Title: Granular Kernel Trees with parallel Genetic Algorithms for drug activity comparisons

Authors: Bo Jin, Yan-Qing Zhang, Binghe Wang

Addresses: Department of Computer Science, Georgia State University, Atlanta, GA 30302, USA. ' Department of Computer Science, Georgia State University, Atlanta, GA 30302, USA. ' Department of Chemistry and Center for Biotechnology and Drug Design, Georgia State University, Atlanta, GA 30302-4098, USA

Abstract: With the growing interests of biological data prediction and chemical data prediction, more powerful and flexible kernels need to be designed so that the prior knowledge and relationships within data can be expressed effectively in kernel functions. In this paper, Granular Kernel Trees (GKTs) are proposed and parallel Genetic Algorithms (GAs) are used to optimise the parameters of GKTs. In applications, SVMs with new kernel trees are employed for drug activity comparisons. The experimental results show that GKTs and evolutionary GKTs can achieve better performances than traditional RBF kernels in terms of prediction accuracy.

Keywords: kernel design; support vector machines; SVMs; granular kernel trees; GKTs; genetic algorithms; parallel GAs; drug activity comparisons; data mining; bioinformatics; prediction accuracy; biological data prediction; chemical data prediction.

DOI: 10.1504/IJDMB.2007.011613

International Journal of Data Mining and Bioinformatics, 2007 Vol.1 No.3, pp.270 - 285

Published online: 06 Dec 2006 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article