seqfeat.asn

ncbi源码

--
-- ===========================================================================
-- PRODUCTION $Log: seqfeat.asn,v $
-- PRODUCTION Revision 1000.0  2003/10/29 21:33:45  gouriano
-- PRODUCTION PRODUCTION: IMPORTED [ORIGINAL] Dev-tree R6.9
-- PRODUCTION
-- ===========================================================================
--

--$Revision: 1000.0 $
--**********************************************************************
--
--  NCBI Sequence Feature elements
--  by James Ostell, 1990
--  Version 3.0 - June 1994
--
--**********************************************************************

NCBI-Seqfeat DEFINITIONS ::=
BEGIN

EXPORTS Seq-feat, Feat-id, Genetic-code;

IMPORTS Gene-ref FROM NCBI-Gene
        Prot-ref FROM NCBI-Protein
        Org-ref FROM NCBI-Organism
        BioSource FROM NCBI-BioSource
        RNA-ref FROM NCBI-RNA
        Seq-loc, Giimport-id FROM NCBI-Seqloc
        Pubdesc, Numbering, Heterogen FROM NCBI-Sequence
        Rsite-ref FROM NCBI-Rsite
        Txinit FROM NCBI-TxInit
        Pub-set FROM NCBI-Pub
        Object-id, Dbtag, User-object FROM NCBI-General;

--*** Feature identifiers ********************************
--*

Feat-id ::= CHOICE {
    gibb INTEGER ,            -- geninfo backbone
    giim Giimport-id ,        -- geninfo import
    local Object-id ,         -- for local software use
    general Dbtag }           -- for use by various databases

--*** Seq-feat *******************************************
--*  sequence feature generalization

Seq-feat ::= SEQUENCE {
    id Feat-id OPTIONAL ,
    data SeqFeatData ,           -- the specific data
    partial BOOLEAN OPTIONAL ,    -- incomplete in some way?
    except BOOLEAN OPTIONAL ,     -- something funny about this?
    comment VisibleString OPTIONAL ,
    product Seq-loc OPTIONAL ,    -- product of process
    location Seq-loc ,            -- feature made from
    qual SEQUENCE OF Gb-qual OPTIONAL ,  -- qualifiers
    title VisibleString OPTIONAL ,   -- for user defined label
    ext User-object OPTIONAL ,    -- user defined structure extension
    cit Pub-set OPTIONAL ,        -- citations for this feature
    exp-ev ENUMERATED {           -- evidence for existence of feature
        experimental (1) ,        -- any reasonable experimental check
        not-experimental (2) } OPTIONAL , -- similarity, pattern, etc
    xref SET OF SeqFeatXref OPTIONAL ,   -- cite other relevant features
    dbxref SET OF Dbtag OPTIONAL ,  -- support for xref to other databases
    pseudo BOOLEAN OPTIONAL ,     -- annotated on pseudogene?
    except-text VisibleString OPTIONAL } -- explain if except=TRUE

SeqFeatData ::= CHOICE {
    gene Gene-ref ,
    org Org-ref ,
    cdregion Cdregion ,
    prot Prot-ref ,
    rna RNA-ref ,
    pub Pubdesc ,              -- publication applies to this seq 
    seq Seq-loc ,              -- to annotate origin from another seq
    imp Imp-feat ,
    region VisibleString,      -- named region (globin locus)
    comment NULL ,             -- just a comment
    bond ENUMERATED {
        disulfide (1) ,
        thiolester (2) ,
        xlink (3) ,
        thioether (4) ,
        other (255) } ,
    site ENUMERATED {
        active (1) ,
        binding (2) ,
        cleavage (3) ,
        inhibit (4) ,
        modified (5),
        glycosylation (6) ,
        myristoylation (7) ,
        mutagenized (8) ,
        metal-binding (9) ,
        phosphorylation (10) ,
        acetylation (11) ,
        amidation (12) ,
        methylation (13) ,
        hydroxylation (14) ,
        sulfatation (15) ,
        oxidative-deamination (16) ,
        pyrrolidone-carboxylic-acid (17) ,
        gamma-carboxyglutamic-acid (18) ,
        blocked (19) ,
        lipid-binding (20) ,
        np-binding (21) ,
        dna-binding (22) ,
        signal-peptide (23) ,
        transit-peptide (24) ,
        transmembrane-region (25) ,
        other (255) } ,
    rsite Rsite-ref ,       -- restriction site  (for maps really)
    user User-object ,      -- user defined structure
    txinit Txinit ,         -- transcription initiation
    num Numbering ,         -- a numbering system
    psec-str ENUMERATED {   -- protein secondary structure
        helix (1) ,         -- any helix
        sheet (2) ,         -- beta sheet
        turn  (3) } ,       -- beta or gamma turn
    non-std-residue VisibleString ,  -- non-standard residue here in seq
    het Heterogen ,         -- cofactor, prosthetic grp, etc, bound to seq
    biosrc BioSource }

SeqFeatXref ::= SEQUENCE {       -- both optional because can have one or both
    id Feat-id OPTIONAL ,        -- the feature copied
    data SeqFeatData OPTIONAL }  -- the specific data
    
--*** CdRegion ***********************************************
--*
--*  Instructions to translate from a nucleic acid to a peptide
--*    conflict means it's supposed to translate but doesn't
--*


Cdregion ::= SEQUENCE {
    orf BOOLEAN OPTIONAL ,             -- just an ORF ?
    frame ENUMERATED {
        not-set (0) ,                  -- not set, code uses one
        one (1) ,
        two (2) ,
        three (3) } DEFAULT not-set ,      -- reading frame
    conflict BOOLEAN OPTIONAL ,        -- conflict
    gaps INTEGER OPTIONAL ,            -- number of gaps on conflict/except
    mismatch INTEGER OPTIONAL ,        -- number of mismatches on above
    code Genetic-code OPTIONAL ,       -- genetic code used
    code-break SEQUENCE OF Code-break OPTIONAL ,   -- individual exceptions
    stops INTEGER OPTIONAL }           -- number of stop codons on above

                    -- each code is 64 cells long, in the order where
                    -- T=0,C=1,A=2,G=3, TTT=0, TTC=1, TCA=4, etc
                    -- NOTE: this order does NOT correspond to a Seq-data
                    -- encoding.  It is "natural" to codon usage instead.
                    -- the value in each cell is the AA coded for
                    -- start= AA coded only if first in peptide
                    --   in start array, if codon is not a legitimate start
                    --   codon, that cell will have the "gap" symbol for
                    --   that alphabet.  Otherwise it will have the AA
                    --   encoded when that codon is used at the start.

Genetic-code ::= SET OF CHOICE {
    name VisibleString ,               -- name of a code
    id INTEGER ,                       -- id in dbase
    ncbieaa VisibleString ,            -- indexed to IUPAC extended
    ncbi8aa OCTET STRING ,             -- indexed to NCBI8aa
    ncbistdaa OCTET STRING ,           -- indexed to NCBIstdaa
    sncbieaa VisibleString ,            -- start, indexed to IUPAC extended
    sncbi8aa OCTET STRING ,             -- start, indexed to NCBI8aa
    sncbistdaa OCTET STRING }           -- start, indexed to NCBIstdaa

Code-break ::= SEQUENCE {              -- specific codon exceptions
    loc Seq-loc ,                      -- location of exception
    aa CHOICE {                        -- the amino acid
        ncbieaa INTEGER ,              -- ASCII value of NCBIeaa code
        ncbi8aa INTEGER ,              -- NCBI8aa code
        ncbistdaa INTEGER } }           -- NCBIstdaa code

Genetic-code-table ::= SET OF Genetic-code     -- table of genetic codes

--*** Import ***********************************************
--*
--*  Features imported from other databases
--*

Imp-feat ::= SEQUENCE {
    key VisibleString ,
    loc VisibleString OPTIONAL ,         -- original location string
    descr VisibleString OPTIONAL }       -- text description

Gb-qual ::= SEQUENCE {
    qual VisibleString ,
    val VisibleString }

END 

--**********************************************************************
--
--  NCBI Restriction Sites
--  by James Ostell, 1990
--  version 0.8
--
--**********************************************************************

NCBI-Rsite DEFINITIONS ::=
BEGIN

EXPORTS Rsite-ref;

IMPORTS Dbtag FROM NCBI-General;

Rsite-ref ::= CHOICE {
    str VisibleString ,     -- may be unparsable
    db  Dbtag }             -- pointer to a restriction site database

END

--**********************************************************************
--
--  NCBI RNAs
--  by James Ostell, 1990
--  version 0.8
--
--**********************************************************************

NCBI-RNA DEFINITIONS ::=
BEGIN

EXPORTS RNA-ref, Trna-ext;

IMPORTS Seq-loc FROM NCBI-Seqloc;

--*** rnas ***********************************************
--*
--*  various rnas
--*
                         -- minimal RNA sequence
RNA-ref ::= SEQUENCE {
    type ENUMERATED {            -- type of RNA feature
        unknown (0) ,
        premsg (1) ,
        mRNA (2) ,
        tRNA (3) ,
        rRNA (4) ,
        snRNA (5) ,
        scRNA (6) ,
        snoRNA (7) ,
        other (255) } ,
    pseudo BOOLEAN OPTIONAL ,  
    ext CHOICE {
        name VisibleString ,        -- for naming "other" type
        tRNA Trna-ext } OPTIONAL }  -- for tRNAs

Trna-ext ::= SEQUENCE {                 -- tRNA feature extensions
    aa CHOICE {                         -- aa this carries
        iupacaa INTEGER ,
        ncbieaa INTEGER ,
        ncbi8aa INTEGER ,
        ncbistdaa INTEGER } OPTIONAL ,
    codon SET OF INTEGER OPTIONAL ,     -- codon(s) as in Genetic-code
	anticodon Seq-loc OPTIONAL }        -- location of anticodon

END

--**********************************************************************
--
--  NCBI Genes
--  by James Ostell, 1990
--  version 0.8
--
--**********************************************************************

NCBI-Gene DEFINITIONS ::=
BEGIN

EXPORTS Gene-ref;

IMPORTS Dbtag FROM NCBI-General;

--*** Gene ***********************************************
--*
--*  reference to a gene
--*

Gene-ref ::= SEQUENCE {
    locus VisibleString OPTIONAL ,        -- Official gene symbol
    allele VisibleString OPTIONAL ,       -- Official allele designation
    desc VisibleString OPTIONAL ,         -- descriptive name
    maploc VisibleString OPTIONAL ,       -- descriptive map location
    pseudo BOOLEAN DEFAULT FALSE ,        -- pseudogene
    db SET OF Dbtag OPTIONAL ,            -- ids in other dbases
    syn SET OF VisibleString OPTIONAL ,   -- synonyms for locus
    locus-tag VisibleString OPTIONAL }    -- systematic gene name (e.g., MI0001, ORF0069)

END


--**********************************************************************
--
--  NCBI Organism
--  by James Ostell, 1994
--  version 3.0
--
--**********************************************************************

NCBI-Organism DEFINITIONS ::=
BEGIN

EXPORTS Org-ref;

IMPORTS Dbtag FROM NCBI-General;