forked from ELIXIR-Belgium/ENA-metadata-templates
-
Notifications
You must be signed in to change notification settings - Fork 0
/
ERC000043.json
962 lines (962 loc) · 39.1 KB
/
ERC000043.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
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
{
"study": {
"description": "A Study is a container for a sequencing investigation that may comprise multiple experiments. The Study has an overall goal, but is otherwise minimally defined in the SRA. A Study is composed of a descriptor, zero or more experiments, and zero or more analyses. The submitter may decorate the Study with web links and properties.",
"fields": [
{
"name": "alias",
"cardinality": "mandatory",
"description": "Unique identificator for a study. This is used to link experiments to the study.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "title",
"cardinality": "mandatory",
"description": "Title of the study as would be used in a publication.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "study_type",
"cardinality": "mandatory",
"description": "The STUDY_TYPE presents a controlled vocabulary for expressing the overall purpose of the study.",
"units": "",
"regex": "",
"cv": [
"Whole Genome Sequencing",
"Metagenomics",
"Transcriptome Analysis",
"Resequencing",
"Epigenetics",
"Synthetic Genomics",
"Forensic or Paleo-genomics",
"Gene Regulation Study",
"Cancer Genomics",
"Population Genomics",
"RNASeq",
"Exome Sequencing",
"Pooled Clone Sequencing",
"Transcriptome Sequencing",
"Other"
],
"field_type": "TEXT_CHOICE_FIELD"
},
{
"name": "new_study_type",
"cardinality": "optional",
"description": "Optional if 'study_type' is not 'other'. To propose a new term, select Other and enter a new study type.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "study_abstract",
"cardinality": "optional",
"description": "Briefly describes the goals, purpose, and scope of the Study. This need not be listed if it can be inherited from a referenced publication.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_AREA_FIELD"
}
]
},
"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": "Identifies the parent study. (From study metadata)",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "sample_alias",
"cardinality": "mandatory",
"description": "(From sample metadata)",
"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": "platform",
"cardinality": "mandatory",
"description": "The PLATFORM record selects which sequencing platform and platform-specific runtime parameters. This will be determined by the Center. optional if 'instrument_model' is provided.",
"units": "",
"regex": "",
"cv": [
"LS454",
"ILLUMINA",
"HELICOS",
"ABI_SOLID",
"COMPLETE_GENOMICS",
"BGISEQ",
"OXFORD_NANOPORE",
"PACBIO_SMRT",
"ION_TORRENT",
"CAPILLARY",
"DNBSEQ",
"ELEMENT",
"ULTIMA",
"VELA_DIAGNOSTICS",
"GENAPSYS",
"GENEMIND",
"TAPESTRI"
],
"field_type": "TEXT_CHOICE_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_name",
"cardinality": "mandatory",
"description": "The name or relative pathname of a run data file.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "file_format",
"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"
}
]
},
"sample": {
"description": "A Sample defines an isolate of sequenceable material upon which sequencing experiments can be based. The Sample object may be a surrogate for taxonomy accession or an anonymized individual identifier. Or, it may fully specify provenance and isolation method of the starting material.",
"fields": [
{
"name": "alias",
"cardinality": "mandatory",
"description": "Unique identificator for each sample.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "title",
"cardinality": "mandatory",
"description": "Short text that can be used to call out sample records in search results or in displays.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "taxon_id",
"cardinality": "mandatory",
"description": "NCBI Taxonomy Identifier. This is appropriate for individual organisms and some environmental samples.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_FIELD"
},
{
"name": "sample_description",
"cardinality": "optional",
"description": "Free-form text describing the sample, its origin, and its method of isolation.",
"units": "",
"regex": "",
"cv": [],
"field_type": "TEXT_AREA_FIELD"
},
{
"name": "sample collection method",
"cardinality": "optional",
"description": "The method employed for collecting the sample. Can be provided in the form of a PMID, DOI, url or text.",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "sample storage conditions",
"cardinality": "optional",
"description": "Conditions at which sample was stored, usually storage temperature, duration and location. In soil context: Explain how and for how long the soil sample was stored before DNA extraction (fresh/frozen/other).",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "sample storage temperature",
"cardinality": "optional",
"description": "temperature at which sample was stored, e.g. -80",
"cv": [],
"units": "\u00b0C",
"field_type": "TEXT_FIELD",
"regex": "[+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?"
},
{
"name": "collected_by",
"cardinality": "recommended",
"description": "name of persons or institute who collected the specimen",
"cv": [],
"units": "",
"field_type": "TEXT_AREA_FIELD",
"regex": ""
},
{
"name": "collection date",
"cardinality": "mandatory",
"description": "The date the sample was collected with the intention of sequencing, either as an instance (single point in time) or interval. In case no exact time is available, the date/time can be right truncated i.e. all of these are valid ISO8601 compliant times: 2008-01-23T19:23:10+00:00; 2008-01-23T19:23:10; 2008-01-23; 2008-01; 2008.",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": "(^[12][0-9]{3}(-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01])(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?([+-][0-9]{1,2})?)?)?)?(/[0-9]{4}(-[0-9]{2}(-[0-9]{2}(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?([+-][0-9]{1,2})?)?)?)?)?$)|(^not applicable$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)|(^missing$)"
},
{
"name": "geographic location (latitude)",
"cardinality": "recommended",
"description": "The geographical origin of the sample as defined by latitude. The values should be reported in decimal degrees and in WGS84 system",
"cv": [],
"units": "DD",
"field_type": "TEXT_FIELD",
"regex": "(^[+-]?[0-9]+.?[0-9]{0,8}$)|(^not applicable$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)|(^missing$)"
},
{
"name": "geographic location (longitude)",
"cardinality": "recommended",
"description": "The geographical origin of the sample as defined by longitude. The values should be reported in decimal degrees and in WGS84 system",
"cv": [],
"units": "DD",
"field_type": "TEXT_FIELD",
"regex": "(^[+-]?[0-9]+.?[0-9]{0,8}$)|(^not applicable$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)|(^missing$)"
},
{
"name": "amount or size of sample collected",
"cardinality": "optional",
"description": "The total amount or size (volume (ml), mass (g) or area (m2) ) of sample collected.",
"cv": [],
"units": "m3",
"field_type": "TEXT_FIELD",
"regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?"
},
{
"name": "water temperature",
"cardinality": "optional",
"description": "Temperature of water at the time of taking the sample. Format: ##.####, SDN:P02:75:TEMP, SDN:P06:46:UPAA for \u00b0C. Example: 17.7122.",
"cv": [],
"units": "\u00baC",
"field_type": "TEXT_FIELD",
"regex": "[+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?"
},
{
"name": "sample storage duration",
"cardinality": "optional",
"description": "Duration for which the sample was stored. Indicate the duration for which the sample was stored written in ISO 8601 format.",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "geographic location (country and/or sea)",
"cardinality": "mandatory",
"description": "The geographical origin of where the sample was collected from, with the intention of sequencing, as defined by the country or sea name. Country or sea names should be chosen from the INSDC country list (http://insdc.org/country.html).",
"cv": [
"Afghanistan",
"Albania",
"Algeria",
"American Samoa",
"Andorra",
"Angola",
"Anguilla",
"Antarctica",
"Antigua and Barbuda",
"Arctic Ocean",
"Argentina",
"Armenia",
"Aruba",
"Ashmore and Cartier Islands",
"Atlantic Ocean",
"Australia",
"Austria",
"Azerbaijan",
"Bahamas",
"Bahrain",
"Baker Island",
"Baltic Sea",
"Bangladesh",
"Barbados",
"Bassas da India",
"Belarus",
"Belgium",
"Belize",
"Benin",
"Bermuda",
"Bhutan",
"Bolivia",
"Borneo",
"Bosnia and Herzegovina",
"Botswana",
"Bouvet Island",
"Brazil",
"British Virgin Islands",
"Brunei",
"Bulgaria",
"Burkina Faso",
"Burundi",
"Cambodia",
"Cameroon",
"Canada",
"Cape Verde",
"Cayman Islands",
"Central African Republic",
"Chad",
"Chile",
"China",
"Christmas Island",
"Clipperton Island",
"Cocos Islands",
"Colombia",
"Comoros",
"Cook Islands",
"Coral Sea Islands",
"Costa Rica",
"Cote d'Ivoire",
"Croatia",
"Cuba",
"Curacao",
"Cyprus",
"Czechia",
"Czech Republic",
"Democratic Republic of the Congo",
"Denmark",
"Djibouti",
"Dominica",
"Dominican Republic",
"East Timor",
"Ecuador",
"Egypt",
"El Salvador",
"Equatorial Guinea",
"Eritrea",
"Estonia",
"Ethiopia",
"Europa Island",
"Falkland Islands (Islas Malvinas)",
"Faroe Islands",
"Fiji",
"Finland",
"France",
"French Guiana",
"French Polynesia",
"French Southern and Antarctic Lands",
"Gabon",
"Gambia",
"Gaza Strip",
"Georgia",
"Germany",
"Ghana",
"Gibraltar",
"Glorioso Islands",
"Greece",
"Greenland",
"Grenada",
"Guadeloupe",
"Guam",
"Guatemala",
"Guernsey",
"Guinea",
"Guinea-Bissau",
"Guyana",
"Haiti",
"Heard Island and McDonald Islands",
"Honduras",
"Hong Kong",
"Howland Island",
"Hungary",
"Iceland",
"India",
"Indian Ocean",
"Indonesia",
"Iran",
"Iraq",
"Ireland",
"Isle of Man",
"Israel",
"Italy",
"Jamaica",
"Jan Mayen",
"Japan",
"Jarvis Island",
"Jersey",
"Johnston Atoll",
"Jordan",
"Juan de Nova Island",
"Kazakhstan",
"Kenya",
"Kerguelen Archipelago",
"Kingman Reef",
"Kiribati",
"Kosovo",
"Kuwait",
"Kyrgyzstan",
"Laos",
"Latvia",
"Lebanon",
"Lesotho",
"Liberia",
"Libya",
"Liechtenstein",
"Lithuania",
"Luxembourg",
"Macau",
"Macedonia",
"Madagascar",
"Malawi",
"Malaysia",
"Maldives",
"Mali",
"Malta",
"Marshall Islands",
"Martinique",
"Mauritania",
"Mauritius",
"Mayotte",
"Mediterranean Sea",
"Mexico",
"Micronesia",
"Midway Islands",
"Moldova",
"Monaco",
"Mongolia",
"Montenegro",
"Montserrat",
"Morocco",
"Mozambique",
"Myanmar",
"Namibia",
"Nauru",
"Navassa Island",
"Nepal",
"Netherlands",
"New Caledonia",
"New Zealand",
"Nicaragua",
"Niger",
"Nigeria",
"Niue",
"Norfolk Island",
"North Korea",
"North Sea",
"Northern Mariana Islands",
"Norway",
"Oman",
"Pacific Ocean",
"Pakistan",
"Palau",
"Palmyra Atoll",
"Panama",
"Papua New Guinea",
"Paracel Islands",
"Paraguay",
"Peru",
"Philippines",
"Pitcairn Islands",
"Poland",
"Portugal",
"Puerto Rico",
"Qatar",
"Republic of the Congo",
"Reunion",
"Romania",
"Ross Sea",
"Russia",
"Rwanda",
"Saint Helena",
"Saint Kitts and Nevis",
"Saint Lucia",
"Saint Pierre and Miquelon",
"Saint Vincent and the Grenadines",
"Samoa",
"San Marino",
"Sao Tome and Principe",
"Saudi Arabia",
"Senegal",
"Serbia",
"Seychelles",
"Sierra Leone",
"Singapore",
"Sint Maarten",
"Slovakia",
"Slovenia",
"Solomon Islands",
"Somalia",
"South Africa",
"South Georgia and the South Sandwich Islands",
"South Korea",
"Southern Ocean",
"Spain",
"Spratly Islands",
"Sri Lanka",
"Sudan",
"Suriname",
"Svalbard",
"Swaziland",
"Sweden",
"Switzerland",
"Syria",
"Taiwan",
"Tajikistan",
"Tanzania",
"Tasman Sea",
"Thailand",
"Togo",
"Tokelau",
"Tonga",
"Trinidad and Tobago",
"Tromelin Island",
"Tunisia",
"Turkey",
"Turkmenistan",
"Turks and Caicos Islands",
"Tuvalu",
"USA",
"Uganda",
"Ukraine",
"United Arab Emirates",
"United Kingdom",
"Uruguay",
"Uzbekistan",
"Vanuatu",
"Venezuela",
"Viet Nam",
"Virgin Islands",
"Wake Island",
"Wallis and Futuna",
"West Bank",
"Western Sahara",
"Yemen",
"Zambia",
"Zimbabwe",
"missing",
"missing: control sample",
"missing: data agreement established pre-2023",
"missing: endangered species",
"missing: human-identifiable",
"missing: lab stock",
"missing: sample group",
"missing: synthetic construct",
"missing: third party data",
"not applicable",
"not collected",
"not provided",
"restricted access"
],
"units": "",
"field_type": "TEXT_CHOICE_FIELD",
"regex": ""
},
{
"name": "light intensity",
"cardinality": "optional",
"description": "measurement of light intensity",
"cv": [],
"units": "lux",
"field_type": "TEXT_FIELD",
"regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?"
},
{
"name": "pH",
"cardinality": "optional",
"description": "pH measurement",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?"
},
{
"name": "salinity",
"cardinality": "optional",
"description": "The total concentration of all dissolved salts in a liquid or solid sample. While salinity can be measured by a complete chemical analysis, this method is difficult and time consuming. More often, it is instead derived from the conductivity measurement. This is known as practical salinity. These derivations compare the specific conductance of the sample to a salinity standard such as seawater.",
"cv": [],
"units": "psu",
"field_type": "TEXT_FIELD",
"regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?"
},
{
"name": "culture_collection",
"cardinality": "optional",
"description": "Unique identifier that references the culture (e.g. live microbial and viral cultures and cell lines) from which the sample has been obtained and that have been deposited in curated culture collections. The ID needs to provide an institution code and the culture id, with optional collection code, in the following structure: (-institution_code:(collection_code):voucher_id. Please note institution codes (and optional collection codes) are taken from a controlled vocabulary maintained by the INSDC: https://ftp.ncbi.nih.gov/pub/taxonomy/biocollections/",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "strain",
"cardinality": "mandatory",
"description": "Name of the strain from which the sample was obtained.",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "Further Details",
"cardinality": "optional",
"description": "Reference details related to a sample in form of an URI.",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "isolation and growth condition",
"cardinality": "optional",
"description": "Publication reference in the form of pubmed ID (pmid), digital object identifier (doi) or url for isolation and growth condition specifications of the organism/material. Mandatory for MIGS and MIMARKS Specimen.",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "depth",
"cardinality": "recommended",
"description": "The vertical distance below local surface, e.g. for sediment or soil samples depth is measured from sediment or soil surface, respectively. Depth can be reported as an interval for subsurface samples.",
"cv": [],
"units": "mm",
"field_type": "TEXT_FIELD",
"regex": "((0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)|(^missing$))"
},
{
"name": "growth condition",
"cardinality": "optional",
"description": "A role that a material entity can play which enables particular conditions used to grow organisms or parts of the organism. This includes isolated environments such as cultures and open environments such as field studies.",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
}
]
}
}