-
Notifications
You must be signed in to change notification settings - Fork 3
/
nextflow_schema.json
197 lines (197 loc) · 7.5 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
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/IGDRion/ANNEXA/master/nextflow_schema.json",
"title": "IGDRion/ANNEXA pipeline parameters",
"description": "An all-in-one pipeline to analyze LR-RNAseq data,reconstruct and quantify known and novel genes and isoforms.",
"type": "object",
"defs": {
"required": {
"title": "Required 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",
"pattern": "^\\S+\\.(csv|tsv|yaml|json)$",
"description": "Path to file listing paths to bam files.",
"fa_icon": "fas fa-file-csv"
},
"fa": {
"type": "string",
"format": "file-path",
"description": "Path to reference genome.",
"fa_icon": "fas fa-folder-open"
},
"gtf": {
"type": "string",
"format": "directory-path",
"description": "Path to reference annotation.",
"fa_icon": "fas fa-folder-open"
}
}
},
"profile_options": {
"title": "Profile options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Define how the pipeline should be executed.",
"properties": {
"profile test": {
"type": "string",
"description": "Run annexa on toy dataset.",
"fa_icon": "fas fa-file-csv"
},
"profile slurm": {
"type": "string",
"description": "Run annexa on slurm executor."
},
"profile singularity": {
"type": "string",
"description": "Run annexa in singularity container."
},
"profile conda": {
"type": "string",
"description": "Run annexa in conda environment."
},
"profile docker": {
"type": "string",
"description": "Run annexa in docker container."
}
}
},
"main_options": {
"title": "Main options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "General ANNEXA parameters.",
"properties": {
"tx_discovery": {
"type": "string",
"description": "Specify which transcriptome reconstruction tool to use.",
"default": "bambu",
"enum": ["bambu", "stringtie2"],
"fa_icon": "fas fa-file-csv"
},
"filter": {
"type": "boolean",
"description": "Perform or not the filtering step.",
"default": "true"
},
"withGeneCoverage": {
"type": "boolean",
"description": "Run RSeQC (can be long depending on annotation and bam sizes).",
"default": "false"
}
}
},
"bambu_options": {
"title": "Bambu options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Parameters related to Bambu.",
"properties": {
"bambu_strand": {
"type": "boolean",
"description": "Run bambu with stranded data",
"default": "true"
},
"bambu_singleexon": {
"type": "boolean",
"description": "Include single exon transcripts in Bambu output or not. These are known to have a high frequency of false positives.",
"default": "true"
},
"bambu_threshold": {
"type": "integer",
"description": "bambu NDR threshold below which new transcripts are retained.",
"default": "0.2"
}
}
},
"filtering_options": {
"title": "Filtering options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Parameters related to filtering step.",
"properties": {
"tfkmers_tokenizer": {
"type": "string",
"description": "Path to TransforKmers tokenizer. Required if filter option is activated."
},
"tfkmers_model": {
"type": "string",
"description": "Path to TransforKmers model. Required if filter activated."
},
"tfkmers_threshold": {
"type": "integer",
"description": "TransforKmers prediction threshold below which new transcripts are retained.",
"default": "0.2",
"minimum": "0",
"maximum": "1"
},
"operation": {
"type": "string",
"description": "Operation to retained novel transcripts. 'union' retain tx validated by either bambu or transforkmers, 'intersection' retain tx validated by both.",
"enum": ["union", "intersection"],
"default": "intersection"
}
}
},
"performance_options": {
"title": "Performance options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Parameters related to performance.",
"properties": {
"maxCpu": {
"type": "integer",
"description": "Max cpu threads used by ANNEXA.",
"default": "8"
},
"maxMemory": {
"type": "integer",
"description": "Max memory (in GB) used by ANNEXA.",
"default": "40"
}
}
},
"nextflow_options": {
"title": "Nextflow options",
"type": "object",
"fa_icon": "fas fa-terminal",
"description": "Parameters related to Nextflow.",
"properties": {
"resume": {
"description": "Resume task from cached work (useful for recovering from errors when using singularity)."
},
"with-report": {
"description": "Create an HTML execution report with metrics such as resource usage for each workflow process."
}
}
}
},
"allOf": [
{
"$ref": "#/defs/required_options"
},
{
"$ref": "#/defs/profile_options"
},
{
"$ref": "#/defs/main_options"
},
{
"$ref": "#/defs/bambu_options"
},
{
"$ref": "#/defs/filtering_options"
},
{
"$ref": "#/defs/performance_options"
},
{
"$ref": "#/defs/nextflow_options"
}
]
}