forked from nf-core/eager
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathschema_fasta.json
More file actions
174 lines (174 loc) · 8.66 KB
/
schema_fasta.json
File metadata and controls
174 lines (174 loc) · 8.66 KB
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
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/nf-core/eager/master/assets/schema_input.json",
"title": "nf-core/eager pipeline - params.input schema",
"description": "Schema for the file provided with params.input",
"type": "array",
"items": {
"type": "object",
"properties": {
"reference_name": {
"type": "string",
"pattern": "^\\S+$",
"meta": ["id"],
"errorMessage": "Reference name must be provided and cannot contain spaces."
},
"fasta": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.f(na|asta|a|as)(\\.gz)?$",
"exists": true,
"errorMessage": "Fasta files for the mapping reference must be provided with file extensions '.fasta', '.fa', '.fas', '.fna', '.fasta.gz','.fa.gz','.fas.gz', '.fna.gz' and cannot contain any spaces."
},
"fai": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.fai$",
"exists": true,
"errorMessage": "Fasta index files for the mapping reference cannot have any spaces and must have file extension '.fai'."
},
"dict": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.dict$",
"exists": true,
"errorMessage": "Picard sequence dictionary files for the mapping reference cannot have any spaces and must have file extensions '.dict'."
},
"mapper_index": {
"type": "string",
"format": "directory-path",
"pattern": "^\\S+$",
"exists": true,
"errorMessage": "The directories of the index files for the mapping reference for a given mapper must not contain any spaces and have file extensions ''."
},
"circular_target": {
"type": "string",
"pattern": "^\\S+$",
"errorMessage": "The headers of the chromosome extended by circulargenerator must not contain any spaces and no leading '>'."
},
"circularmapper_elongatedfasta": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.f(na|asta|a|as)(\\.gz)?$",
"exists": true,
"errorMessage": "The elongated Fasta files for the mapping reference must be provided with file extensions '.fasta', '.fa', '.fas', '.fna', '.fasta.gz','.fa.gz','.fas.gz', '.fna.gz' and cannot contain any spaces."
},
"circularmapper_elongatedindex": {
"type": "string",
"format": "directory-path",
"pattern": "^\\S+$",
"exists": true,
"errorMessage": "The directories of the index files for the elongated mapping reference for circularmapper must not contain any spaces and have file extensions ''."
},
"mitochondrion_header": {
"type": "string",
"pattern": "^\\S+$",
"errorMessage": "The names of the fasta entry of the mapping reference corresponding to the mitochondrial genome must not contain any spaces and no leading '>'."
},
"snpcapture_bed": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.bed(\\.gz)?$",
"exists": true,
"errorMessage": "SNP capture bed files must not contain any spaces and have file extensions '.bed' or '.bed.gz'."
},
"pileupcaller_bedfile": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.bed(\\.gz)?$",
"exists": true,
"errorMessage": "SNP capture bed files for pileupcaller must not contain any spaces, have file extensions '.bed' or '.bed.gz' and be provided alongside a pileupcall_bedfile."
},
"pileupcaller_snpfile": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.snp$",
"exists": true,
"errorMessage": "SNP panel files for pileupcaller must not contain any spaces, have file extension '.snp' and be provided alongside a pileupcaller_snpfile."
},
"hapmap_file": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+$",
"exists": true,
"errorMessage": "HapMap files for contamination estimation with ANGSD must not contain any spaces."
},
"pmdtools_masked_fasta": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.f(na|asta|a|as)(\\.gz)?$",
"exists": true,
"errorMessage": "Masked fasta files for PMDtools must not contain any spaces and have file extensions '.fasta', '.fa', '.fas', '.fna', '.fasta.gz','.fa.gz','.fas.gz' or '.fna.gz'."
},
"pmdtools_bed_for_masking": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.bed(\\.gz)?$",
"exists": true,
"errorMessage": "SNP capture bed files to mask the reference for PMDtools must not contain any spaces and have file extensions '.bed' or '.bed.gz'."
},
"sexdeterrmine_snp_bed": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.bed?(\\.gz)$",
"exists": true,
"errorMessage": "SNP capture bed files for SexDetERRmine must not contain any spaces and have file extensions '.bed' or '.bed.gz'."
},
"bedtools_feature_file": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.(bed|gff|gff3)(\\.gz)?$",
"exists": true,
"errorMessage": "Feature files must not contain any spaces and have file extensions '.bed', '.bed.gz', '.gff', '.gff.gz', '.gff3' or '.gff3.gz'."
},
"genotyping_reference_ploidy": {
"type": "integer",
"meta": ["genotyping_ploidy"],
"errorMessage": "Organism ploidy for GATK or FreeBayes must be provided as integers."
},
"genotyping_gatk_dbsnp": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.vcf$",
"exists": true,
"errorMessage": "SNP annotation files for GATK must not contain any spaces and have file extension '.vcf'."
},
"consensus_multivcfanalyzer_additional_vcf_files": {
"type": "string",
"format": "directory-path",
"pattern": "^\\S+\\.$",
"exists": true,
"errorMessage": "The directory containing the additional vcf files for multivcfanalyzer must not contain any spaces and have file extensions ''. Wildcards allowed."
},
"consensus_multivcfanalyzer_reference_gff_annotations": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.gff(\\.gz)?$",
"exists": true,
"errorMessage": "The annotation file must not contain any spaces and have file extension '.gff'."
},
"consensus_multivcfanalyzer_reference_gff_exclude": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.gff(\\.gz)?$",
"exists": true,
"errorMessage": "The annotation file must not contain any spaces and have file extension '.gff'."
},
"consensus_multivcfanalyzer_reference_snpeff_results": {
"type": "string",
"format": "file-path",
"pattern": "^\\S+\\.txt$",
"exists": true,
"errorMessage": "The snpeff file containing the results from the SnpEff analysis must not contain any spaces and have file extensions 'txt'."
}
},
"required": ["reference_name", "fasta"],
"dependentRequired": {
"pileupcaller_snpfile": ["pileupcaller_bedfile"],
"pileupcaller_bedfile": ["pileupcaller_snpfile"],
"bam": ["bam_reference_id"],
"bam_reference_id": ["bam"]
}
},
"uniqueEntries": ["reference_name", "fasta"]
}