Mining association rule bases from integrated genomic data and annotations

Abstract : During the last decade, several clustering and association rule mining techniques have been applied to highlight groups of co-regulated genes in gene expression data. Nowadays, integrating these data and biological knowledge into a single framework has become a ma- jor challenge to improve the relevance of mined patterns and simplify their interpretation by biologists. GenMiner was developed for mining association rules from such integrated datasets. It combines a new normalized discretization method, called NorDi, and the JClose algorithm to extract condensed representations for association rules. Experimental results show that GenMiner requires less memory than Apriori based approaches and that it improves the relevance of extracted rules. Moreover, association rules obtained revealed significant co-annotated and co-expressed gene patterns showing important biological relationships supported by recent biological literature.
Type de document :
Communication dans un congrès
Sth International Conference on Computational Intelligence Methods for Bioinformatics and Biostatistics (CIBB'09), Oct 2009, Genova, Italy
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01154860
Contributeur : Claude Pasquier <>
Soumis le : lundi 25 mai 2015 - 08:28:18
Dernière modification le : mardi 26 mai 2015 - 01:04:20

Identifiants

  • HAL Id : hal-01154860, version 1

Collections

Citation

Claude Pasquier, Ricardo Martinez, Nicolas Pasquier. Mining association rule bases from integrated genomic data and annotations. Sth International Conference on Computational Intelligence Methods for Bioinformatics and Biostatistics (CIBB'09), Oct 2009, Genova, Italy. 〈hal-01154860〉

Partager

Métriques

Consultations de la notice

54