forked from ELIXIR-Belgium/ENA-metadata-templates
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathERC000049.json
1492 lines (1492 loc) · 66.3 KB
/
ERC000049.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
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
{
"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-T10x4RS",
"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 NovaSeq X Plus",
"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": "observed biotic relationship",
"cardinality": "optional",
"description": "Description of relationship(s) between the subject organism and other organism(s) it is associated with. E.g., parasite on species X; mutualist with species Y. The target organism is the subject of the relationship, and the other organism(s) is the object.",
"cv": [
"commensal",
"free living",
"mutualism",
"parasite",
"symbiont"
],
"units": "",
"field_type": "TEXT_CHOICE_FIELD",
"regex": ""
},
{
"name": "known pathogenicity",
"cardinality": "optional",
"description": "To what is the entity pathogenic, for instance plant, fungi, bacteria",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "sample collection device",
"cardinality": "optional",
"description": "The device used to collect an environmental sample. It is recommended to use terms listed under environmental sampling device (http://purl.obolibrary.org/obo/ENVO) and/or terms listed under specimen collection device (http://purl.obolibrary.org/obo/GENEPIO_0002094).",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"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": "metagenomic source",
"cardinality": "mandatory",
"description": "The metagenomic source of the sample. This value should contain \u201cmetagenome\u201d and be in the taxonomy database e.g. wastewater metagenome or human gut metagenome. Please note \u201cmetagenome\u201d alone will not be accepted. Check here for more details on metagenome taxonomy: https://ena-docs.readthedocs.io/en/latest/faq_taxonomy.html#environmental-taxonomic-classifications",
"cv": [],
"units": "",
"field_type": "TAXON_FIELD",
"regex": ""
},
{
"name": "sample derived from",
"cardinality": "mandatory",
"description": "Reference to parental sample(s) or original run(s) that the assembly is derived from. The referenced samples or runs should already be registered in INSDC. This should be formatted as one of the following. A single sample/run e.g. ERSxxxxxx OR a comma separated list e.g. ERSxxxxxx,ERSxxxxxx OR a range e.g. ERSxxxxxx-ERSxxxxxx",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": "(^[ESD]R[SR]\\d{6,}(,[ESD]R[SR]\\d{6,})*$)|(^SAM[END][AG]?\\d+(,SAM[END][AG]?\\d+)*$)|(^EGA[NR]\\d{11}(,EGA[NR]\\d{11})*$)|(^[ESD]R[SR]\\d{6,}-[ESD]R[SR]\\d{6,}$)|(^SAM[END][AG]?\\d+-SAM[END][AG]?\\d+$)|(^EGA[NR]\\d{11}-EGA[NR]\\d{11}$)"
},
{
"name": "project name",
"cardinality": "mandatory",
"description": "Name of the project within which the sequencing was organized",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "estimated size",
"cardinality": "optional",
"description": "The estimated size of the genome (in bp) prior to sequencing. Of particular importance in the sequencing of (eukaryotic) genome which could remain in draft form for a long or unspecified period. Mandatory for MIGS of eukaryotes.",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": "[+-]?[0-9]+"
},
{
"name": "multiplex identifiers",
"cardinality": "optional",
"description": "Molecular barcodes, called Multiplex Identifiers (MIDs), that are used to specifically tag unique samples in a sequencing run. Sequence should be reported in uppercase letters",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "relevant electronic resources",
"cardinality": "optional",
"description": "A related resource that is referenced, cited, or otherwise associated to the sequence in the format of a PMID, DOI or URL",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "relevant standard operating procedures",
"cardinality": "optional",
"description": "Standard operating procedures used in assembly and/or annotation of genomes, metagenomes or environmental sequences in the format of a PMID, DOI or URL",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "number of standard tRNAs extracted",
"cardinality": "optional",
"description": "The total number of tRNAs identified from the bin, SAG or MAG",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": "[+-]?[0-9]+"
},
{
"name": "feature prediction",
"cardinality": "optional",
"description": "Method used to predict UViGs features such as ORFs, integration site, etc. Add names and versions of software(s), parameters used",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "similarity search method",
"cardinality": "optional",
"description": "Tool used to compare ORFs with database, along with version and cutoffs used. Add names and versions of software(s), parameters used",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "tRNA extraction software",
"cardinality": "optional",
"description": "Tools used for tRNA identification. Add names and versions of software(s), parameters used",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "completeness score",
"cardinality": "optional",
"description": "Completeness score is typically based on either the fraction of markers found as compared to a database or the percent of a genome found as compared to a closely related reference genome. Completeness score is one of 3 attributes which in combination reflect the standard quality of a MAG, see here for more information: https://ena-docs.readthedocs.io/en/latest/faq_metagenomes.html. Mandatory for all samples directly linked with SAGs or MAGs.",
"cv": [],
"units": "%",
"field_type": "TEXT_FIELD",
"regex": "^(\\d|[1-9]\\d|\\d\\.\\d{1,2}|[1-9]\\d\\.\\d{1,2}|100)$"
},
{
"name": "completeness software",
"cardinality": "optional",
"description": "Tools used for completion estimate, i.e. checkm, anvi'o, busco. Mandatory for all samples directly linked with SAGs or MAGs.",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "completeness approach",
"cardinality": "optional",
"description": "The approach used to determine the completeness of a given bin, SAG or MAG, which would typically make use of a set of conserved marker genes or a closely related reference genome. For UViG completeness, include reference genome or group used, and contig feature suggesting a complete genome",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "binning software",
"cardinality": "optional",
"description": "Tool(s) used for the extraction of genomes from metagenomic datasets, where possible include a product ID (PID) of the tool(s) used. E.g. MetaCluster-TA (RRID:SCR_004599) or MaxBin (biotools:maxbin)",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "reassembly post binning",
"cardinality": "optional",
"description": "Has an assembly been performed on a genome bin extracted from a metagenomic assembly?",
"cv": [
"No",
"Yes"
],
"units": "Yes",
"field_type": "TEXT_CHOICE_FIELD",
"regex": ""
},
{
"name": "MAG coverage software",
"cardinality": "optional",
"description": "Tool(s) used to determine the genome coverage if coverage is used as a binning parameter in the extraction of genomes from metagenomic datasets e.g. bwa, bbmap, bowtie, other",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "binning parameters",
"cardinality": "optional",
"description": "The parameters that have been applied during the extraction of genomes from metagenomic datasets e.g. coverage and kmer",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "taxonomic identity marker",
"cardinality": "optional",
"description": "The phylogenetic marker(s) used to assign an organism name to the bin, SAG or MAG. Examples are 16S gene, multi-marker approach or other e.g. rpoB gene. Mandatory for all samples directly linked with SAGs or MAGs.",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "source of UViGs",
"cardinality": "mandatory",
"description": "Type of dataset from which the UViG was obtained",
"cv": [
"isolate microbial genome",
"metagenome (not viral targeted)",
"metatranscriptome (not viral targeted)",
"microbial single amplified genome (SAG)",
"other",
"sequence-targeted RNA metagenome",
"sequence-targeted metagenome",
"viral fraction RNA metagenome (RNA virome)",
"viral fraction metagenome (virome)",
"viral single amplified genome (vSAG)"
],
"units": "",
"field_type": "TEXT_CHOICE_FIELD",
"regex": ""
},
{
"name": "predicted genome type",
"cardinality": "mandatory",
"description": "Type of genome predicted for the UViG",
"cv": [
"DNA",
"RNA",
"dsDNA",
"dsRNA",
"mixed",
"ssDNA",
"ssRNA",
"ssRNA (+)",
"ssRNA (-)",
"uncharacterized"
],
"units": "",
"field_type": "TEXT_CHOICE_FIELD",
"regex": ""
},
{
"name": "predicted genome structure",
"cardinality": "mandatory",
"description": "Expected structure of the viral genome",
"cv": [
"non-segmented",
"segmented",
"undetermined"
],
"units": "",
"field_type": "TEXT_CHOICE_FIELD",
"regex": ""
},
{
"name": "detection type",
"cardinality": "mandatory",
"description": "Type of UViG detection",
"cv": [
"independent sequence (UViG)",
"provirus (UpViG)"
],
"units": "",
"field_type": "TEXT_CHOICE_FIELD",
"regex": ""
},
{
"name": "viral identification software",
"cardinality": "mandatory",
"description": "Tool(s) used for the identification of UViG as a viral genome, software or protocol name including version number, parameters, and cutoffs used formatted {software};{version};{parameters} e.g. VirSorter; 1.0.4; Virome database, category 2",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "OTU classification approach",
"cardinality": "optional",
"description": "Cutoffs and approach used when clustering \u201cspecies-level\u201d OTUs. Note that results from standard 95% ANI / 85% AF clustering should be provided alongside OTUS defined from another set of thresholds, even if the latter are the ones primarily used during the analysis. This should be formatted {ANI cutoff};{AF cutoff};{clustering method} e.g. 95% ANI;85% AF; greedy incremental clustering",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "OTU sequence comparison approach",
"cardinality": "optional",
"description": "Tool and thresholds used to compare sequences when computing \"species-level\" OTUs formatted: {software};{version};{parameters} e.g. gblastn;2.6.0+;e-value cutoff: 0.001",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "OTU database",
"cardinality": "optional",
"description": "Reference database (i.e. sequences not generated as part of the current study) used to cluster new genomes in \"species-level\" OTUs, if any. This should be formatted: {database};{version} e.g. NCBI Viral RefSeq;83",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "UViG assembly quality",
"cardinality": "mandatory",
"description": "UViG assembly quality is one of 3 attributes which in combination reflect the standard quality of a UViG, see here for more information: https://ena-docs.readthedocs.io/en/latest/faq_metagenomes.html.",
"cv": [
"One or multiple fragments, totaling \u2265 90% of the expected genome or replicon sequence or predicted complete",
"One or multiple fragments, totalling < 90% of the expected genome or replicon sequence, or for which no genome size could be estimated",
"Single, validated, contiguous sequence per replicon without gaps or ambiguities, with extensive manual review and editing to annotate putative gene functions and transcriptional units"
],
"units": "",
"field_type": "TEXT_CHOICE_FIELD",
"regex": ""
},
{
"name": "isolation_source",
"cardinality": "mandatory",
"description": "describes the physical, environmental and/or local geographical source of the biological sample from which the sample was derived",
"cv": [],
"units": "",
"field_type": "TEXT_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$)"
},
{
"name": "altitude",
"cardinality": "optional",
"description": "The altitude of the sample is the vertical distance between Earth's surface above Sea Level and the sampled position in the air.",
"cv": [],
"units": "m",
"field_type": "TEXT_FIELD",
"regex": "((0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^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$))"
},
{
"name": "geographic location (latitude)",
"cardinality": "mandatory",
"description": "The geographical origin of the sample as defined by latitude. The values should be reported in decimal degrees and in WGS84 system",
"cv": [],
"units": "DD",
"field_type": "TEXT_FIELD",
"regex": "(^[+-]?[0-9]+.?[0-9]{0,8}$)|(^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$)"
},
{
"name": "geographic location (longitude)",
"cardinality": "mandatory",
"description": "The geographical origin of the sample as defined by longitude. The values should be reported in decimal degrees and in WGS84 system",
"cv": [],
"units": "DD",
"field_type": "TEXT_FIELD",
"regex": "(^[+-]?[0-9]+.?[0-9]{0,8}$)|(^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": "geographic location (region and locality)",
"cardinality": "optional",
"description": "The geographical origin of the sample as defined by the specific region name followed by the locality name.",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "broad-scale environmental context",
"cardinality": "mandatory",
"description": "Report the major environmental system the sample or specimen came from. The system(s) identified should have a coarse spatial grain, to provide the general environmental context of where the sampling was done (e.g. in the desert or a rainforest). We recommend using subclasses of EnvO\u2019s biome class: http://purl.obolibrary.org/obo/ENVO_00000428. EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS.",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "local environmental context",
"cardinality": "mandatory",
"description": "Report the entity or entities which are in the sample or specimen\u2019s local vicinity and which you believe have significant causal influences on your sample or specimen. We recommend using EnvO terms which are of smaller spatial grain than your entry for \"broad-scale environmental context\". Terms, such as anatomical sites, from other OBO Library ontologies which interoperate with EnvO (e.g. UBERON) are accepted in this field. EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS.",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "environmental medium",
"cardinality": "mandatory",
"description": "Report the environmental material(s) immediately surrounding the sample or specimen at the time of sampling. We recommend using subclasses of 'environmental material' (http://purl.obolibrary.org/obo/ENVO_00010483). EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS . Terms from other OBO ontologies are permissible as long as they reference mass/volume nouns (e.g. air, water, blood) and not discrete, countable entities (e.g. a tree, a leaf, a table top).",
"cv": [],
"units": "",
"field_type": "TEXT_FIELD",
"regex": ""
},
{
"name": "elevation",
"cardinality": "optional",
"description": "The elevation of the sampling site as measured by the vertical distance from mean sea level.",
"cv": [],
"units": "m",
"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": "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": "size fraction selected",
"cardinality": "optional",
"description": "Filtering pore size used in sample preparation e.g. 0-0.22 micrometer",
"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",