-
Notifications
You must be signed in to change notification settings - Fork 8
Expand file tree
/
Copy pathSRA.experiment.xsd.xml
More file actions
799 lines (777 loc) · 37.2 KB
/
Copy pathSRA.experiment.xsd.xml
File metadata and controls
799 lines (777 loc) · 37.2 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
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
<?xml version="1.0" encoding="UTF-8"?>
<!--
~ Copyright 2018 EMBL - European Bioinformatics Institute
~ Licensed under the Apache License, Version 2.0 (the "License"); you may not use this
~ file except in compliance with the License. You may obtain a copy of the License at
~ http://www.apache.org/licenses/LICENSE-2.0
~ Unless required by applicable law or agreed to in writing, software distributed under the
~ License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
~ CONDITIONS OF ANY KIND, either express or implied. See the License for the
~ specific language governing permissions and limitations under the License.
-->
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:com="SRA.common">
<xs:import schemaLocation="SRA.common.xsd" namespace="SRA.common"/>
<!-- STRING ENUMERATIONS BEGIN -->
<xs:simpleType name="typeLibraryStrategy">
<xs:annotation>
<xs:documentation>Sequencing technique intended for this library.</xs:documentation>
</xs:annotation>
<xs:restriction base="xs:string">
<xs:enumeration value="WGS">
<xs:annotation>
<xs:documentation>Whole Genome Sequencing - random sequencing of the whole genome (see pubmed 10731132 for details)
</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="WGA">
<xs:annotation>
<xs:documentation>Whole Genome Amplification followed by random sequencing. (see pubmed 1631067,8962113 for details)
</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="WXS">
<xs:annotation>
<xs:documentation> Random sequencing of exonic regions selected from the genome. (see pubmed 20111037 for details)
</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="RNA-Seq">
<xs:annotation>
<xs:documentation> Random sequencing of whole transcriptome, also known as Whole Transcriptome Shotgun Sequencing, or WTSS). (see
pubmed 18611170 for details) </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="ssRNA-seq">
<xs:annotation>
<xs:documentation> Strand-specific RNA sequencing.
</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="snRNA-seq">
<xs:annotation>
<xs:documentation>Single nucleus RNA sequencing is a method for profiling gene expression in cells which are difficult to isolate.</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="miRNA-Seq">
<xs:annotation>
<xs:documentation> Micro RNA sequencing strategy designed to capture post-transcriptional RNA elements and include non-coding
functional elements. (see pubmed 21787409 for details) </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="ncRNA-Seq">
<xs:annotation>
<xs:documentation>Capture of other non-coding RNA types, including post-translation modification types such as snRNA (small
nuclear RNA) or snoRNA (small nucleolar RNA), or expression regulation types such as siRNA (small interfering RNA) or
piRNA/piwi/RNA (piwi-interacting RNA).</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="FL-cDNA">
<xs:annotation>
<xs:documentation> Full-length sequencing of cDNA templates </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="EST">
<xs:annotation>
<xs:documentation> Single pass sequencing of cDNA templates </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="Hi-C">
<xs:annotation>
<xs:documentation> Chromosome Conformation Capture technique where a biotin-labeled nucleotide is incorporated at the ligation junction, enabling selective purification of chimeric DNA ligation junctions followed by deep sequencing. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="ATAC-seq">
<xs:annotation>
<xs:documentation> Assay for Transposase-Accessible Chromatin (ATAC) strategy is used to study genome-wide chromatin accessibility. alternative method to DNase-seq that uses an engineered Tn5 transposase to cleave DNA and to integrate primer DNA sequences into the cleaved genomic DNA. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="WCS">
<xs:annotation>
<xs:documentation> Random sequencing of a whole chromosome or other replicon isolated from a genome. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="RAD-Seq"/>
<xs:enumeration value="CLONE">
<xs:annotation>
<xs:documentation> Genomic clone based (hierarchical) sequencing. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="POOLCLONE">
<xs:annotation>
<xs:documentation> Shotgun of pooled clones (usually BACs and Fosmids). </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="AMPLICON">
<xs:annotation>
<xs:documentation> Sequencing of overlapping or distinct PCR or RT-PCR products. For example, metagenomic community profiling
using SSU rRNA . </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="CLONEEND">
<xs:annotation>
<xs:documentation> Clone end (5', 3', or both) sequencing. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="FINISHING">
<xs:annotation>
<xs:documentation> Sequencing intended to finish (close) gaps in existing coverage. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="ChIP-Seq">
<xs:annotation>
<xs:documentation> ChIP-seq, Chromatin ImmunoPrecipitation, reveals binding sites of specific proteins, typically transcription factors (TFs) using antibodies to extract DNA fragments bound to the target protein. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="MNase-Seq">
<xs:annotation>
<xs:documentation> Identifies well-positioned nucleosomes. uses Micrococcal Nuclease (MNase) is an endo-exonuclease that processively digests DNA until an obstruction, such as a nucleosome, is reached. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="DNase-Hypersensitivity">
<xs:annotation>
<xs:documentation> Sequencing of hypersensitive sites, or segments of open chromatin that are more readily cleaved by DNaseI.
</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="Bisulfite-Seq">
<xs:annotation>
<xs:documentation>MethylC-seq. Sequencing following treatment of DNA with bisulfite to convert cytosine residues to uracil
depending on methylation status. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="CTS">
<xs:annotation>
<xs:documentation> Concatenated Tag Sequencing </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="MRE-Seq">
<xs:annotation>
<xs:documentation> Methylation-Sensitive Restriction Enzyme Sequencing. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="MeDIP-Seq">
<xs:annotation>
<xs:documentation> Methylated DNA Immunoprecipitation Sequencing. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="MBD-Seq">
<xs:annotation>
<xs:documentation> Methyl CpG Binding Domain Sequencing. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="Tn-Seq">
<xs:annotation>
<xs:documentation>Quantitatively determine fitness of bacterial genes based on how many times a purposely seeded transposon gets
inserted into each gene of a colony after some time. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="VALIDATION">
<xs:annotation>
<xs:documentation>CGHub special request: Independent experiment to re-evaluate putative variants. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="FAIRE-seq">
<xs:annotation>
<xs:documentation>Formaldehyde Assisted Isolation of Regulatory Elements. Reveals regions of open chromatin. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="SELEX">
<xs:annotation>
<xs:documentation>Systematic Evolution of Ligands by Exponential enrichment</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="RIP-Seq">
<xs:annotation>
<xs:documentation>Direct sequencing of RNA immunoprecipitates (includes CLIP-Seq, HITS-CLIP and PAR-CLIP). </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="ChIA-PET">
<xs:annotation>
<xs:documentation>Direct sequencing of proximity-ligated chromatin immunoprecipitates.</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="Synthetic-Long-Read">
<xs:annotation>
<xs:documentation>binning and barcoding of large DNA fragments to facilitate assembly of the fragment</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="Targeted-Capture">
<xs:annotation>
<xs:documentation>Enrichment of a targeted subset of loci.</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="Tethered Chromatin Conformation Capture"/>
<xs:enumeration value="NOMe-Seq">
<xs:annotation>
<xs:documentation>Nucleosome Occupancy and Methylome sequencing.</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="ChM-Seq">
<xs:annotation>
<xs:documentation>ChIPmentation combines chromatin immunoprecipitation with sequencing library preparation by Tn5 transposase (see pubmed 26280331 for details)</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="GBS">
<xs:annotation>
<xs:documentation>Genotyping by sequencing is a method to discover single nucleotide polymorphisms for genotyping studies.</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="Ribo-Seq">
<xs:annotation>
<xs:documentation>Ribosome profiling (also named ribosome footprinting) that uses specialized messenger RNA (mRNA) sequencing to determine which mRNAs are being actively translated. It produces a "global snapshot" of all the ribosomes active in a cell at a particular moment, known as a translatome.</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="OTHER">
<xs:annotation>
<xs:documentation> Library strategy not listed. </xs:documentation>
</xs:annotation>
</xs:enumeration>
</xs:restriction>
</xs:simpleType>
<xs:simpleType name="typeLibrarySource">
<xs:annotation>
<xs:documentation> The LIBRARY_SOURCE specifies the type of source material that is being sequenced. </xs:documentation>
</xs:annotation>
<xs:restriction base="xs:string">
<xs:enumeration value="GENOMIC">
<xs:annotation>
<xs:documentation> Genomic DNA (includes PCR products from genomic DNA). </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="GENOMIC SINGLE CELL"/>
<xs:enumeration value="TRANSCRIPTOMIC">
<xs:annotation>
<xs:documentation> Transcription products or non genomic DNA (EST, cDNA, RT-PCR, screened libraries). </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="TRANSCRIPTOMIC SINGLE CELL"/>
<xs:enumeration value="METAGENOMIC">
<xs:annotation>
<xs:documentation> Mixed material from metagenome. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="METATRANSCRIPTOMIC">
<xs:annotation>
<xs:documentation> Transcription products from community targets </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="SYNTHETIC">
<xs:annotation>
<xs:documentation> Synthetic DNA. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="VIRAL RNA">
<xs:annotation>
<xs:documentation> Viral RNA. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="OTHER">
<xs:annotation>
<xs:documentation> Other, unspecified, or unknown library source material. </xs:documentation>
</xs:annotation>
</xs:enumeration>
</xs:restriction>
</xs:simpleType>
<xs:simpleType name="typeLibrarySelection">
<xs:annotation>
<xs:documentation> Method used to enrich the target in the sequence library preparation </xs:documentation>
</xs:annotation>
<xs:restriction base="xs:string">
<xs:enumeration value="RANDOM">
<xs:annotation>
<xs:documentation>No Selection or Random selection</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="PCR">
<xs:annotation>
<xs:documentation>target enrichment via PCR</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="RANDOM PCR">
<xs:annotation>
<xs:documentation>Source material was selected by randomly generated primers.</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="RT-PCR">
<xs:annotation>
<xs:documentation>target enrichment via </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="HMPR">
<xs:annotation>
<xs:documentation>Hypo-methylated partial restriction digest</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="MF">
<xs:annotation>
<xs:documentation>Methyl Filtrated</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="repeat fractionation">
<xs:annotation>
<xs:documentation>Selection for less repetitive (and more gene rich) sequence through Cot filtration (CF) or other fractionation
techniques based on DNA kinetics. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="size fractionation">
<xs:annotation>
<xs:documentation> Physical selection of size appropriate targets. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="MSLL">
<xs:annotation>
<xs:documentation>Methylation Spanning Linking Library</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="cDNA">
<xs:annotation>
<xs:documentation>PolyA selection or enrichment for messenger RNA (mRNA); synonymize with PolyA </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="cDNA_randomPriming"/>
<xs:enumeration value="cDNA_oligo_dT"/>
<xs:enumeration value="PolyA">
<xs:annotation>
<xs:documentation>PolyA selection or enrichment for messenger RNA (mRNA); should replace cDNA enumeration. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="Oligo-dT">
<xs:annotation>
<xs:documentation>enrichment of messenger RNA (mRNA) by hybridization to Oligo-dT. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="Inverse rRNA">
<xs:annotation>
<xs:documentation>depletion of ribosomal RNA by oligo hybridization. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="Inverse rRNA selection">
<xs:annotation>
<xs:documentation>depletion of ribosomal RNA by inverse oligo hybridization. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="ChIP">
<xs:annotation>
<xs:documentation>Chromatin immunoprecipitation</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="ChIP-Seq">
<xs:annotation>
<xs:documentation>Chromatin immunoPrecipitation, reveals binding sites of specific proteins, typically transcription factors (TFs) using antibodies to extract DNA fragments bound to the target protein.</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="MNase">
<xs:annotation>
<xs:documentation>Identifies well-positioned nucleosomes. uses Micrococcal Nuclease (MNase) is an endo-exonuclease that processively digests DNA until an obstruction, such as a nucleosome, is reached.</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="DNase">
<xs:annotation>
<xs:documentation>DNase I endonuclease digestion and size selection reveals regions of chromatin where the DNA is highly sensitive to DNase I.</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="Hybrid Selection">
<xs:annotation>
<xs:documentation>Selection by hybridization in array or solution.</xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="Reduced Representation">
<xs:annotation>
<xs:documentation>Reproducible genomic subsets, often generated by restriction fragment size selection, containing a manageable
number of loci to facilitate re-sampling. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="Restriction Digest">
<xs:annotation>
<xs:documentation> DNA fractionation using restriction enzymes. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="5-methylcytidine antibody">
<xs:annotation>
<xs:documentation> Selection of methylated DNA fragments using an antibody raised against 5-methylcytosine or 5-methylcytidine
(m5C). </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="MBD2 protein methyl-CpG binding domain">
<xs:annotation>
<xs:documentation> Enrichment by methyl-CpG binding domain. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="CAGE">
<xs:annotation>
<xs:documentation> Cap-analysis gene expression. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="RACE">
<xs:annotation>
<xs:documentation> Rapid Amplification of cDNA Ends. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="MDA">
<xs:annotation>
<xs:documentation> Multiple Displacement Amplification, a non-PCR based DNA amplification technique that amplifies a minute
quantifies of DNA to levels suitable for genomic analysis. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="padlock probes capture method">
<xs:annotation>
<xs:documentation> Targeted sequence capture protocol covering an arbitrary set of nonrepetitive genomics targets. An example is
capture bisulfite sequencing using padlock probes (BSPP). </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="other">
<xs:annotation>
<xs:documentation> Other library enrichment, screening, or selection process. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="unspecified">
<xs:annotation>
<xs:documentation> Library enrichment, screening, or selection is not specified. </xs:documentation>
</xs:annotation>
</xs:enumeration>
</xs:restriction>
</xs:simpleType>
<!-- STRING ENUMERATIONS END -->
<xs:complexType name="PoolMemberType">
<xs:complexContent>
<xs:extension base="com:RefObjectType">
<xs:sequence>
<xs:element name="READ_LABEL" minOccurs="0" maxOccurs="unbounded">
<xs:complexType>
<xs:simpleContent>
<xs:extension base="xs:string">
<xs:attribute name="read_group_tag" type="xs:string">
<xs:annotation>
<xs:documentation> Assignment of read_group_tag to decoded read </xs:documentation>
</xs:annotation>
</xs:attribute>
</xs:extension>
</xs:simpleContent>
</xs:complexType>
</xs:element>
</xs:sequence>
<xs:attribute name="member_name" type="xs:string" use="optional">
<xs:annotation>
<xs:documentation> Label a sample within a scope of the pool </xs:documentation>
</xs:annotation>
</xs:attribute>
<xs:attribute name="proportion" type="xs:float" use="optional">
<xs:annotation>
<xs:documentation> Proportion of this sample (in percent) that was included in sample pool. </xs:documentation>
</xs:annotation>
</xs:attribute>
</xs:extension>
</xs:complexContent>
</xs:complexType>
<xs:complexType name="SampleDescriptorType">
<xs:complexContent>
<xs:extension base="com:RefObjectType">
<xs:choice minOccurs="0" maxOccurs="1">
<xs:element name="POOL">
<xs:annotation>
<xs:documentation>
Identifies a list of group/pool/multiplex sample members. This implies that
this sample record is a group, pool, or multiplex, but it continues to receive
its own accession and can be referenced by an experiment. By default if
no match to any of the listed members can be determined, then the default
sample reference is used.
</xs:documentation>
</xs:annotation>
<xs:complexType>
<xs:sequence>
<xs:element name="DEFAULT_MEMBER" type="PoolMemberType" minOccurs="0" maxOccurs="1">
<xs:annotation>
<xs:documentation> Reference to the sample that is used when read membership cannot be determined. A default member should
be provided if there exists a possibility that some reads will be left over from barcode/MID resolution. A default member
is not needed when defining a true pool (where individual samples are not distinguished in the reads), or the reads have
been partitioned among the pool members (no leftovers). </xs:documentation>
</xs:annotation>
</xs:element>
<xs:element name="MEMBER" type="PoolMemberType" minOccurs="1" maxOccurs="unbounded">
<xs:annotation>
<xs:documentation> Reference to the sample as determined from barcode/MID resolution or read partition. </xs:documentation>
</xs:annotation>
</xs:element>
</xs:sequence>
</xs:complexType>
</xs:element>
</xs:choice>
</xs:extension>
</xs:complexContent>
</xs:complexType>
<xs:complexType name="LibraryDescriptorType">
<xs:annotation>
<xs:documentation> The LIBRARY_DESCRIPTOR specifies the origin of the material being
sequenced and any treatments that the material might have undergone that affect the
sequencing result. This specification is needed even if the platform does not
require a library construction step per se. </xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="LIBRARY_NAME" type="xs:string" maxOccurs="1" minOccurs="0">
<xs:annotation>
<xs:documentation>
The submitter's name for this library.
</xs:documentation>
</xs:annotation>
</xs:element>
<xs:element name="LIBRARY_STRATEGY" type="typeLibraryStrategy" minOccurs="1" maxOccurs="1"/>
<xs:element name="LIBRARY_SOURCE" type="typeLibrarySource" minOccurs="1" maxOccurs="1"/>
<xs:element name="LIBRARY_SELECTION" type="typeLibrarySelection" minOccurs="1" maxOccurs="1"/>
<xs:element name="LIBRARY_LAYOUT">
<xs:annotation>
<xs:documentation>
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.
</xs:documentation>
</xs:annotation>
<xs:complexType>
<xs:choice>
<xs:element name="SINGLE">
<xs:complexType>
<xs:annotation>
<xs:documentation>
Reads are unpaired (usual case).
</xs:documentation>
</xs:annotation>
</xs:complexType>
</xs:element>
<xs:element name="PAIRED">
<xs:complexType>
<xs:attribute name="NOMINAL_LENGTH" type="xs:nonNegativeInteger"/>
<xs:attribute name="NOMINAL_SDEV" type="xs:double"/>
</xs:complexType>
</xs:element>
</xs:choice>
</xs:complexType>
</xs:element>
<xs:element name="TARGETED_LOCI" minOccurs="0" maxOccurs="1">
<xs:complexType>
<xs:annotation>
<xs:documentation>
Names the gene(s) or locus(loci) or other genomic feature(s) targeted by the sequence.
</xs:documentation>
</xs:annotation>
<xs:sequence>
<xs:element name="LOCUS" maxOccurs="unbounded" minOccurs="1">
<xs:complexType>
<xs:sequence>
<xs:element name="PROBE_SET" type="com:XRefType" maxOccurs="1" minOccurs="0">
<xs:annotation>
<xs:documentation> Reference to an archived primer or
probe set. Example: dbProbe </xs:documentation>
</xs:annotation>
</xs:element>
</xs:sequence>
<xs:attribute name="locus_name">
<xs:simpleType>
<xs:restriction base="xs:string">
<xs:enumeration value="16S rRNA">
<xs:annotation>
<xs:documentation> Bacterial small subunit ribosomal RNA, a locus used for
phylogenetic studies of bacteria and as a target for random target PCR in
environmental biodiversity screening. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="18S rRNA">
<xs:annotation>
<xs:documentation> Eukaryotic small subunit ribosomal RNA, a locus used for
phylogenetic studies of eukaryotes and as a target for random target PCR in
environmental biodiversity screening. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="28S rRNA">
<xs:annotation>
<xs:documentation>Structural ribosomal RNA for the large component, or large
subunit (LSU) of eukaryotic cytoplasmic ribosomes.. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="RBCL">
<xs:annotation>
<xs:documentation> RuBisCO large subunit : ribulose-1,5-bisphosphate
carboxylase/oxygenase large subunit, a locus used for phylogenetic studies
of plants. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="matK">
<xs:annotation>
<xs:documentation> Maturase K gene, a locus used for phylogenetic studies of
plants. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="COX1">
<xs:annotation>
<xs:documentation> Mitochondrial cytochrome c oxidase 1 gene, a locus used for
phylogenetic studies of animals </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="ITS1-5.8S-ITS2">
<xs:annotation>
<xs:documentation> Internal transcribed spacers 1 and 2 plus 5.8S rRNA region,
a locus used for phylogenetic studies of fungi. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="exome">
<xs:annotation>
<xs:documentation> All exonic regions of the genome. </xs:documentation>
</xs:annotation>
</xs:enumeration>
<xs:enumeration value="other">
<xs:annotation>
<xs:documentation> Other locus, please describe.
</xs:documentation>
</xs:annotation>
</xs:enumeration>
</xs:restriction>
</xs:simpleType>
</xs:attribute>
<xs:attribute name="description" type="xs:string">
<xs:annotation>
<xs:documentation> Submitter supplied description of alternate locus and auxiliary
information. </xs:documentation>
</xs:annotation>
</xs:attribute>
</xs:complexType>
</xs:element>
</xs:sequence>
</xs:complexType>
</xs:element>
<xs:element name="POOLING_STRATEGY" minOccurs="0" maxOccurs="1">
<xs:annotation>
<xs:documentation>
The optional pooling strategy indicates how the library or libraries are organized if multiple samples are involved.
</xs:documentation>
</xs:annotation>
<xs:simpleType>
<xs:restriction base="xs:string"> </xs:restriction>
</xs:simpleType>
</xs:element>
<xs:element name="LIBRARY_CONSTRUCTION_PROTOCOL" type="xs:string" minOccurs="0" maxOccurs="1">
<xs:annotation>
<xs:documentation>
Free form text describing the protocol by which the sequencing library was constructed.
</xs:documentation>
</xs:annotation>
</xs:element>
</xs:sequence>
</xs:complexType>
<xs:complexType name="LibraryType">
<xs:sequence>
<xs:element name="DESIGN_DESCRIPTION" type="xs:string">
<xs:annotation>
<xs:documentation>Goal and setup of the individual library including library was constructed.</xs:documentation>
</xs:annotation>
</xs:element>
<xs:element name="SAMPLE_DESCRIPTOR" type="SampleDescriptorType">
<xs:annotation>
<xs:documentation> Pick a sample to associate this experiment with. The sample may be an individual or a pool,
depending on how it is specified. </xs:documentation>
</xs:annotation>
</xs:element>
<xs:element name="LIBRARY_DESCRIPTOR" type="LibraryDescriptorType">
<xs:annotation>
<xs:documentation> The LIBRARY_DESCRIPTOR specifies the origin of the material being sequenced and any
treatments that the material might have undergone that affect the sequencing result. This specification is
needed even if the platform does not require a library construction step per se. </xs:documentation>
</xs:annotation>
</xs:element>
<xs:element name="SPOT_DESCRIPTOR" type="com:SpotDescriptorType" minOccurs="0" maxOccurs="1">
<xs:annotation>
<xs:documentation> The SPOT_DESCRIPTOR specifies how to decode the individual reads of interest from the
monolithic spot sequence. The spot descriptor contains aspects of the experimental design, platform, and
processing information. There will be two methods of specification: one will be an index into a table of
typical decodings, the other being an exact specification. This construct is needed for loading data and for
interpreting the loaded runs. It can be omitted if the loader can infer read layout (from multiple input
files or from one input files). </xs:documentation>
</xs:annotation>
</xs:element>
</xs:sequence>
</xs:complexType>
<xs:complexType name="ExperimentType">
<xs:annotation>
<xs:documentation>
An Experiment specifies of what will be sequenced and how the sequencing will be performed.
It does not contain results.
An Experiment is composed of a design, a platform selection, and processing parameters.
</xs:documentation>
</xs:annotation>
<xs:complexContent>
<xs:extension base="com:ObjectType">
<xs:sequence>
<xs:element name="TITLE" type="xs:string" minOccurs="0" maxOccurs="1">
<xs:annotation>
<xs:documentation>
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.
</xs:documentation>
</xs:annotation>
</xs:element>
<xs:element name="STUDY_REF" minOccurs="1" maxOccurs="1">
<xs:annotation>
<xs:documentation>
Identifies the parent study.
</xs:documentation>
</xs:annotation>
<xs:complexType>
<xs:complexContent>
<xs:extension base="com:RefObjectType"> </xs:extension>
</xs:complexContent>
</xs:complexType>
</xs:element>
<xs:element name="DESIGN" type="LibraryType" maxOccurs="1" minOccurs="1">
<xs:annotation>
<xs:documentation> The library design including library properties, layout, protocol, targeting information, and spot and gap
descriptors. </xs:documentation>
</xs:annotation>
</xs:element>
<xs:element name="PLATFORM" type="com:PlatformType" maxOccurs="1" minOccurs="1">
<xs:annotation>
<xs:documentation>
The PLATFORM record selects which sequencing platform and platform-specific runtime parameters.
This will be determined by the Center.
</xs:documentation>
</xs:annotation>
</xs:element>
<xs:element name="PROCESSING" type="com:ProcessingType" minOccurs="0" maxOccurs="1"/>
<xs:element name="EXPERIMENT_LINKS" minOccurs="0" maxOccurs="1">
<xs:annotation>
<xs:documentation>
Links to resources related to this experiment or experiment set (publication, datasets, online databases).
</xs:documentation>
</xs:annotation>
<xs:complexType>
<xs:sequence minOccurs="1" maxOccurs="unbounded">
<xs:element name="EXPERIMENT_LINK" type="com:LinkType"/>
</xs:sequence>
</xs:complexType>
</xs:element>
<xs:element name="EXPERIMENT_ATTRIBUTES" minOccurs="0" maxOccurs="1">
<xs:annotation>
<xs:documentation>
Properties and attributes of the experiment. These can be entered as free-form
tag-value pairs.
</xs:documentation>
</xs:annotation>
<xs:complexType>
<xs:sequence maxOccurs="unbounded" minOccurs="1">
<xs:element name="EXPERIMENT_ATTRIBUTE" type="com:AttributeType"/>
</xs:sequence>
</xs:complexType>
</xs:element>
</xs:sequence>
</xs:extension>
</xs:complexContent>
</xs:complexType>
<xs:complexType name="ExperimentSetType">
<xs:sequence minOccurs="1" maxOccurs="1">
<xs:element name="EXPERIMENT" type="ExperimentType" maxOccurs="unbounded"/>
</xs:sequence>
</xs:complexType>
<xs:element name="EXPERIMENT_SET" type="ExperimentSetType">
<xs:annotation>
<xs:documentation>
An EXPERMENT_SET is a container for a set of experiments and a common namespace.
</xs:documentation>
</xs:annotation>
</xs:element>
<xs:element name="EXPERIMENT" type="ExperimentType"/>
</xs:schema>