From pattern to causality: using linear discriminant analysis and Bayesian network on microarray data of breast cancers

In this paper, we aim at using genetic algorithms for gene selection and propose silhouette statistics as a discriminant function to classify breast cancers on microarray data for pattern discovery. In order to see the causality among these genes, we use the Bayesian method to construct a probability network for the pattern discovered. Consequently, we found a set of genes that is effective to discriminate breast cancer subtypes and present their probability dependencies to construct a diagnostic system. PRIB 2008 proceedings found at: http://dx.doi.org/10.1007/978-3-540-88436-1 Contributors: Monash University. Faculty of Information Technology. Gippsland School of Information Technology ; Chetty, Madhu ; Ahmad, Shandar ; Ngom, Alioune ; Teng, Shyh Wei ; Third IAPR International Conference on Pattern Recognition in Bioinformatics (PRIB) (3rd : 2008 : Melbourne, Australia) ; Coverage: Rights: Copyright by Third IAPR International Conference on Pattern Recognition in Bioinformatics. All rights reserved.