seq.asn

ncbi源码

    ascending BOOLEAN DEFAULT TRUE }  -- ascending numbers?

Num-enum ::= SEQUENCE {          -- any tags to residues
    num INTEGER ,                        -- number of tags to follow
    names SEQUENCE OF VisibleString }    -- the tags

Num-ref ::= SEQUENCE {           -- by reference to other sequences
    type ENUMERATED {            -- type of reference
        not-set (0) ,
        sources (1) ,            -- by segmented or const seq sources
        aligns (2) } ,           -- by alignments given below
    aligns Seq-align OPTIONAL }

Num-real ::= SEQUENCE {          -- mapping to floating point system
    a REAL ,                     -- from an integer system used by Bioseq
    b REAL ,                     -- position = (a * int_position) + b
    units VisibleString OPTIONAL }

Pubdesc ::= SEQUENCE {              -- how sequence presented in pub
    pub Pub-equiv ,                 -- the citation(s)
    name VisibleString OPTIONAL ,   -- name used in paper
    fig VisibleString OPTIONAL ,    -- figure in paper
    num Numbering OPTIONAL ,        -- numbering from paper
    numexc BOOLEAN OPTIONAL ,       -- numbering problem with paper
    poly-a BOOLEAN OPTIONAL ,       -- poly A tail indicated in figure?
    maploc VisibleString OPTIONAL , -- map location reported in paper
    seq-raw StringStore OPTIONAL ,  -- original sequence from paper
    align-group INTEGER OPTIONAL ,  -- this seq aligned with others in paper
    comment VisibleString OPTIONAL, -- any comment on this pub in context
	reftype INTEGER {           -- type of reference in a GenBank record
		seq (0) ,               -- refers to sequence
		sites (1) ,             -- refers to unspecified features
		feats (2) ,             -- refers to specified features
		no-target (3) }         -- nothing specified (EMBL)
		DEFAULT seq }

Heterogen ::= VisibleString       -- cofactor, prosthetic group, inhibitor, etc

--*** Instances of sequences *******************************
--*

Seq-inst ::= SEQUENCE {            -- the sequence data itself
    repr ENUMERATED {              -- representation class
        not-set (0) ,              -- empty
        virtual (1) ,              -- no seq data
        raw (2) ,                  -- continuous sequence
        seg (3) ,                  -- segmented sequence
        const (4) ,                -- constructed sequence
        ref (5) ,                  -- reference to another sequence
        consen (6) ,               -- consensus sequence or pattern
        map (7) ,                  -- ordered map of any kind
        delta (8) ,              -- sequence made by changes (delta) to others
        other (255) } ,
    mol ENUMERATED {               -- molecule class in living organism
        not-set (0) ,              --   > cdna = rna
        dna (1) ,
        rna (2) ,
        aa (3) ,
        na (4) ,                   -- just a nucleic acid
        other (255) } ,
    length INTEGER OPTIONAL ,      -- length of sequence in residues
    fuzz Int-fuzz OPTIONAL ,       -- length uncertainty
    topology ENUMERATED {          -- topology of molecule
        not-set (0) ,
        linear (1) ,
        circular (2) ,
        tandem (3) ,               -- some part of tandem repeat
        other (255) } DEFAULT linear ,
    strand ENUMERATED {            -- strandedness in living organism
        not-set (0) ,
        ss (1) ,                   -- single strand
        ds (2) ,                   -- double strand
        mixed (3) ,
        other (255) } OPTIONAL ,   -- default ds for DNA, ss for RNA, pept
    seq-data Seq-data OPTIONAL ,   -- the sequence
    ext Seq-ext OPTIONAL ,         -- extensions for special types
    hist Seq-hist OPTIONAL }       -- sequence history

--*** Sequence Extensions **********************************
--*  for representing more complex types
--*  const type uses Seq-hist.assembly

Seq-ext ::= CHOICE {
    seg Seg-ext ,        -- segmented sequences
    ref Ref-ext ,        -- hot link to another sequence (a view)
    map Map-ext ,        -- ordered map of markers
    delta Delta-ext }

Seg-ext ::= SEQUENCE OF Seq-loc

Ref-ext ::= Seq-loc

Map-ext ::= SEQUENCE OF Seq-feat

Delta-ext ::= SEQUENCE OF Delta-seq

Delta-seq ::= CHOICE {
    loc Seq-loc ,       -- point to a sequence
    literal Seq-literal }   -- a piece of sequence

Seq-literal ::= SEQUENCE {
    length INTEGER ,         -- must give a length in residues
    fuzz Int-fuzz OPTIONAL , -- could be unsure
    seq-data Seq-data OPTIONAL } -- may have the data

--*** Sequence History Record ***********************************
--** assembly = records how seq was assembled from others
--** replaces = records sequences made obsolete by this one
--** replaced-by = this seq is made obsolete by another(s)

Seq-hist ::= SEQUENCE {
    assembly SET OF Seq-align OPTIONAL ,-- how was this assembled?
    replaces Seq-hist-rec OPTIONAL ,    -- seq makes these seqs obsolete
    replaced-by Seq-hist-rec OPTIONAL , -- these seqs make this one obsolete
    deleted CHOICE {
        bool BOOLEAN ,
        date Date } OPTIONAL }

Seq-hist-rec ::= SEQUENCE {
    date Date OPTIONAL ,
    ids SET OF Seq-id }
    
--*** Various internal sequence representations ************
--*      all are controlled, fixed length forms

Seq-data ::= CHOICE {              -- sequence representations
    iupacna IUPACna ,              -- IUPAC 1 letter nuc acid code
    iupacaa IUPACaa ,              -- IUPAC 1 letter amino acid code
    ncbi2na NCBI2na ,              -- 2 bit nucleic acid code
    ncbi4na NCBI4na ,              -- 4 bit nucleic acid code
    ncbi8na NCBI8na ,              -- 8 bit extended nucleic acid code
    ncbipna NCBIpna ,              -- nucleic acid probabilities
    ncbi8aa NCBI8aa ,              -- 8 bit extended amino acid codes
    ncbieaa NCBIeaa ,              -- extended ASCII 1 letter aa codes
    ncbipaa NCBIpaa ,              -- amino acid probabilities
    ncbistdaa NCBIstdaa }          -- consecutive codes for std aas


IUPACna ::= StringStore       -- IUPAC 1 letter codes, no spaces
IUPACaa ::= StringStore       -- IUPAC 1 letter codes, no spaces
NCBI2na ::= OCTET STRING      -- 00=A, 01=C, 10=G, 11=T
NCBI4na ::= OCTET STRING      -- 1 bit each for agct
                              -- 0001=A, 0010=C, 0100=G, 1000=T/U
                              -- 0101=Purine, 1010=Pyrimidine, etc
NCBI8na ::= OCTET STRING      -- for modified nucleic acids
NCBIpna ::= OCTET STRING      -- 5 octets/base, prob for a,c,g,t,n
                              -- probabilities are coded 0-255 = 0.0-1.0
NCBI8aa ::= OCTET STRING      -- for modified amino acids
NCBIeaa ::= StringStore       -- ASCII extended 1 letter aa codes
                              -- IUPAC codes + U=selenocysteine
NCBIpaa ::= OCTET STRING      -- 25 octets/aa, prob for IUPAC aas in order:
                              -- A-Y,B,Z,X,(ter),anything
                              -- probabilities are coded 0-255 = 0.0-1.0
NCBIstdaa ::= OCTET STRING    -- codes 0-25, 1 per byte

--*** Sequence Annotation *************************************
--*

Annot-id ::= CHOICE {
    local Object-id ,
    ncbi INTEGER ,
    general Dbtag }
    
Annot-descr ::= SET OF Annotdesc

Annotdesc ::= CHOICE {
    name VisibleString ,         -- a short name for this collection
    title VisibleString ,        -- a title for this collection
    comment VisibleString ,      -- a more extensive comment
    pub Pubdesc ,                -- a reference to the publication
    user User-object ,           -- user defined object
    create-date Date ,           -- date entry first created/released
    update-date Date ,           -- date of last update
    src Seq-id ,                 -- source sequence from which annot came
    align Align-def,             -- definition of the SeqAligns
    region Seq-loc }             -- all contents cover this region

Align-def ::= SEQUENCE {
    align-type INTEGER {         -- class of align Seq-annot
      ref (1) ,                  -- set of alignments to the same sequence
      alt (2) ,                  -- set of alternate alignments of the same seqs
      blocks (3) ,               -- set of aligned blocks in the same seqs
      other (255) } ,
    ids SET OF Seq-id OPTIONAL } -- used for the one ref seqid for now

Seq-annot ::= SEQUENCE {
    id SET OF Annot-id OPTIONAL ,
    db INTEGER {                 -- source of annotation
        genbank (1) ,
        embl (2) ,
        ddbj (3) ,
        pir  (4) ,
        sp   (5) ,
        bbone (6) ,
        pdb   (7) ,
        other (255) } OPTIONAL ,
    name VisibleString OPTIONAL ,-- source if "other" above
    desc Annot-descr OPTIONAL ,  -- used only for stand alone Seq-annots
    data CHOICE {
        ftable SET OF Seq-feat ,
        align SET OF Seq-align ,
        graph SET OF Seq-graph ,
        ids SET OF Seq-id ,        -- used for communication between tools
        locs SET OF Seq-loc } }    -- used for communication between tools

END