Artificial Immune System for Classification of Gene Expression Data

Shin Ando¹ and Hitoshi Iba²

¹Dept. of Electronics
School of Engineering
University of Tokyo
ando@miv.t.u-tokyo.ac.jp

²Dept. of Frontier Informatics
School of Frontier Science
University of Tokyo
iba@miv.t.u-tokyo.ac.jp

Abstract. DNA microarray experiments generate thousands of gene expression measurement simultaneously. Analyzing the difference of gene expression in cell and tissue samples is useful in diagnosis of disease. This paper presents an Artificial Immune System for classifying microarray-monitored data. The system evolutionarily selects important features and optimizes their weights to derive classification rules. This system was applied to two datasets of cancerous cells and tissues. The primary result found few classification rules which correctly classified all the test samples and gave some interesting implications for feature selection.

LNCS 2724, p. 1926 ff.

Full article in PDF

lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2003