Using Voronoi Grid and SVM Linear Regression in Drug Discovery

Author

Ghaibeh, A.A. ; Sasaki, M. ; Chuman, H.

Author_Institution

Saila Syst. Inc., Tokyo

fYear

2006

fDate

28-29 Sept. 2006

Firstpage

1

Lastpage

6

Abstract

In this paper we propose a new method for generating an informative QSAR model (called VSVR-QSAR) using Voronoi grid and support vector machines regression. The procedure enables researchers to understand the physicochemical meaning of the steric and electrostatics measurements and the inclusion of those measurements as latent variables in the generated QSAR model. The procedure proved to be comparable or better than the classical QSAR, as well as conventional 3D-QSAR procedures

Keywords

chemical engineering computing; computational geometry; drugs; regression analysis; support vector machines; Voronoi grid; drug discovery; electrostatics measurement; linear regression; physicochemical; quantitative structure-activity relationship model; steric measurement; support vector machines; Biological system modeling; Databases; Drugs; Electrostatic measurements; Genetic algorithms; Lattices; Linear regression; Mesh generation; Process design; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence and Bioinformatics and Computational Biology, 2006. CIBCB '06. 2006 IEEE Symposium on

Conference_Location

Toronto, Ont.

Print_ISBN

1-4244-0623-4

Electronic_ISBN

1-4244-0624-2

Type

conf

DOI

10.1109/CIBCB.2006.331011

Filename

4133153