An Intentional Kernel Function for RNA Classification

Abstract

This paper presents a kernel function class K _RNA which is based on the concept of the intentional kernel (Doi et al., 2006) as opposed to that of the convolution kernel (Haussler, 1999). A kernel function in K _RNA computes the similarity between two RNA sequences from the viewpoint of secondary structures. As an instance of K _RNA , we give the definition and the algorithm of $K_{RNA}^{N}$ which takes a pair of RNA sequences as its inputs, and facilitates Support Vector Machine (SVM) classifying RNA sequences in a higher dimension space. Our experimental results show a high performance of $K_{RNA}^{N}$, compared with the string kernel which is a convolution kernel.