GenMiner: Mining Informative Association Rules from Genomic Data

Abstract

GENMINER is a smart adaptation of closed itemsets based association rules extraction to genomic data. It takes advantage of the novel NORDI discretization method and of the CLOSE [27] algorithm to efficiently generate min- imal non-redundant association rules. GENMINER facili- tates the integration ofnumerous sources ofbiological in- formation such as gene expressions and annotations, and can tacitly integrate qualitative information on biological conditions (age, sex, etc.). We validated this approach ana- lyzing the microarray datasets used by Eisen et al. [10] with several sources ofbiological annotations. Extracted asso- ciations revealed significant co-annotatedand co-expressed gene patterns, showing important biological relationships between genes and their features. Several ofthese relation- ships are supported by recent biological literature.

Publication
IEEE International Conference on Bioinformatics and Biomedicine (BIBM'07)