Table 1 An initial list of genomic "features" that will be the subjects of analysis by the system.
From: Automating Genomic Data Mining via a Sequence-based Matrix Format and Associative Rule Set
Features | Classification tree |
|---|---|
Gene | Entity |
Splice site | Entity, probabilistic |
Alu | Entity, probabilistic |
Enzyme cut site | Entity, set, categorical |
Post-translation Mod | Entity, set, categorical |
Protein Motif | Entity, set, categorical |
Promoter | Entity, set, categorical |
VNTR | Entity, set, categorical |
Exon | Entity, set, range |
Chromosome | Entity, set, range |
Cytoband | Entity, set, range |
CpG island | Property (sequence), window-based, binary |
G+C% Isochore | Property (sequence), window-based, range |
# of interactions | Property (gene), range |
Transcript variants | Property (gene), range |
Transcription level | Property (gene), range, conditional |
Gene Ontology | Property (gene), categorical, hierarchical |
Imprinted | Property (CpG Island), categorical (no/maternal/paternal) |
Polymorphic | Property (VNTR), range |