Skip to content

Commit 74bfb1b

Browse files
vdkkiavdkkia
authored
Merge pull request #28 from rabuono/dev
Update of ENA and ArrayExpress Templates
2 parents 58a23b3 + 0c381a9 commit 74bfb1b

19 files changed

+3003
-58
lines changed

‎Attribute type possibilities.txt‎

Lines changed: 23 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,23 @@
1+
String
2+
Date time
3+
Date
4+
Real number
5+
Integer
6+
Web link
7+
Email address
8+
Text
9+
ChEBI
10+
ECN
11+
MetaNEtX chemical
12+
MetaNEtX reaction
13+
MetaNEtX compartment
14+
InChi
15+
Boolean
16+
SEEK Strain
17+
SEEK Sample
18+
SEEK Sample Multi
19+
Controlled Vocabulary
20+
URI
21+
DOI
22+
NCBI ID
23+
SEEK Data file

templates/ena/all_organisms_v1.2.0.json renamed to Old versions/ENA single file study templates/all_organisms_v1.2.0.json

File renamed without changes.

templates/ena/plant_v1.2.0.json renamed to Old versions/ENA single file study templates/plant_v1.2.0.json

File renamed without changes.

‎templates/arrayexpress/library construction_v1.0.0.json‎

Lines changed: 140 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,140 @@
1+
{
2+
"meta": { "measurement": "genome sequencing", "technology": "nucleotide sequencing" },
3+
"data": {
4+
"library construction": [
5+
{
6+
"name": "protocol type",
7+
"description": "type of assay or experimental step performed.",
8+
"required": true,
9+
"ontology": null,
10+
"dataType": "string",
11+
"CVList": ["library construction"]
12+
},
13+
{
14+
"name": "library source",
15+
"description": "The LIBRARY_SOURCE specifies the type of source material that is being sequenced. (SRA 1.2 documentation)",
16+
"dataType": "List",
17+
"required": true,
18+
"ontology": null,
19+
"CVList": [
20+
"GENOMIC",
21+
"GENOMIC SINGLE CELL",
22+
"TRANSCRIPTOMIC",
23+
"TRANSCRIPTOMIC SINGLE CELL",
24+
"METAGENOMIC",
25+
"METATRANSCRIPTOMIC",
26+
"SYNTHETIC",
27+
"VIRAL RNA",
28+
"OTHER"
29+
]
30+
},
31+
{
32+
"name": "library strategy",
33+
"description": "Sequencing technique intended for this library (SRA 1.2 documentation)",
34+
"dataType": "List",
35+
"required": true,
36+
"ontology": null,
37+
"CVList": ["WGS",
38+
"WGA",
39+
"WXS",
40+
"RNA-Seq",
41+
"ssRNA-seq",
42+
"miRNA-Seq",
43+
"ncRNA-Seq",
44+
"FL-cDNA",
45+
"EST",
46+
"Hi-C",
47+
"ATAC-seq",
48+
"WCS",
49+
"RAD-Seq",
50+
"CLONE",
51+
"POOLCLONE",
52+
"AMPLICON",
53+
"CLONEEND",
54+
"FINISHING",
55+
"ChIP-Seq",
56+
"MNase-Seq",
57+
"DNase-Hypersensitivity",
58+
"Bisulfite-Seq",
59+
"CTS",
60+
"MRE-Seq",
61+
"MeDIP-Seq",
62+
"MBD-Seq",
63+
"Tn-Seq",
64+
"VALIDATION",
65+
"FAIRE-seq",
66+
"SELEX",
67+
"RIP-Seq",
68+
"ChIA-PET",
69+
"Synthetic-Long-Read",
70+
"Targeted-Capture",
71+
"OTHER"
72+
]
73+
},
74+
{
75+
"name": "library selection",
76+
"description": "Whether any method was used to select for or against, enrich, or screen the material being sequenced. (SRA 1.2 documentation)",
77+
"dataType": "List",
78+
"required": true,
79+
"ontology": null,
80+
"CVList": [
81+
"RANDOM",
82+
"PCR",
83+
"RANDOM PCR",
84+
"RT-PCR",
85+
"HMPR",
86+
"MF",
87+
"repeat fractionation",
88+
"size fractionation",
89+
"MSLL",
90+
"cDNA",
91+
"cDNA_randomPriming",
92+
"cDNA_oligo_dT",
93+
"PolyA",
94+
"Oligo-dT",
95+
"Inverse rRNA",
96+
"Inverse rRNA selection",
97+
"ChIP",
98+
"ChIP-Seq",
99+
"MNase",
100+
"DNase",
101+
"Hybrid Selection",
102+
"Reduced Representation",
103+
"Restriction Digest",
104+
"5-methylcytidine antibody",
105+
"MBD2 protein methyl-CpG binding domain",
106+
"CAGE",
107+
"RACE",
108+
"MDA",
109+
"padlock probes capture method",
110+
"other",
111+
"unspecified"
112+
]
113+
},
114+
{
115+
"name": "library layout",
116+
"description": "specifies whether to expect single, paired, or other configuration of reads.",
117+
"dataType": "List",
118+
"required": true,
119+
"ontology": null,
120+
"CVList": ["SINGLE", "PAIRED"]
121+
},
122+
{
123+
"name": "library strand",
124+
"description": "",
125+
"dataType": "List",
126+
"required": false,
127+
"ontology": null,
128+
"CVList": ["first strand", "second strand", "not applicable"]
129+
},
130+
{
131+
"name": "orientation",
132+
"description": "",
133+
"dataType": "List",
134+
"required": false,
135+
"ontology": null,
136+
"CVList": ["5'-3'-3'-5'", "5'-3'-5'-3'"]
137+
}
138+
]
139+
}
140+
}

‎templates/arrayexpress/library construction_v1.2.0.json‎

Lines changed: 10 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -6,10 +6,10 @@
66
"temporary_name": "4_arrayexpress_library_construction",
77
"template_version": "1.2.0",
88
"isa_config": "genome_seq_default_v2015-07-02",
9-
"isa_measurement_type": "genome sequencing",
9+
"isa_measurement_type": "transcription profiling",
1010
"isa_technology_type": "nucleotide sequencing",
1111
"isa_protocol_type": "library construction",
12-
"repo_schema_id": "ENA General experiment information 2021",
12+
"repo_schema_id": "General experiment information 2021",
1313
"organism": "any",
1414
"level": "assay"
1515
},
@@ -29,9 +29,11 @@
2929
"required": true,
3030
"isaTag": "protocol",
3131
"ontology": null,
32-
"CVList": [] //SOPtitle
32+
"dataType": "String", //need to be autofilled with name of selected SOP for that block
33+
"CVList": null //SOPtitle
3334
},
3435
{
36+
"iri": null,
3537
"name": "library source",
3638
"description": "The LIBRARY_SOURCE specifies the type of source material that is being sequenced. (SRA 1.2 documentation)",
3739
"dataType": "Controlled Vocabulary",
@@ -51,6 +53,7 @@
5153
]
5254
},
5355
{
56+
"iri": null,
5457
"name": "library strategy",
5558
"description": "Sequencing technique intended for this library (SRA 1.2 documentation)",
5659
"dataType": "Controlled Vocabulary",
@@ -96,6 +99,7 @@
9699
]
97100
},
98101
{
102+
"iri": null,
99103
"name": "library selection",
100104
"description": "Whether any method was used to select for or against, enrich, or screen the material being sequenced. (SRA 1.2 documentation)",
101105
"dataType": "Controlled Vocabulary",
@@ -137,6 +141,7 @@
137141
]
138142
},
139143
{
144+
"iri": null,
140145
"name": "library layout",
141146
"description": "specifies whether to expect single, paired, or other configuration of reads.",
142147
"dataType": "Controlled Vocabulary",
@@ -146,6 +151,7 @@
146151
"CVList": ["SINGLE", "PAIRED"]
147152
},
148153
{
154+
"iri": null,
149155
"name": "library strand",
150156
"description": "",
151157
"dataType": "Controlled Vocabulary",
@@ -171,7 +177,7 @@
171177
"required": true,
172178
"isaTag": "otherMaterial",
173179
"ontology": null,
174-
"CVList": []
180+
"CVList": null
175181
}
176182
]
177183
}

‎templates/arrayexpress/nucleic acid extraction_v1.0.0.json‎

Lines changed: 46 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,46 @@
1+
{
2+
"meta": { "measurement": "genome sequencing", "technology": "nucleotide sequencing" },
3+
"data": {
4+
"nucleic acid extraction": [
5+
{
6+
"name": "protocol type",
7+
"description": "type of assay or experimental step performed.",
8+
"required": true,
9+
"ontology": null,
10+
"dataType": "string",
11+
"CVList": ["nucleic acid extraction"]
12+
},
13+
{
14+
"name": "sample volume or weight for DNA extraction",
15+
"description": "Volume (mL) or weight (g) of sample processed for DNA extraction",
16+
"required": "false",
17+
"ontology": null,
18+
"dataType": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?",
19+
"unit": null //need to add unit options here
20+
},
21+
{
22+
"name": "Extract Name",
23+
"description": "User-defined names for each portion of extracted material.",
24+
"dataType": "String",
25+
"required": true,
26+
"ontology": null,
27+
"CVList": null
28+
},
29+
{
30+
"name": "Material type",
31+
"description": "This column contains terms describing the type of each material, for examples: whole organism, organism part, cell, total RNA.",
32+
"dataType": "List",
33+
"required": true,
34+
"ontology": null,
35+
"CVList": [
36+
"whole organism",
37+
"organism part",
38+
"RNA",
39+
"DNA",
40+
"cell"
41+
]
42+
}
43+
]
44+
45+
}
46+
}

‎templates/arrayexpress/nucleic acid extraction_v1.2.0.json‎

Lines changed: 13 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@
66
"temporary_name": "3_arrayexpress_nucleic_acid_extraction",
77
"template_version": "1.2.0",
88
"isa_config": "genome_seq_default_v2015-07-02",
9-
"isa_measurement_type": "genome sequencing",
9+
"isa_measurement_type": "transcription profiling",
1010
"isa_technology_type": "nucleotide sequencing",
1111
"isa_protocol_type": "nucleic acid extraction",
1212
"repo_schema_id": "NA",
@@ -33,6 +33,17 @@
3333
"CVList": [] //SOPtitle
3434
},
3535
{
36+
"iri": null,
37+
"name": "sample volume or weight for DNA extraction",
38+
"description": "Volume (mL) or weight (g) of sample processed for DNA extraction",
39+
"dataType": "String",
40+
"required": false,
41+
"isaTag": "parameter_value",
42+
"ontology": null,
43+
"unit": null
44+
},
45+
{
46+
"iri": null,
3647
"name": "Extract Name",
3748
"description": "User-defined names for each portion of extracted material.",
3849
"dataType": "String",
@@ -43,15 +54,7 @@
4354
"CVList": null
4455
},
4556
{
46-
"name": "sample volume or weight for DNA extraction",
47-
"description": "Volume (mL) or weight (g) of sample processed for DNA extraction",
48-
"dataType": "String",
49-
"required": false,
50-
"isaTag": "parameter_value",
51-
"ontology": null,
52-
"unit": null
53-
},
54-
{
57+
"iri": null,
5558
"name": "Material type",
5659
"description": "This column contains terms describing the type of each material, for examples: whole organism, organism part, cell, total RNA.",
5760
"dataType": "Controlled Vocabulary",

0 commit comments

Comments
 (0)