GC-AssemblyUnit

Defined in file genome_collection.asn
C++ class: CGC_AssemblyUnit


GC-AssemblyUnit ::= SEQUENCE
{
    -- The identifier of this assembly
    -- Contains: GenColl internal id, GenColl accession.version,
    --            AGP id, UCSC name, Ensembl name
    -- Types of DbTags used:
    -- db "GenColl", tag id 
    -- db "GenColl", tag str 
    -- db "AGP", tag id 
    -- db "GenColl_Chain", tag id 
    -- "Ensembl_name" and "UCSC_name" will not appear in the Unit level since
    -- these organizations do not define assembly-units.
    id SET OF Dbtag,

    -- 'class' defines the semantics of how to interpret this item
    class INTEGER {
        --  units for haploid/diploid assemblies
        haploid-unit(1),
        -- this unit represents one or more alternate loci for a haploid
        -- assembly
        alt-loci(2),
        -- assembly-patch
        assembly-patch(3),
        -- stopper
        other(255)
    },

    -- descriptors live in a shared data block
    desc GC-AssemblyDesc,

    -- collections of molecules for this assembly
    mols SET OF GC-Replicon OPTIONAL,

    -- On primary assembly-unit: here will be the unplaced sequences
    -- On alt-loci: list of sequences aligned/unaligned to primary unit
    other-sequences SET OF GC-TaggedSequences  OPTIONAL,

    -- statistics
    -- "stats" field holds stats for all chromosomes combined:
    --     ordered/unordered scaffolds
    -- "unplaced-stats" holds stats for ChrUn which is omitted from "stats"
    stats GC-SequenceStats OPTIONAL,
    unplaced-stats SET OF GC-Scaf-stats OPTIONAL,
    unplaced-unlocalized-stats SET OF GC-Scaf-stats OPTIONAL

}