Normalization of gene expression data using support vector machine approach

Abstract

Normalization of gene expression data refers the process of minimizing non biological variation in measured probe intensity levels so that biological differences in gene expression can be appropriately detected. Several linear normalization within arrays approaches has already been proposed. Recently, use of non-linear methods has been gained quite attention. In this study, our objective is to formulate non-linear normalization methods using support vector regression (SVR) and support vector machine quantile regression (SVMQR) approaches, more easier way and, assess the consistency of these methods with respect to other standard normalization methods for further application in gene expression data. SVR and SVMQR normalization methods have been implemented and their performance have been evaluated with respect to other standard normalization methods namely, locally weighted scatter plot smoothing and Kernel regression. It has been found that the normalized data based on proposed methods are capable of producing minimum variances within replicate groups and also able to detect truly expressible significant genes with respect to above mentioned other normalized data