cdd.asn

ncbi源码

-- alignment

Update-align ::= SEQUENCE {
  description   SEQUENCE OF Update-comment OPTIONAL,  
  seqannot      Seq-annot OPTIONAL,     -- contains the SeqAlign
  type          INTEGER { unassigned(0),
                          update(1),
                          update-3d(2),
                          demoted(51),
                          demoted-3d(52),
                          other(255)}
}

Reject-id ::= SEQUENCE {
  description   SEQUENCE OF Update-comment OPTIONAL,
  ids           SET OF Seq-id
}

Feature-evidence ::= CHOICE {
  comment       VisibleString,          -- so we can spell out what doesn't
                                        -- fit in any other category
  reference     Pub,                    -- evidence via a literature reference
  bsannot       Biostruc-annot-set,     -- evidence via Biostruc-features, such
                                        -- as structure superpositions 
  seqfeat       Seq-feat,               -- evidence is a Sequence feature found
                                        -- elsewhere
  book-ref      Cdd-book-ref            -- evidence is a book chapter or figure
}

Align-annot ::= SEQUENCE {
  location      Seq-loc,                -- points to a location in one of the
                                        -- aligned sequences, usually the
                                        -- master/representative
  description   VisibleString OPTIONAL, -- to hold descriptions/names like
                                        -- "Heme binding site" or "catalytic
                                        -- triad" etc., something that should
                                        -- be used for labels in visualization
  evidence      SEQUENCE OF Feature-evidence OPTIONAL -- evidence we can
                                                      -- compute with
}

Align-annot-set ::= SEQUENCE OF 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.

Domain-parent ::= SEQUENCE {

  parent-type    INTEGER { classical           (0), -- the classification of parent child relations
                           fusion              (1),
                           deletion            (2),
                           permutation         (3),
                           other               (255) },
  parentid       Cdd-id,                -- identify the section parent by accession
  seqannot       Seq-annot OPTIONAL     -- contains the sequence alignment linking
                                        -- CD alignment models, should align the 
                                        -- masters/representatives of each CD
}


-- record sequence trees generated by a suitable algorithm.

Sequence-tree ::= SEQUENCE {
  cdAccession    VisibleString OPTIONAL,
  algorithm      Algorithm-type,
  isAnnotated    BOOLEAN DEFAULT FALSE,
  root           SeqTree-node
}

SeqTree-node ::= SEQUENCE {
  isAnnotated    BOOLEAN DEFAULT FALSE,
  name           VisibleString           OPTIONAL,
  distance       REAL                    OPTIONAL,
  children       CHOICE {
    children SEQUENCE OF SeqTree-node,
    footprint SEQUENCE {
      seqRange   Seq-interval,
      rowId      INTEGER OPTIONAL
    }
  },
  annotation     Node-annotation         OPTIONAL
}

Algorithm-type ::= SEQUENCE {
  scoring-Scheme    INTEGER { unassigned           (0),
                              percent-id           (1),
                              kimura-corrected     (2),
                              aligned-score        (3),
                              aligned-score-ext    (4),
                              aligned-score-filled (5),
                              blast-footprint      (6),
                              blast-full           (7),
                              other           (255) },
  clustering-Method INTEGER { unassigned             (0),
                              single-linkage         (1),
                              neighbor-joining       (2),
                              fast-minimum-evolution (3),
                              other                (255) },
  score-Matrix      INTEGER { unassigned (0),
                              blosum45   (1),
                              blosum62   (2),
                              blosum80   (3),
                              pam30      (4),
                              pam70      (5),
                              pam250     (6),
                              other    (255) } OPTIONAL,
  gapOpen           INTEGER OPTIONAL,
  gapExtend         INTEGER OPTIONAL,
  gapScaleFactor    INTEGER OPTIONAL,
  nTerminalExt      INTEGER OPTIONAL,
  cTerminalExt      INTEGER OPTIONAL
}

Node-annotation ::= SEQUENCE {
  presentInChildCD VisibleString OPTIONAL,
  note             VisibleString OPTIONAL
}

-- 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)

Cdd ::= SEQUENCE {
  name          VisibleString,          -- a short name (can be the accession..)
  id            Cdd-id-set,             -- this CD's Ids
  description   Cdd-descr-set OPTIONAL, -- status, references, etc.
  seqannot      SEQUENCE OF Seq-annot    OPTIONAL,  -- contains the CD alignment
  features      Biostruc-annot-set       OPTIONAL,  -- contains structure
                                                    -- alignment data
                                                    -- or "core" definitions
  sequences     Seq-entry     OPTIONAL, -- store as bioseq-set inside seq-entry
  profile-range Seq-interval  OPTIONAL, -- profile for this region only
                                        -- also stores the Seq-id of the master
  trunc-master  Bioseq        OPTIONAL, -- holds the truncated master, which
                                        -- may be something like a consensus,
                                        -- uses the same sequence coordinate
                                        -- frame as the profile-range
  posfreq       Matrix        OPTIONAL, -- relative residue frequencies
  scoremat      Matrix        OPTIONAL, -- Position dependent score matrix
  distance      Triangle      OPTIONAL, -- pairwise distances for all seqs.
  parent        Cdd-id        OPTIONAL, -- this CD is the result of a split
  children      Cdd-id-set    OPTIONAL, -- this CD has been split, not used
  siblings      Cdd-id-set    OPTIONAL, -- related CDs (common hits), not used
  neighbors     Cdd-id-set    OPTIONAL, -- co-occurring CDs, not used
  pending       SEQUENCE OF Update-align OPTIONAL,  -- contains alignments from
                                                    -- update or "lower panel"
  rejects       SEQUENCE OF Reject-id    OPTIONAL,  -- SeqIds of rejected CD-
                                                    -- members, ignore in update
  master3d      SET OF Seq-id OPTIONAL, -- record if CD has a 3D representative
  alignannot    Align-annot-set OPTIONAL,           -- alignment annotation
  style-dictionary Cn3d-style-dictionary OPTIONAL,  -- record rendering styles
  user-annotations Cn3d-user-annotations OPTIONAL,  -- user annotations in Cn3D
  ancestors     SEQUENCE OF Domain-parent OPTIONAL, -- list of parents
  scoreparams   Score-matrix-parameters  OPTIONAL,
  seqtree       Sequence-tree            OPTIONAL
}

Cdd-set ::= SET OF 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.

Cdd-Viewer-Rect ::= SEQUENCE {
  top           INTEGER,           -- top coordinate
  left          INTEGER,           -- left  coordinate
  width         INTEGER,           -- width 
  height        INTEGER            -- height
}

Cdd-Viewer ::= SEQUENCE {
  ctrl          INTEGER {                   -- viewer type
                  unassigned          (0),
		  cd-info             (1),
		  align-annot         (2),
		  seq-list            (3),
		  seq-tree            (4),
		  merge-preview       (5),
		  cross-hits          (6),
		  notes               (7),
		  tax-tree            (8),
		  dart                (9),
		  dart-selected-rows (10),
		  other (255)
                },
  rect          Cdd-Viewer-Rect OPTIONAL,  -- viewer rectangle
  accessions    SEQUENCE OF VisibleString  -- list of accessions associated with a viewer
}

Cdd-Script ::= SEQUENCE {
  type          INTEGER {
                  unassigned (0),
                  user-recorded (1),
		  server-generated (2),
                  other (255)
                } OPTIONAL,
  name          VisibleString OPTIONAL,   -- user assigned name/description
  commands      VisibleString             -- actual script commands
}


-- cd colors are as:  0000FF for red, 00FF00 for green, FF0000 for blue

Cdd-Project ::= SEQUENCE {
  cds           SEQUENCE OF Cdd ,         -- cds
  cdcolor       SEQUENCE OF INTEGER,      -- colors  
  viewers       SEQUENCE OF Cdd-Viewer,   -- Sequence viewers
  log           VisibleString,            -- log
  scripts       SEQUENCE OF Cdd-Script OPTIONAL    -- command scripts
}

END