-
Notifications
You must be signed in to change notification settings - Fork 9
/
nextflow_schema.json
195 lines (195 loc) · 7.19 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
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/IARCbioinfo/RNAseq-nf/master/nextflow_schema.json",
"title": "IARCbioinfo RNAseq-nf pipeline parameters",
"description": "Nextflow pipeline for RNA sequencing mapping, quality control, reads counting, and unsupervised analysis",
"type": "object",
"definitions": {
"input_output_params": {
"title": "Input_output_params",
"type": "object",
"description": "Input and output parameters",
"default": "",
"properties": {
"input_folder": {
"type": "string",
"description": "Folder containing BAM or fastq files to be aligned"
},
"input_file": {
"type": "string",
"description": "Input tabulation-separated values file with columns SM (sample name), RG (read group), pair1 (first fastq pair file), and pair2 (second fastq pair file)"
},
"fastq_ext": {
"type": "string",
"description": "Extension of fastq files",
"default": "fq.gz"
},
"suffix1": {
"type": "string",
"description": "Suffix of 1st fastq file (first element of read files pair)",
"default": "_1"
},
"suffix2": {
"type": "string",
"description": "Suffix of 2nd fastq file (second element of read files pair)",
"default": "_2"
},
"output_folder": {
"type": "string",
"description": "Output folder",
"default": "."
}
}
},
"computing_params": {
"title": "Computing_params",
"type": "object",
"description": "Computing parameters",
"default": "",
"properties": {
"cpu": {
"type": "integer",
"description": "Number of cpu used by bwa mem and sambamba",
"default": 4
},
"cpu_GATK": {
"type": "integer",
"default": 1,
"description": "Number of cpu used by GATK"
},
"cpu_trim": {
"type": "integer",
"default": 15,
"description": "Number of cpu used by cutadapt"
},
"mem": {
"type": "integer",
"default": 50,
"description": "Size of memory used for mapping (in GB)"
},
"mem_QC": {
"type": "integer",
"description": "Size of memory used for QC and cutadapt (in GB)",
"default": 2
}
}
},
"ref_params": {
"title": "Ref_params",
"type": "object",
"description": "Reference parameters",
"default": "",
"properties": {
"ref": {
"type": "string",
"description": "Reference fasta file (with index) for splice junction trimming and base recalibration",
"default": "ref.fa"
},
"ref_folder": {
"type": "string",
"description": "Folder with genome reference files (with index)"
},
"gtf": {
"type": "string",
"description": "Annotation GTF file"
},
"bed": {
"type": "string",
"description": "Bed file with genes for RESeQC (interval list)"
},
"snp_vcf": {
"type": "string",
"description": "Path to SNP VCF from GATK bundle",
"default": "dbsnp.vcf"
},
"indel_vcf": {
"type": "string",
"description": "Path to indel VCF from GATK bundle",
"default": "Mills_100G_indels.vcf"
}
},
"required": [
"ref_folder",
"gtf",
"bed"
]
},
"pipeline_params": {
"title": "Pipeline_params",
"type": "object",
"description": "Pipeline parameters",
"default": "",
"properties": {
"RG": {
"type": "string",
"description": "Samtools read group specification",
"default": "PL:ILLUMINA"
},
"cutadapt": {
"type": "boolean",
"description": "Perform adapter and quality reads trimming before alignment"
},
"stranded": {
"type": "string",
"description": "Strand information for counting with htseq [no, yes, reverse]",
"default": "no",
"enum": [
"no",
"yes",
"reverse"
]
},
"STAR_mapqUnique": {
"type": "integer",
"description": "STAR default mapping quality for unique mappers",
"default": 255
},
"htseq_maxreads": {
"type": "integer",
"description": "Maximum number of reads taken into account by htseq-count",
"default": 30000000
},
"hisat2": {
"type": "boolean",
"description": "Use hisat2 instead of STAR for mapping"
},
"hisat2_idx": {
"type": "string",
"description": "hisat2 index file prefix",
"default": "genome_tran"
},
"sjtrim": {
"type": "boolean",
"description": "Enable reads trimming at splice junctions"
},
"recalibration": {
"type": "boolean",
"description": "Perform base quality score recalibration (GATK)"
},
"multiqc_config": {
"type": "string",
"description": "Config yaml file for multiqc",
"default": "NO_FILE"
},
"help": {
"type": "boolean",
"description": "Display help"
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/input_output_params"
},
{
"$ref": "#/definitions/computing_params"
},
{
"$ref": "#/definitions/ref_params"
},
{
"$ref": "#/definitions/pipeline_params"
}
]
}