-
Notifications
You must be signed in to change notification settings - Fork 0
/
ENA_experiment_metadata_fields.json
403 lines (403 loc) · 15.3 KB
/
ENA_experiment_metadata_fields.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
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
{
"experiment": {
"description": "An experiment object serves as a metadata record encapsulating essential details about a sequencing experiment, including the experimental design, sequencing type, and relevant parameters. This information enhances the interpretation and contextual understanding of nucleotide sequences submitted to the archive.",
"fields": [
{
"name": "alias",
"cardinality": "mandatory",
"description": "Unique identificator for each experiment. This is used to link runs to experiments.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "title",
"cardinality": "mandatory",
"description": "Short text that can be used to call out experiment records in searches or in displays. This element is technically optional but should be used for all new records.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "study_alias",
"cardinality": "mandatory",
"description": "Accession number of the study (PRJEBxxxxxx), from the Studies report in Webin Portal.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "sample_alias",
"cardinality": "mandatory",
"description": "Accession number of the sample (SAMEAxxxxxx or ERSxxxxxx) that the sequencing where made on, from the Samples report in Webin Portal, or the sample_alias.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "design_description",
"cardinality": "mandatory",
"description": "Goal and setup of the individual library including library was constructed.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_AREA_FIELD"
},
{
"name": "library_name",
"cardinality": "optional",
"description": "The submitter's name for this library.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "library_strategy",
"cardinality": "mandatory",
"description": "Sequencing technique intended for this library.",
"units": "",
"regex": "",
"cv": [
"WGS",
"WGA",
"WXS",
"RNA-Seq",
"ssRNA-seq",
"snRNA-seq",
"miRNA-Seq",
"ncRNA-Seq",
"FL-cDNA",
"EST",
"Hi-C",
"ATAC-seq",
"WCS",
"RAD-Seq",
"CLONE",
"POOLCLONE",
"AMPLICON",
"CLONEEND",
"FINISHING",
"ChIP-Seq",
"MNase-Seq",
"DNase-Hypersensitivity",
"Bisulfite-Seq",
"CTS",
"MRE-Seq",
"MeDIP-Seq",
"MBD-Seq",
"Tn-Seq",
"VALIDATION",
"FAIRE-seq",
"SELEX",
"RIP-Seq",
"ChIA-PET",
"Synthetic-Long-Read",
"Targeted-Capture",
"Tethered Chromatin Conformation Capture",
"NOMe-Seq",
"ChM-Seq",
"GBS",
"Ribo-Seq",
"OTHER"
],
"field_type": "TEXT_CHOICE_FIELD"
},
{
"name": "library_source",
"cardinality": "mandatory",
"description": "The LIBRARY_SOURCE specifies the type of source material that is being sequenced.",
"units": "",
"regex": "",
"cv": [
"GENOMIC",
"GENOMIC SINGLE CELL",
"TRANSCRIPTOMIC",
"TRANSCRIPTOMIC SINGLE CELL",
"METAGENOMIC",
"METATRANSCRIPTOMIC",
"SYNTHETIC",
"VIRAL RNA",
"OTHER"
],
"field_type": "TEXT_CHOICE_FIELD"
},
{
"name": "library_selection",
"cardinality": "mandatory",
"description": "Method used to enrich the target in the sequence library preparation",
"units": "",
"regex": "",
"cv": [
"RANDOM",
"PCR",
"RANDOM PCR",
"RT-PCR",
"HMPR",
"MF",
"repeat fractionation",
"size fractionation",
"MSLL",
"cDNA",
"cDNA_randomPriming",
"cDNA_oligo_dT",
"PolyA",
"Oligo-dT",
"Inverse rRNA",
"Inverse rRNA selection",
"ChIP",
"ChIP-Seq",
"MNase",
"DNase",
"Hybrid Selection",
"Reduced Representation",
"Restriction Digest",
"5-methylcytidine antibody",
"MBD2 protein methyl-CpG binding domain",
"CAGE",
"RACE",
"MDA",
"padlock probes capture method",
"other",
"unspecified"
],
"field_type": "TEXT_CHOICE_FIELD"
},
{
"name": "library_layout",
"cardinality": "mandatory",
"description": "LIBRARY_LAYOUT specifies whether to expect single, paired, or other configuration of reads. In the case of paired reads, information about the relative distance and orientation is specified.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "insert_size",
"cardinality": "optional",
"description": "Insert size for paired reads",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "library_construction_protocol",
"cardinality": "optional",
"description": "Free form text describing the protocol by which the sequencing library was constructed.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "instrument_model",
"cardinality": "mandatory",
"description": "Model of the sequencing instrument.",
"units": "",
"regex": "",
"cv": [
"454 GS",
"454 GS 20",
"454 GS FLX",
"454 GS FLX Titanium",
"454 GS FLX+",
"454 GS Junior",
"AB 310 Genetic Analyzer",
"AB 3130 Genetic Analyzer",
"AB 3130xL Genetic Analyzer",
"AB 3500 Genetic Analyzer",
"AB 3500xL Genetic Analyzer",
"AB 3730 Genetic Analyzer",
"AB 3730xL Genetic Analyzer",
"AB 5500 Genetic Analyzer",
"AB 5500xl Genetic Analyzer",
"AB 5500xl-W Genetic Analysis System",
"AB SOLiD 3 Plus System",
"AB SOLiD 4 System",
"AB SOLiD 4hq System",
"AB SOLiD PI System",
"AB SOLiD System",
"AB SOLiD System 2.0",
"AB SOLiD System 3.0",
"BGISEQ-50",
"BGISEQ-500",
"Complete Genomics",
"DNBSEQ-G400",
"DNBSEQ-G400 FAST",
"DNBSEQ-G50",
"DNBSEQ-T7",
"Element AVITI",
"FASTASeq 300",
"GENIUS",
"GS111",
"Genapsys Sequencer",
"GenoCare 1600",
"GenoLab M",
"GridION",
"Helicos HeliScope",
"HiSeq X Five",
"HiSeq X Ten",
"Illumina Genome Analyzer",
"Illumina Genome Analyzer II",
"Illumina Genome Analyzer IIx",
"Illumina HiScanSQ",
"Illumina HiSeq 1000",
"Illumina HiSeq 1500",
"Illumina HiSeq 2000",
"Illumina HiSeq 2500",
"Illumina HiSeq 3000",
"Illumina HiSeq 4000",
"Illumina HiSeq X",
"Illumina MiSeq",
"Illumina MiniSeq",
"Illumina NovaSeq 6000",
"Illumina NovaSeq X",
"Illumina iSeq 100",
"Ion GeneStudio S5",
"Ion GeneStudio S5 Plus",
"Ion GeneStudio S5 Prime",
"Ion Torrent Genexus",
"Ion Torrent PGM",
"Ion Torrent Proton",
"Ion Torrent S5",
"Ion Torrent S5 XL",
"MGISEQ-2000RS",
"MinION",
"NextSeq 1000",
"NextSeq 2000",
"NextSeq 500",
"NextSeq 550",
"Onso",
"PacBio RS",
"PacBio RS II",
"PromethION",
"Revio",
"Sentosa SQ301",
"Sequel",
"Sequel II",
"Sequel IIe",
"Tapestri",
"UG 100",
"unspecified"
],
"field_type": "TEXT_CHOICE_FIELD"
}
]
},
"run": {
"description": "A run contains a group of reads generated for a particular experiment.",
"fields": [
{
"name": "alias",
"cardinality": "mandatory",
"description": "Unique identificator for each run.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "experiment_alias",
"cardinality": "mandatory",
"description": "From_experiment_metadata",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "file_type",
"cardinality": "mandatory",
"description": "The run data file model.",
"units": "",
"regex": "",
"cv": [
"sra",
"srf",
"sff",
"fastq",
"fasta",
"tab",
"454_native",
"454_native_seq",
"454_native_qual",
"Helicos_native",
"Illumina_native",
"Illumina_native_seq",
"Illumina_native_prb",
"Illumina_native_int",
"Illumina_native_qseq",
"Illumina_native_scarf",
"SOLiD_native",
"SOLiD_native_csfasta",
"SOLiD_native_qual",
"PacBio_HDF5",
"bam",
"cram",
"CompleteGenomics_native",
"OxfordNanopore_native"
],
"field_type": "TEXT_CHOICE_FIELD"
},
{
"name": "file_name",
"cardinality": "mandatory",
"description": "The name or relative pathname of a run data file.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "file_md5",
"cardinality": "mandatory",
"description": "The MD5 checksum of the file. This field is mandatory if you do not use the Webin File Uploader or upload the checksum using a .md5 file. The field is used for all file types except paired fastq files.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "forward_file_name",
"cardinality": "mandatory",
"description": "The name or relative pathname of a run data file. The field is used for paired fastq files.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "forward_file_md5",
"cardinality": "mandatory",
"description": "The MD5 checksum of the file. This field is mandatory if you do not use the Webin File Uploader or upload the checksum using a .md5 file. The field is used for paired fastq files.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "reverse_file_name",
"cardinality": "mandatory",
"description": "The name or relative pathname of a run data file. The field is used for paired fastq files.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "reverse_file_md5",
"cardinality": "mandatory",
"description": "The MD5 checksum of the file. This field is mandatory if you do not use the Webin File Uploader or upload the checksum using a .md5 file. The field is used for paired fastq files.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
}
]
}
}