all.asn

ncbi源码

    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 corresspond 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) ,
        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

END


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

NCBI-Organism DEFINITIONS ::=
BEGIN

EXPORTS Org-ref;

IMPORTS Dbtag FROM NCBI-General;

--*** Org-ref ***********************************************
--*
--*  Reference to an organism
--*     defines only the organism.. lower levels of detail for biological
--*     molecules are provided by the Source object
--*

Org-ref ::= SEQUENCE {
    taxname VisibleString OPTIONAL ,   -- preferred formal name
    common VisibleString OPTIONAL ,    -- common name
    mod SET OF VisibleString OPTIONAL , -- unstructured modifiers
    db SET OF Dbtag OPTIONAL ,         -- ids in taxonomic or culture dbases
    syn SET OF VisibleString OPTIONAL ,  -- synonyms for taxname or common
    orgname OrgName OPTIONAL }
    

OrgName ::= SEQUENCE {
    name CHOICE {
        binomial BinomialOrgName ,         -- genus/species type name
        virus VisibleString ,              -- virus names are different
        hybrid MultiOrgName ,              -- hybrid between organisms
        namedhybrid BinomialOrgName ,      -- some hybrids have genus x species name
        partial PartialOrgName } OPTIONAL , -- when genus not known
    attrib VisibleString OPTIONAL ,        -- attribution of name
    mod SEQUENCE OF OrgMod OPTIONAL ,
    lineage VisibleString OPTIONAL ,       -- lineage with semicolon separators
    gcode INTEGER OPTIONAL ,               -- genetic code (see CdRegion)
    mgcode INTEGER OPTIONAL ,              -- mitochondrial genetic code
	div VisibleString OPTIONAL }           -- GenBank division code
    

OrgMod ::= SEQUENCE {
    subtype INTEGER {
        strain (2) ,
        substrain (3) ,
        type (4) ,
        subtype (5) ,
        variety (6) ,
        serotype (7) ,
        serogroup (8) ,
        serovar (9) ,
        cultivar (10) ,
        pathovar (11) ,
        chemovar (12) ,
        biovar (13) ,
        biotype (14) ,
        group (15) ,
        subgroup (16) ,
        isolate (17) ,
        common (18) ,
        acronym (19) ,
        dosage (20) ,		-- chromosome dosage of hybrid
        nat-host (21) ,		-- natural host of this specimen
	sub-species (22) ,
        specimen-voucher (23) ,
	authority (24) ,
	forma (25) ,
	forma-specialis (26) ,
	ecotype (27) ,
	synonym (28) ,
	anamorph (29) ,
	teleomorph (30) ,
	breed (31) ,
	old-lineage (253) ,
        old-name (254) ,
        other (255) } ,         -- ASN5: old-name (254) will be added to next spec
    subname VisibleString ,
    attrib VisibleString OPTIONAL }  -- attribution/source of name

BinomialOrgName ::= SEQUENCE {
    genus VisibleString ,               -- required
    species VisibleString OPTIONAL ,    -- species required if subspecies used
    subspecies VisibleString OPTIONAL }

MultiOrgName ::= SEQUENCE OF OrgName   -- the first will be used to assign division

PartialOrgName ::= SEQUENCE OF TaxElement  -- when we don't know the genus

TaxElement ::= SEQUENCE {
    fixed-level INTEGER {
       other (0) ,                     -- level must be set in string
       family (1) ,
       order (2) ,
       class (3) } ,
    level VisibleString OPTIONAL ,
    name VisibleString }

END


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

NCBI-BioSource DEFINITIONS ::=
BEGIN

EXPORTS BioSource;

IMPORTS Org-ref FROM NCBI-Organism;

--********************************************************************
--
-- BioSource gives the source of the biological material
--   for sequences
--
--********************************************************************

BioSource ::= SEQUENCE {
    genome INTEGER {		 -- biological context
        unknown (0) ,
        genomic (1) ,
        chloroplast (2) ,
        chromoplast (3) ,
        kinetoplast (4) ,
        mitochondrion (5) ,
        plastid (6) ,
        macronuclear (7) ,
        extrachrom (8) ,
        plasmid (9) ,
        transposon (10) ,
        insertion-seq (11) ,
	cyanelle (12) ,
	proviral (13) ,
	virion (14) ,
	nucleomorph (15) ,
	apicoplast (16) ,
	leucoplast (17) ,
	proplastid (18) ,
	endogenous-virus (19)
	 } DEFAULT unknown ,
                                       -- 4 more genome values coming
                                       -- nucleomorph (15)
                                       -- apicoplast (16)
                                       -- leucoplast (17)
                                       -- proplastid (18)
    origin INTEGER {
      unknown (0) ,
      natural (1) ,                    -- normal biological entity
      natmut (2) ,                     -- naturally occurring mutant
      mut (3) ,                        -- artificially mutagenized
      artificial (4) ,                 -- artificially engineered
      synthetic (5) ,                  -- purely synthetic
      other (255) } DEFAULT unknown , 
    org Org-ref ,
    subtype SEQUENCE OF SubSource OPTIONAL ,
    is-focus NULL OPTIONAL }   -- to distinguish biological focus

SubSource ::= SEQUENCE {