A New Promoter Prediction Method using Support Vector Machines

Abstract

Promoter classification is the task of separating promoter sequences from non-promoter sequences. Determining promoter regions where the transcription initiation takes place is important for several reasons such as improving genome annotation and defining transcription start sites. There are two main problems in promoter classification, which are selection of the informative features and selection of the classification method. In this study, signal, context, and structure features, which are representing promoter sequences, are used. In addition to current methods related to promoter classification, the similarity feature, which compares the promoter regions between human and other species, is added to the proposed system. Support vector machine is used as the classification method. Support vector machine requires some kernels and kernel parameters to classify the data. The genetic algoritm decides which kernel and the kernel parameters will be used in the support vector machine. The results show that the classification accuracy is increased by the proposed method.