Variation

Defined in file variation.asn
C++ class: CVariation


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
        }
    } OPTIONAL,

    -- Frameshift-related info. Applies only to protein-level variations.
    -- see http://www.hgvs.org/mutnomen/recs-prot.html
    frameshift SEQUENCE {
       phase INTEGER OPTIONAL,
       x-length INTEGER OPTIONAL
    } 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
    } OPTIONAL,

    exceptions SET OF VariationException OPTIONAL,

    so-terms SET OF INTEGER OPTIONAL
}