
"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": {
"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
},
"multiqc_config": {
"type": "string",
"format": "file-path",
"description": "Custom config file to supply to MultiQC.",
"fa_icon": "fas fa-cog",
"hidden": true
},
"extra_multiqc_config": {
"type": "string",
"hidden": true,
"description": "Custom config file to supply to MultiQC."
},
"multiqc_logo": {
"type": "string",
"description": "Custom logo file to supply to MultiQC. File name must also be set in the MultiQC config file",
"fa_icon": "fas fa-image",
"hidden": true
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/required_options"
},
{
"$ref": "#/definitions/input_output_options"
},
{
"$ref": "#/definitions/reference_genome_options"
},
{
"$ref": "#/definitions/bowtie2_alignment_options"
},
{
"$ref": "#/definitions/seacr_options"
},
{
"$ref": "#/definitions/macs2_options"
},
{
"$ref": "#/definitions/generic_options"
}
]
}