Go to the SVN repository for this file
Go to list of all specification files

--$Revision: 66445 $
--  NCBI Variation container
--  by Variation Working Group, 2011
--  The Variation type describes a sequence change at location(s),
--  or a hierarchical combination thereof.
--  Related location-centric type is SeqFeatData.Variation-ref

NCBI-VariationPackage DEFINITIONS ::=

EXPORTS Variation, VariantPlacement;

IMPORTS Int-fuzz, Dbtag, User-object, Object-id FROM NCBI-General
        Population-data, Phenotype, Variation-inst, VariantProperties FROM NCBI-Variation
        Seq-loc FROM NCBI-Seqloc
        SubSource FROM NCBI-BioSource
        Seq-literal, Bioseq FROM NCBI-Sequence
        Pub-set FROM NCBI-Pub;

VariationException ::= SEQUENCE
    code INTEGER {
        hgvs-parsing (1), --invalid hgvs expression
        hgvs-exon-boundary (2), --anchor position in an intronic HGVS expression is not at an exon boundary
        inconsistent-consequence (3), --consequence protein variation attached to precursor variation's consequence
                                      --could not be derived from it.
        inconsistent-asserted-allele (4), --asserted allele is inconsistent with the reference
        no-mapping (5),      --could not remap
        partial-mapping (6), --mapped location is shorter than the query
        split-mapping (7),   --a source interval maps to multiple non-abutting intervals.
        mismatches-in-mapping (8), --the source sequence differs from sequence at mapped loc
        inconsistent-asserted-moltype (9), --asserted mol-type is inconsistent with seq-id (e.g. NM_12345.6:g.)
        bioseq-state (10),
        ambiguous-sequence (11),
        ref-same-as-variant (12), --reference sequence at the location is same as variant sequence in the variation
        seqfetch-too-long (13), --can't fetch sequence because location is longer than specified threshold
        seqfetch-intronic (14), --can't fetch sequence for an intronic (anchor+offset)-based location
        seqfetch-invalid (15),   --can't fetch sequence because location is invalid (e.g. extends past the end)
        no-mapping-from-newer-version (16), --have mapping from older version of a sequence, but not from newer
        source-location-overhang (17), --The source location overhangs the alignment by at least 5kb (VAR-1307)
        hgvs-exon-boundary-induced (18)  --Similar to (2), except induced by 5'/3'-terminal or an exon extension (VAR-1309)
    message VisibleString

VariantPlacement ::= SEQUENCE
    -- actual concrete placement we are considering
    loc Seq-loc,

    mol INTEGER {
        genomic(1),      --"g." coordinates in HGVS
        cdna(2),         --"c." coordinates in HGVS
        rna(3),          --"n." coordinates in HGVS
        protein(4),      --"p." coordinates in HGVS
        mitochondrion(5) --"mt." coordinates in HGVS

    -- location flags
    placement-method INTEGER {

    -- location refinements, describing offsets into introns from product coordinates.
    -- Biological semantics: start-offset/stop-offset apply to bio-start/bio-stop respectively.
    -- positive = downstream; negative = upstream.
    start-offset INTEGER OPTIONAL,
    start-offset-fuzz Int-fuzz OPTIONAL,
    stop-offset INTEGER OPTIONAL,
    stop-offset-fuzz Int-fuzz OPTIONAL,

    -- 0-based position of bio-start relative to containing codon

    -- for situations in which a raw location isn't sufficient
    seq Seq-literal OPTIONAL, 

    -- reference to the assembly (GenColl ID) for this location
    assembly Dbtag OPTIONAL,

    hgvs-name VisibleString OPTIONAL,

    -- the reference location for this variant
    comment VisibleString OPTIONAL,

    exceptions SET OF VariationException OPTIONAL,

    dbxrefs SET OF Dbtag OPTIONAL, --e.g. rs#, that are placement-specific

    ext SET OF User-object OPTIONAL, --for process-specific placement tags/labels

    gene-location INTEGER OPTIONAL, --Same semantics as VariantProperties.gene-location, except placement-specific

    id Object-id OPTIONAL,
    parent-id Object-id OPTIONAL, --id of the placement from which this one was derived

    so-terms SEQUENCE OF INTEGER OPTIONAL --Sequence Ontology terms for this placement

VariationMethod ::= SEQUENCE
    -- sequencing / acuisition method
    method SET OF INTEGER {
        unknown             (0),
        bac-acgh            (1),
        computational       (2),
        curated             (3),
        digital-array       (4),
        expression-array    (5),
        fish                (6),
        flanking-sequence   (7),
        maph                (8),
        mcd-analysis        (9),
        mlpa                (10),
        oea-assembly        (11),
        oligo-acgh          (12),
        paired-end          (13),
        pcr                 (14),
        qpcr                (15),
        read-depth          (16),
        roma                (17),
        rt-pcr              (18),
        sage                (19),
        sequence-alignment  (20),
        sequencing          (21),
        snp-array           (22),
        snp-genoytyping     (23),
        southern            (24),
        western             (25),
        optical-mapping     (26),

        other               (255)

    -- if sequence-based validation methods are used,
    -- what reference sequence location validated the presence of this?
    reference-location Seq-loc OPTIONAL

Variation ::= SEQUENCE
    -- ids (i.e., SNP rsid / ssid, dbVar nsv/nssv)
    -- expected values include 'dbSNP|rs12334', 'dbSNP|ss12345', 'dbVar|nsv1'
    -- we relate three kinds of IDs here:
    --  - our current object's id
    --  - the id of this object's parent, if it exists
    --  - the sample ID that this item originates from
    id        Dbtag OPTIONAL,
    parent-id Dbtag OPTIONAL,
    sample-id SET OF Object-id OPTIONAL,
    other-ids SET OF Dbtag OPTIONAL,

    -- names and synonyms
    -- some variants have well-known canonical names and possible accepted
    -- synonyms
    name VisibleString OPTIONAL,
    synonyms SET OF VisibleString OPTIONAL,

    -- tag for comment and descriptions
    description VisibleString OPTIONAL,

    -- where this beast is seen
    -- note that this is a set of locations, and there are no restrictions to
    -- the contents to this set. 
    placements SEQUENCE OF VariantPlacement OPTIONAL,

    -- phenotype
    phenotype SET OF Phenotype OPTIONAL,

    -- sequencing / acuisition method
    method VariationMethod OPTIONAL,

    -- Note about SNP representation and pretinent fields: allele-frequency,
    -- population, quality-codes:
    -- The case of multiple alleles for a SNP would be described by
    -- parent-feature of type Variation-set.diff-alleles, where the child
    -- features of type Variation-inst, all at the same location, would
    -- describe individual alleles.

    -- population data
    population-data SET OF Population-data OPTIONAL,

    -- variant properties bit fields
    variant-prop VariantProperties OPTIONAL,

    -- publication support; same type as in seq-feat
    pub Pub-set OPTIONAL,

    -- References to external 
    clinical-test Dbtag OPTIONAL,

    data CHOICE {
        unknown NULL,
        note    VisibleString, --free-form
        uniparental-disomy NULL,

        -- actual sequence-edit at feat.location
        instance        Variation-inst,

        -- Set of related Variations.
        -- Location of the set equals to the union of member locations
        set SEQUENCE {
            type INTEGER {
                unknown     (0),
                compound    (1), -- complex change at the same location on the
                                 -- same molecule
                products    (2), -- different products arising from the same
                                 -- variation in a precursor, e.g. r.[13g>a,
                                 -- 13_88del]
                haplotype   (3), -- changes on the same allele, e.g
                                 -- r.[13g>a;15u>c]
                genotype    (4), -- changes on different alleles in the same
                                 -- genotype, e.g. g.[476C>T]+[476C>T]
                mosaic      (5), -- different genotypes in the same individual
                individual  (6), -- same organism; allele relationship unknown,
                                 -- e.g. g.[476C>T(+)183G>C]
                population  (7), -- population
                alleles     (8), -- set represents a set of observed alleles
                package     (9), -- set represents a package of observations at
                                 -- a given location, generally containing
                                 -- asserted + reference
                chimeric    (10), -- e.g. c.[1C>T//2G>T]
                other       (255)
            variations SET OF Variation,
            name  VisibleString OPTIONAL

        -- variant is a complex and undescribed change at the location
        -- This type of variant is known to occur in dbVar submissions
        complex NULL,

        seq Bioseq -- Sequnece as it exists post-alteration

    consequence SET OF CHOICE {
        unknown     NULL,
        splicing    NULL, --some effect on splicing
        note        VisibleString,  --freeform

        -- Describe resulting variation in the product, e.g. missense,
        -- nonsense, silent, neutral, etc in a protein, that arises from
        -- THIS variation.
        variation   Variation,

        loss-of-heterozygosity SEQUENCE {
            -- In germline comparison, it will be reference genome assembly
            -- (default) or reference/normal population. In somatic mutation,
            -- it will be a name of the normal tissue.
            reference VisibleString OPTIONAL,

            -- Name of the testing subject type or the testing tissue.
            test VisibleString OPTIONAL

    -- Frameshift-related info. Applies only to protein-level variations.
    -- see
    frameshift SEQUENCE {
       phase INTEGER OPTIONAL,
       x-length INTEGER OPTIONAL

    -- Additional undescribed extensions
    ext             SET OF User-object OPTIONAL,

    somatic-origin SET OF SEQUENCE {
        -- description of the somatic origin itself
        source SubSource OPTIONAL,
        -- condition related to this origin's type
        condition SEQUENCE {
            description VisibleString OPTIONAL,
            -- reference to BioTerm / other descriptive database
            object-id SET OF Dbtag OPTIONAL
        } OPTIONAL

    exceptions SET OF VariationException OPTIONAL,