Introduction to Classification in Microarray Experiments

Abstract

Deoxyribonucleic acid (DNA) microarrays are part of a new and promising class of biotechnologies that allow the simultaneous monitoring of expression levels in cells for thousands of genes. Microarray experiments are increasingly being performed in biological and medical research to address a wide range of problems. In cancer research, microarrays are used to study the molecular variations among tumors, with the aim of developing better diagnosis and treatment strategies for the disease. Classification is an important question in microarray experiments, for purposes of classifying biological samples and predicting clinical or other outcomes using gene expression data. Although classification is by no means a new subject in the statistical literature, the large and complex multivariate datasets generated by microarray experiments raise new methodological and computational challenges. This chapter addresses statistical issues arising in the classification of biological samples using gene expression data from DNA microarray experiments. It discusses the statistical foundations of classification and provides an overview of different classifiers, including linear discriminant analysis, nearest neighbor classifiers, classification trees, and support vector machines. Applications of resampling methods, such as bagging and boosting, for improving classifier accuracy are described. The important questions of feature selection and classifier performance assessment are also addressed. The performance of five main types of classifiers is examined using gene expression data from recently published cancer microarray studies of breast and brain tumors.