An information theoretic approach for the discovery of irregular and repetitive patterns in genomic data.
Willard DavisAnanth KalyanaramanDiane J. CookPublished in: CIBCB (2008)
Keyphrases
- genomic data
- repetitive patterns
- high throughput
- biological data
- repetitive structures
- protein protein interactions
- gene expression data
- salient features
- image patches
- experimental conditions
- gene ontology
- microarray
- knowledge discovery
- gene expression
- data integration
- gene expression profiles
- databases
- feature selection
- multiscale
- training set
- information theoretic
- data mining
- nearest neighbor