File: NCBI_Cdd.mod.dtd

package info (click to toggle)
python-biopython 1.68%2Bdfsg-3
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 46,860 kB
  • ctags: 13,237
  • sloc: python: 160,306; xml: 93,216; ansic: 9,118; sql: 1,208; makefile: 155; sh: 63
file content (1088 lines) | stat: -rw-r--r-- 28,292 bytes parent folder | download | duplicates (7)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
<!-- ============================================
     ::DATATOOL:: Generated from "cdd.asn"
     ::DATATOOL:: by application DATATOOL version 2.0.0
     ::DATATOOL:: on 08/02/2010 23:05:14
     ============================================ -->

<!-- ============================================ -->
<!-- This section is mapped from module "NCBI-Cdd"
================================================= -->

<!--
$Revision: 194512 $
**********************************************************************

  Definitions for CDD's 

  NCBI Structure Group

  National Center for Biotechnology Information
  National Institutes of Health
  Bethesda, MD 20894 USA

  October 1999

  asntool -m cdd.asn -w 100 -o cdd.h
  asntool -B objcdd -m cdd.asn -G -w 100 -I objseq.h objsset.h -K cdd.h \
          -M asn.all
**********************************************************************
 NCBI Conserved Domain Definition
-->

<!-- Elements used by other modules:
          Cdd-id,
          Cdd-id-set,
          Cdd,
          Cdd-set,
          Cdd-tree,
          Cdd-tree-set,
          Cdd-pref-nodes,
          Cdd-Project -->

<!-- Elements referenced from other modules:
          Date FROM NCBI-General,
          Pub FROM NCBI-Pub,
          Biostruc-annot-set FROM MMDB,
          Bioseq FROM NCBI-Sequence,
          Seq-annot FROM NCBI-Sequence,
          Seq-entry FROM NCBI-Seqset,
          Org-ref FROM NCBI-Organism,
          Seq-id FROM NCBI-Seqloc,
          Seq-interval FROM NCBI-Seqloc,
          Seq-loc FROM NCBI-Seqloc,
          Seq-feat FROM NCBI-Seqfeat,
          Score-set FROM NCBI-Seqalign,
          Cn3d-style-dictionary,
          Cn3d-user-annotations FROM NCBI-Cn3d,
          PssmWithParameters FROM NCBI-ScoreMat -->
<!-- ============================================ -->

<!-- dealing with lists of preferred tax-nodes  -->
<!ELEMENT Cdd-org-ref (
        Cdd-org-ref_reference, 
        Cdd-org-ref_active?, 
        Cdd-org-ref_parent-tax-id?, 
        Cdd-org-ref_rank?)>

<!ELEMENT Cdd-org-ref_reference (Org-ref)>

<!ELEMENT Cdd-org-ref_active EMPTY>
<!ATTLIST Cdd-org-ref_active value ( true | false ) "true" >


<!ELEMENT Cdd-org-ref_parent-tax-id (%INTEGER;)>

<!ELEMENT Cdd-org-ref_rank (#PCDATA)>


<!ELEMENT Cdd-org-ref-set (Cdd-org-ref*)>


<!ELEMENT Cdd-pref-node-descr (
        Cdd-pref-node-descr_create-date | 
        Cdd-pref-node-descr_description)>

<!ELEMENT Cdd-pref-node-descr_create-date (Date)>

<!ELEMENT Cdd-pref-node-descr_description (#PCDATA)>


<!ELEMENT Cdd-pref-node-descr-set (Cdd-pref-node-descr*)>


<!ELEMENT Cdd-pref-nodes (
        Cdd-pref-nodes_preferred-nodes, 
        Cdd-pref-nodes_model-organisms?, 
        Cdd-pref-nodes_optional-nodes?, 
        Cdd-pref-nodes_description?)>

<!ELEMENT Cdd-pref-nodes_preferred-nodes (Cdd-org-ref-set)>

<!ELEMENT Cdd-pref-nodes_model-organisms (Cdd-org-ref-set)>

<!ELEMENT Cdd-pref-nodes_optional-nodes (Cdd-org-ref-set)>

<!ELEMENT Cdd-pref-nodes_description (Cdd-pref-node-descr-set)>

<!--
 Cdd's should not exist without a unique accession, but alternative id's may
 be present as well. It is conceivable that a CD which is created as a merged
 product of two highly redundant CDs will retain the source ids in addition 
 to its new unique id
 database the object resides in
 currently not in use
-->
<!ELEMENT Global-id (
        Global-id_accession, 
        Global-id_release?, 
        Global-id_version?, 
        Global-id_database?)>

<!-- SMART, Pfam, LOAD or CD accession -->
<!ELEMENT Global-id_accession (#PCDATA)>

<!--
 to hold CD-Database release number
 if desired, currently not used
-->
<!ELEMENT Global-id_release (#PCDATA)>

<!--
 version 0 is the seed, version
 numbers increase with update/curate
 cycles
-->
<!ELEMENT Global-id_version (%INTEGER;)>

<!-- this is NOT the source!, rather the -->
<!ELEMENT Global-id_database (#PCDATA)>


<!ELEMENT Cdd-id (
        Cdd-id_uid | 
        Cdd-id_gid)>

<!--
 for synchronization with Entrez
 holds PSSM-Ids
-->
<!ELEMENT Cdd-id_uid (%INTEGER;)>

<!-- holds accession/version pairs -->
<!ELEMENT Cdd-id_gid (Global-id)>


<!ELEMENT Cdd-id-set (Cdd-id*)>

<!--
 record whether the CD contains
 repeated sequence/structure motifs
-->
<!ELEMENT Cdd-repeat (
        Cdd-repeat_count, 
        Cdd-repeat_location?, 
        Cdd-repeat_avglen?)>

<!-- number of tandem repeats in the CD -->
<!ELEMENT Cdd-repeat_count (%INTEGER;)>

<!-- location on the representative -->
<!ELEMENT Cdd-repeat_location (Seq-loc)>

<!-- average repeat length -->
<!ELEMENT Cdd-repeat_avglen (%INTEGER;)>

<!-- record a link to Entrez Books -->
<!ELEMENT Cdd-book-ref (
        Cdd-book-ref_bookname, 
        Cdd-book-ref_textelement, 
        Cdd-book-ref_elementid?, 
        Cdd-book-ref_subelementid?, 
        Cdd-book-ref_celementid?, 
        Cdd-book-ref_csubelementid?)>

<!-- abbreviated book title -->
<!ELEMENT Cdd-book-ref_bookname (#PCDATA)>

<!ELEMENT Cdd-book-ref_textelement %ENUM;>

<!--
    unassigned	-  type of element 
    section	-  a section or paragraph
    figgrp	-  a figure or set of figures
    table	-  a table
    chapter	-  a whole chapter
    biblist	-  a lisf of references
    box	-  an inserted box
    glossary	-  glossary
    appendix	-  appendix
-->
<!ATTLIST Cdd-book-ref_textelement value (
        unassigned |
        section |
        figgrp |
        table |
        chapter |
        biblist |
        box |
        glossary |
        appendix |
        other
        ) #REQUIRED >


<!-- numerical address of the text-element -->
<!ELEMENT Cdd-book-ref_elementid (%INTEGER;)>

<!-- exact address, used with section -->
<!ELEMENT Cdd-book-ref_subelementid (%INTEGER;)>

<!-- address of the text element, if character string -->
<!ELEMENT Cdd-book-ref_celementid (#PCDATA)>

<!-- exact address, if character string -->
<!ELEMENT Cdd-book-ref_csubelementid (#PCDATA)>

<!--
 The description of CDD's refers to the specific set of aligned sequences,
 the region that is being aligned and the information contained in the
 alignment. It may contain a lengthy comment
 describing the function of the domain as well as its origin and all
 other anecdotal information that can't be pressed into a rigid scheme.
 Crosslinks to reference papers available in PubMed are possible as well.
 There can be as many of these as you want in the CDD.
-->
<!ELEMENT Cdd-descr (
        Cdd-descr_othername | 
        Cdd-descr_category | 
        Cdd-descr_comment | 
        Cdd-descr_reference | 
        Cdd-descr_create-date | 
        Cdd-descr_tax-source | 
        Cdd-descr_source | 
        Cdd-descr_status | 
        Cdd-descr_update-date | 
        Cdd-descr_scrapbook | 
        Cdd-descr_source-id | 
        Cdd-descr_repeats | 
        Cdd-descr_old-root | 
        Cdd-descr_curation-status | 
        Cdd-descr_readonly-status | 
        Cdd-descr_book-ref | 
        Cdd-descr_attribution | 
        Cdd-descr_title)>

<!--
 alternative names for the CDD
 if domain has several common names
-->
<!ELEMENT Cdd-descr_othername (#PCDATA)>

<!--
 intracellular, extracellular, etc.
 to record spatial and/or temporal
 expression in free-text format
-->
<!ELEMENT Cdd-descr_category (#PCDATA)>

<!-- this is where descriptions go -->
<!ELEMENT Cdd-descr_comment (#PCDATA)>

<!-- a citation describing the domain -->
<!ELEMENT Cdd-descr_reference (Pub)>

<!-- Date of first creation/dump -->
<!ELEMENT Cdd-descr_create-date (Date)>

<!-- holds the highest common tax node -->
<!ELEMENT Cdd-descr_tax-source (Org-ref)>

<!--
 the database the seeds were created
 from, e.g. SMART, PFAM, etc..
-->
<!ELEMENT Cdd-descr_source (#PCDATA)>

<!ELEMENT Cdd-descr_status (%INTEGER;)>

<!--
    finished-ok	-  a public curated CD
    pending-release	-  needs work done, not yet released
    other-asis	-  imported as-is, immediate release
    matrix-only	-  CD holds a Psi-Blast PSSM only,
         does not contain alignment data
    update-running	-  has been flagged for
         update (in queue)
    auto-updated	-  update finished, no
         work necessary
    claimed	-  is earmarked for curation
    curated-complete	-  public curated member of a
         completed family
    other	-  for CD production?
-->
<!ATTLIST Cdd-descr_status value (
        unassigned |
        finished-ok |
        pending-release |
        other-asis |
        matrix-only |
        update-running |
        auto-updated |
        claimed |
        curated-complete |
        other
        ) #IMPLIED >


<!-- Date of last version change -->
<!ELEMENT Cdd-descr_update-date (Date)>

<!--
 for storing curation notes
 those won't make it into public
 distributions
-->
<!ELEMENT Cdd-descr_scrapbook (Cdd-descr_scrapbook_E*)>


<!ELEMENT Cdd-descr_scrapbook_E (#PCDATA)>

<!-- for linking back to source db -->
<!ELEMENT Cdd-descr_source-id (Cdd-id-set)>

<!-- to record repeat counts -->
<!ELEMENT Cdd-descr_repeats (Cdd-repeat)>

<!-- to record short-term history -->
<!ELEMENT Cdd-descr_old-root (Cdd-id-set)>

<!ELEMENT Cdd-descr_curation-status (%INTEGER;)>

<!--
    unassigned	-  to record curation status
    prein	-  when CD is checked out from
    ofc	-  the tracking database, for 
    iac	-  use within curation software
-->
<!ATTLIST Cdd-descr_curation-status value (
        unassigned |
        prein |
        ofc |
        iac |
        ofv1 |
        iav1 |
        ofv2 |
        iav2 |
        postin |
        other
        ) #IMPLIED >


<!ELEMENT Cdd-descr_readonly-status (%INTEGER;)>

<!--
    unassigned	-  to record read-only status
    readonly	-  when CD is checked out from
    readwrite	-  the tracking database, for
    other	-  use within curation software
-->
<!ATTLIST Cdd-descr_readonly-status value (
        unassigned |
        readonly |
        readwrite |
        other
        ) #IMPLIED >


<!-- links to Entrez/books -->
<!ELEMENT Cdd-descr_book-ref (Cdd-book-ref)>

<!-- add citations and/or author names -->
<!ELEMENT Cdd-descr_attribution (Pub)>

<!-- hold short descriptive text -->
<!ELEMENT Cdd-descr_title (#PCDATA)>


<!ELEMENT Cdd-descr-set (Cdd-descr*)>

<!--
 the Cdd-tree stores the hierarchy of CDDs. These objects are stored separate
 from the CDs to allow for fast retrieval and use as an 'index' into CDs
 all the components in a CD-tree match components in the full-sized CD
 and should be synchronized
-->
<!ELEMENT Cdd-tree (
        Cdd-tree_name, 
        Cdd-tree_id, 
        Cdd-tree_description?, 
        Cdd-tree_parent?, 
        Cdd-tree_children?, 
        Cdd-tree_siblings?, 
        Cdd-tree_neighbors?)>

<!-- short name  copied from CD -->
<!ELEMENT Cdd-tree_name (#PCDATA)>

<!-- IDs         copied from CD -->
<!ELEMENT Cdd-tree_id (Cdd-id-set)>

<!-- description copied from CD -->
<!ELEMENT Cdd-tree_description (Cdd-descr-set)>

<!-- CD is the result of a split/merge -->
<!ELEMENT Cdd-tree_parent (Cdd-id)>

<!-- this CD has been split -->
<!ELEMENT Cdd-tree_children (Cdd-id-set)>

<!-- related CDs (have common hits) -->
<!ELEMENT Cdd-tree_siblings (Cdd-id-set)>

<!--
 co-occurring CDs (non-overlapping 
 hits to same sequences)
-->
<!ELEMENT Cdd-tree_neighbors (Cdd-id-set)>


<!ELEMENT Cdd-tree-set (Cdd-tree*)>

<!--
 Matrix definitions, these are supposed to store PSSMs and corresponding 
 matrices of relative residue frequencies.
 the number of columns and rows is listed explicitly, values in columns
 are stored column by column, i.e. in groups of nrows values for each column
-->
<!ELEMENT Matrix (
        Matrix_ncolumns, 
        Matrix_nrows, 
        Matrix_row-labels?, 
        Matrix_scale-factor, 
        Matrix_columns)>

<!ELEMENT Matrix_ncolumns (%INTEGER;)>

<!ELEMENT Matrix_nrows (%INTEGER;)>

<!ELEMENT Matrix_row-labels (Matrix_row-labels_E*)>


<!ELEMENT Matrix_row-labels_E (#PCDATA)>

<!ELEMENT Matrix_scale-factor (%INTEGER;)>

<!ELEMENT Matrix_columns (Matrix_columns_E*)>


<!ELEMENT Matrix_columns_E (%INTEGER;)>

<!--
 definition for matrix of pairwise "distances", stored as the upper 
 triangle of a squared n x n matrix (excluding the diagonal), this is
 supposed to store pairwise percentages of identical residues, pairwise
 alignment scores or E-values from pairwise BLAST sequence comparisons
-->
<!ELEMENT Triangle (
        Triangle_nelements, 
        Triangle_scores?, 
        Triangle_div-ranks?)>

<!ELEMENT Triangle_nelements (%INTEGER;)>

<!ELEMENT Triangle_scores (Score-set)>

<!ELEMENT Triangle_div-ranks (Triangle_div-ranks_E*)>


<!ELEMENT Triangle_div-ranks_E (%INTEGER;)>

<!--
 Update-align is supposed to contain alignments that still need some work
 done to fit into the CD-proper alignment. These originate from the
 CD update process (generated by Blast, for example) or may be created in
 an editing session to save its state
-->
<!ELEMENT Update-comment (
        Update-comment_comment | 
        Update-comment_addthis | 
        Update-comment_replaces | 
        Update-comment_reject-loc | 
        Update-comment_reference)>

<!--
 free text to describe nature of
 Update-align
-->
<!ELEMENT Update-comment_comment (#PCDATA)>

<!--
 suggestion for inclusion in the CD
 without corresponding alignment
-->
<!ELEMENT Update-comment_addthis (Seq-loc)>

<!--
 if one or several alignment rows are
 to be replaced by the Update-align
-->
<!ELEMENT Update-comment_replaces (Seq-loc)>

<!--
 if used with Reject-id, specify a
 location on a sequence which should
 not be used
-->
<!ELEMENT Update-comment_reject-loc (Seq-loc)>

<!--
 if update alignment imported from
 citation and for whenever it seems
 necessary to cite
-->
<!ELEMENT Update-comment_reference (Pub)>

<!--
 Both fields are optional, as the Update-align may be a Seq-annot without
 description, or a suggestion to add a sequence without the corresponding
 alignment
-->
<!ELEMENT Update-align (
        Update-align_description?, 
        Update-align_seqannot?, 
        Update-align_type)>

<!ELEMENT Update-align_description (Update-comment*)>

<!-- contains the SeqAlign -->
<!ELEMENT Update-align_seqannot (Seq-annot)>

<!ELEMENT Update-align_type (%INTEGER;)>
<!ATTLIST Update-align_type value (
        unassigned |
        update |
        update-3d |
        demoted |
        demoted-3d |
        other
        ) #IMPLIED >



<!ELEMENT Reject-id (
        Reject-id_description?, 
        Reject-id_ids)>

<!ELEMENT Reject-id_description (Update-comment*)>

<!ELEMENT Reject-id_ids (Seq-id*)>


<!ELEMENT Feature-evidence (
        Feature-evidence_comment | 
        Feature-evidence_reference | 
        Feature-evidence_bsannot | 
        Feature-evidence_seqfeat | 
        Feature-evidence_book-ref)>

<!--
 so we can spell out what doesn't
 fit in any other category
-->
<!ELEMENT Feature-evidence_comment (#PCDATA)>

<!-- evidence via a literature reference -->
<!ELEMENT Feature-evidence_reference (Pub)>

<!--
 evidence via Biostruc-features, such
 as structure superpositions 
-->
<!ELEMENT Feature-evidence_bsannot (Biostruc-annot-set)>

<!--
 evidence is a Sequence feature found
 elsewhere
-->
<!ELEMENT Feature-evidence_seqfeat (Seq-feat)>

<!-- evidence is a book chapter or figure -->
<!ELEMENT Feature-evidence_book-ref (Cdd-book-ref)>


<!ELEMENT Align-annot (
        Align-annot_location, 
        Align-annot_description?, 
        Align-annot_evidence?, 
        Align-annot_type?, 
        Align-annot_aliases?, 
        Align-annot_motif?, 
        Align-annot_motifuse?)>

<!--
 points to a location in one of the
 aligned sequences, usually the
 master/representative
-->
<!ELEMENT Align-annot_location (Seq-loc)>

<!--
 to hold descriptions/names like
 "Heme binding site" or "catalytic
 triad" etc., something that should
 be used for labels in visualization
-->
<!ELEMENT Align-annot_description (#PCDATA)>

<!--
 evidence we can
 compute with
-->
<!ELEMENT Align-annot_evidence (Feature-evidence*)>

<!--
 for typing annotated features
 0 .. no type assigned
 1 .. active site
 2 .. polypeptide binding site
 3 .. nucleic acid binding site
 4 .. ion binding site
 5 .. chemical binding site
 6 .. posttranslational modification site
-->
<!ELEMENT Align-annot_type (%INTEGER;)>

<!-- adding more names for indexing -->
<!ELEMENT Align-annot_aliases (Align-annot_aliases_E*)>


<!ELEMENT Align-annot_aliases_E (#PCDATA)>

<!-- to validate mapping of sites -->
<!ELEMENT Align-annot_motif (#PCDATA)>

<!--
 0 for validation,
 1 for motif somewhere in seqloc
 2 for multiple motifs in seqloc
-->
<!ELEMENT Align-annot_motifuse (%INTEGER;)>


<!ELEMENT Align-annot-set (Align-annot*)>

<!--
 the Domain-parent records an evolutionary relationship which may not be
 as simple as a classical parent-child relationship in a typical hierarchy,
 i.e. where a CD is merely a specific subgroup ("child") of a more general
 diverse alignment model ("parent"). A CD alignment model may be the result
 of an ancient fusion event, combining two or more domains into a bigger unit
 which has subsequently undergone a divergent evolutionary process similar to
 what may have happened to a single "domain". A CD alignment model may 
 also reflect the result of a deletion event, where a specific subgroup
 lacks part of a (set of) domain(s), but where the part present is found to
 be highly similar to a putative "parent", with some added evidence for
 an actual deletion, like from the distribution of truncated copies in phylogenetic
 lineages. Deletion events which affect different parts of a set of
 duplicated domain architectures may be indistinguishable from actual
 fission events, which means that we may want to represent the latter as
 deletions after duplication and do not need a special case for fissions.
-->
<!ELEMENT Domain-parent (
        Domain-parent_parent-type, 
        Domain-parent_parentid, 
        Domain-parent_seqannot?)>

<!ELEMENT Domain-parent_parent-type (%INTEGER;)>

<!--
    classical	-  the classification of parent child relations
-->
<!ATTLIST Domain-parent_parent-type value (
        classical |
        fusion |
        deletion |
        permutation |
        other
        ) #IMPLIED >


<!-- identify the section parent by accession -->
<!ELEMENT Domain-parent_parentid (Cdd-id)>

<!--
 contains the sequence alignment linking
 CD alignment models, should align the 
 masters/representatives of each CD
-->
<!ELEMENT Domain-parent_seqannot (Seq-annot)>

<!-- record sequence trees generated by a suitable algorithm. -->
<!ELEMENT Sequence-tree (
        Sequence-tree_cdAccession?, 
        Sequence-tree_algorithm, 
        Sequence-tree_isAnnotated?, 
        Sequence-tree_root)>

<!ELEMENT Sequence-tree_cdAccession (#PCDATA)>

<!ELEMENT Sequence-tree_algorithm (Algorithm-type)>

<!ELEMENT Sequence-tree_isAnnotated EMPTY>
<!ATTLIST Sequence-tree_isAnnotated value ( true | false ) "false" >


<!ELEMENT Sequence-tree_root (SeqTree-node)>


<!ELEMENT SeqTree-node (
        SeqTree-node_isAnnotated?, 
        SeqTree-node_name?, 
        SeqTree-node_distance?, 
        SeqTree-node_children, 
        SeqTree-node_annotation?)>

<!ELEMENT SeqTree-node_isAnnotated EMPTY>
<!ATTLIST SeqTree-node_isAnnotated value ( true | false ) "false" >


<!ELEMENT SeqTree-node_name (#PCDATA)>

<!ELEMENT SeqTree-node_distance (%REAL;)>

<!ELEMENT SeqTree-node_children (
        SeqTree-node_children_children | 
        SeqTree-node_children_footprint)>

<!ELEMENT SeqTree-node_children_children (SeqTree-node*)>

<!ELEMENT SeqTree-node_children_footprint (
        SeqTree-node_children_footprint_seqRange, 
        SeqTree-node_children_footprint_rowId?)>

<!ELEMENT SeqTree-node_children_footprint_seqRange (Seq-interval)>

<!ELEMENT SeqTree-node_children_footprint_rowId (%INTEGER;)>

<!ELEMENT SeqTree-node_annotation (Node-annotation)>


<!ELEMENT Algorithm-type (
        Algorithm-type_scoring-Scheme, 
        Algorithm-type_clustering-Method, 
        Algorithm-type_score-Matrix?, 
        Algorithm-type_gapOpen?, 
        Algorithm-type_gapExtend?, 
        Algorithm-type_gapScaleFactor?, 
        Algorithm-type_nTerminalExt?, 
        Algorithm-type_cTerminalExt?, 
        Algorithm-type_tree-scope?, 
        Algorithm-type_coloring-scope?)>

<!ELEMENT Algorithm-type_scoring-Scheme (%INTEGER;)>
<!ATTLIST Algorithm-type_scoring-Scheme value (
        unassigned |
        percent-id |
        kimura-corrected |
        aligned-score |
        aligned-score-ext |
        aligned-score-filled |
        blast-footprint |
        blast-full |
        hybrid-aligned-score |
        other
        ) #IMPLIED >


<!ELEMENT Algorithm-type_clustering-Method (%INTEGER;)>
<!ATTLIST Algorithm-type_clustering-Method value (
        unassigned |
        single-linkage |
        neighbor-joining |
        fast-minimum-evolution |
        other
        ) #IMPLIED >


<!ELEMENT Algorithm-type_score-Matrix (%INTEGER;)>
<!ATTLIST Algorithm-type_score-Matrix value (
        unassigned |
        blosum45 |
        blosum62 |
        blosum80 |
        pam30 |
        pam70 |
        pam250 |
        other
        ) #IMPLIED >


<!ELEMENT Algorithm-type_gapOpen (%INTEGER;)>

<!ELEMENT Algorithm-type_gapExtend (%INTEGER;)>

<!ELEMENT Algorithm-type_gapScaleFactor (%INTEGER;)>

<!ELEMENT Algorithm-type_nTerminalExt (%INTEGER;)>

<!ELEMENT Algorithm-type_cTerminalExt (%INTEGER;)>

<!ELEMENT Algorithm-type_tree-scope (%INTEGER;)>
<!ATTLIST Algorithm-type_tree-scope value (
        allDescendants |
        immediateChildrenOnly |
        selfOnly |
        other
        ) #IMPLIED >


<!ELEMENT Algorithm-type_coloring-scope (%INTEGER;)>
<!ATTLIST Algorithm-type_coloring-scope value (
        allDescendants |
        immediateChildrenOnly |
        other
        ) #IMPLIED >



<!ELEMENT Node-annotation (
        Node-annotation_presentInChildCD?, 
        Node-annotation_note?)>

<!ELEMENT Node-annotation_presentInChildCD (#PCDATA)>

<!ELEMENT Node-annotation_note (#PCDATA)>

<!--
 the Cdd is the basic ASN.1 object storing an annotated and curated set of
 alignments (formulated as a set of pairwise master-slave alignments). 
 The alignment data are contained in Seq-annots, and a special type of
 object, the Update-align, contains additional alignment data from unfinished
 editing sessions and update processes. The Biostruc-annot-set holds 
 structure superposition information for multiple structure-derived rows in
 the alignment.
 Version numbers in Global-ids are meant to be updated every time the Cdd is
 changed in a way that does not require Global-ids to be changed (sequences
 added in update cycle, annotation changed, alignment errors fixed)
-->
<!ELEMENT Cdd (
        Cdd_name, 
        Cdd_id, 
        Cdd_description?, 
        Cdd_seqannot?, 
        Cdd_features?, 
        Cdd_sequences?, 
        Cdd_profile-range?, 
        Cdd_trunc-master?, 
        Cdd_posfreq?, 
        Cdd_scoremat?, 
        Cdd_distance?, 
        Cdd_parent?, 
        Cdd_children?, 
        Cdd_siblings?, 
        Cdd_neighbors?, 
        Cdd_pending?, 
        Cdd_rejects?, 
        Cdd_master3d?, 
        Cdd_alignannot?, 
        Cdd_style-dictionary?, 
        Cdd_user-annotations?, 
        Cdd_ancestors?, 
        Cdd_scoreparams?, 
        Cdd_seqtree?)>

<!-- a short name (can be the accession..) -->
<!ELEMENT Cdd_name (#PCDATA)>

<!-- this CD's Ids -->
<!ELEMENT Cdd_id (Cdd-id-set)>

<!-- status, references, etc. -->
<!ELEMENT Cdd_description (Cdd-descr-set)>

<!-- contains the CD alignment -->
<!ELEMENT Cdd_seqannot (Seq-annot*)>

<!--
 contains structure
 alignment data
 or "core" definitions
-->
<!ELEMENT Cdd_features (Biostruc-annot-set)>

<!-- store as bioseq-set inside seq-entry -->
<!ELEMENT Cdd_sequences (Seq-entry)>

<!--
 profile for this region only
 also stores the Seq-id of the master
-->
<!ELEMENT Cdd_profile-range (Seq-interval)>

<!--
 holds the truncated master, which
 may be something like a consensus,
 uses the same sequence coordinate
 frame as the profile-range
-->
<!ELEMENT Cdd_trunc-master (Bioseq)>

<!-- relative residue frequencies -->
<!ELEMENT Cdd_posfreq (Matrix)>

<!-- Position dependent score matrix -->
<!ELEMENT Cdd_scoremat (Matrix)>

<!-- pairwise distances for all seqs. -->
<!ELEMENT Cdd_distance (Triangle)>

<!-- this CD is the result of a split -->
<!ELEMENT Cdd_parent (Cdd-id)>

<!-- this CD has been split, not used -->
<!ELEMENT Cdd_children (Cdd-id-set)>

<!-- related CDs (common hits), clusters -->
<!ELEMENT Cdd_siblings (Cdd-id-set)>

<!-- co-occurring CDs, not used -->
<!ELEMENT Cdd_neighbors (Cdd-id-set)>

<!--
 contains alignments from
 update or "lower panel"
-->
<!ELEMENT Cdd_pending (Update-align*)>

<!--
 SeqIds of rejected CD-
 members, ignore in update
-->
<!ELEMENT Cdd_rejects (Reject-id*)>

<!-- record if CD has a 3D representative -->
<!ELEMENT Cdd_master3d (Seq-id*)>

<!-- alignment annotation -->
<!ELEMENT Cdd_alignannot (Align-annot-set)>

<!-- record rendering styles -->
<!ELEMENT Cdd_style-dictionary (Cn3d-style-dictionary)>

<!-- user annotations in Cn3D -->
<!ELEMENT Cdd_user-annotations (Cn3d-user-annotations)>

<!-- list of parents -->
<!ELEMENT Cdd_ancestors (Domain-parent*)>

<!ELEMENT Cdd_scoreparams (PssmWithParameters)>
<!-- record sequence trees generated by a suitable algorithm. -->
<!ELEMENT Cdd_seqtree (Sequence-tree)>


<!ELEMENT Cdd-set (Cdd*)>

<!--
 Cdd projects store a set of CDs, typically related to each other
 relationships would be specified using the ancestors fields in the
 individual CD objects. For use with CD-Tree, a program to visualize
 curated CD hierarchies and evidence for hierarchical family structures.
-->
<!ELEMENT Cdd-Viewer-Rect (
        Cdd-Viewer-Rect_top, 
        Cdd-Viewer-Rect_left, 
        Cdd-Viewer-Rect_width, 
        Cdd-Viewer-Rect_height)>

<!-- top coordinate -->
<!ELEMENT Cdd-Viewer-Rect_top (%INTEGER;)>

<!-- left  coordinate -->
<!ELEMENT Cdd-Viewer-Rect_left (%INTEGER;)>

<!-- width  -->
<!ELEMENT Cdd-Viewer-Rect_width (%INTEGER;)>

<!-- height -->
<!ELEMENT Cdd-Viewer-Rect_height (%INTEGER;)>


<!ELEMENT Cdd-Viewer (
        Cdd-Viewer_ctrl, 
        Cdd-Viewer_rect?, 
        Cdd-Viewer_accessions)>
<!-- viewer type -->
<!ELEMENT Cdd-Viewer_ctrl (%INTEGER;)>
<!ATTLIST Cdd-Viewer_ctrl value (
        unassigned |
        cd-info |
        align-annot |
        seq-list |
        seq-tree |
        merge-preview |
        cross-hits |
        notes |
        tax-tree |
        dart |
        dart-selected-rows |
        other
        ) #IMPLIED >


<!-- viewer rectangle -->
<!ELEMENT Cdd-Viewer_rect (Cdd-Viewer-Rect)>

<!-- list of accessions associated with a viewer -->
<!ELEMENT Cdd-Viewer_accessions (Cdd-Viewer_accessions_E*)>


<!ELEMENT Cdd-Viewer_accessions_E (#PCDATA)>


<!ELEMENT Cdd-Script (
        Cdd-Script_type?, 
        Cdd-Script_name?, 
        Cdd-Script_commands)>

<!ELEMENT Cdd-Script_type (%INTEGER;)>
<!ATTLIST Cdd-Script_type value (
        unassigned |
        user-recorded |
        server-generated |
        other
        ) #IMPLIED >


<!-- user assigned name/description -->
<!ELEMENT Cdd-Script_name (#PCDATA)>

<!-- actual script commands -->
<!ELEMENT Cdd-Script_commands (#PCDATA)>

<!-- cd colors are as:  0000FF for red, 00FF00 for green, FF0000 for blue -->
<!ELEMENT Cdd-Project (
        Cdd-Project_cds, 
        Cdd-Project_cdcolor, 
        Cdd-Project_viewers, 
        Cdd-Project_log, 
        Cdd-Project_scripts?, 
        Cdd-Project_id?, 
        Cdd-Project_rids?, 
        Cdd-Project_create-date?, 
        Cdd-Project_update-date?, 
        Cdd-Project_project-id?)>

<!-- cds -->
<!ELEMENT Cdd-Project_cds (Cdd*)>

<!-- colors   -->
<!ELEMENT Cdd-Project_cdcolor (Cdd-Project_cdcolor_E*)>


<!ELEMENT Cdd-Project_cdcolor_E (%INTEGER;)>

<!-- Sequence viewers -->
<!ELEMENT Cdd-Project_viewers (Cdd-Viewer*)>

<!-- log -->
<!ELEMENT Cdd-Project_log (#PCDATA)>

<!-- command scripts -->
<!ELEMENT Cdd-Project_scripts (Cdd-Script*)>

<!-- to assign unique project id -->
<!ELEMENT Cdd-Project_id (Cdd-id-set)>

<!-- to store request IDs for batch CD-Searches -->
<!ELEMENT Cdd-Project_rids (Cdd-Project_rids_E*)>


<!ELEMENT Cdd-Project_rids_E (#PCDATA)>

<!ELEMENT Cdd-Project_create-date (Date)>

<!ELEMENT Cdd-Project_update-date (Date)>

<!-- for temporary tracking in the database -->
<!ELEMENT Cdd-Project_project-id (%INTEGER;)>