Splice Site Recognition Using Lower Dimensional LHMM Features and SVM Classifier
International Journal for Research in Applied Science and Engineering Technology
Recognition of coding region from DNA sequence has gained immense importance in the field of the research of gene identification. Splice sites which are the borders between exons and introns in DNA sequence are found in the eukaryotic organism. At present, there are several algorithms available for splice site recognition with an aim to improve the prediction accuracy. With an objective to further develop an efficient algorithm, Splice site recognition using lower dimensional Linear Hidden
... Linear Hidden Markov Model (LHMM) features have been proposed in this paper. The proposed algorithm of Splice site recognition using lower dimension consists of three stages. Initial step use first order Markov Model (MM1) for feature extraction, in second stage dimension of feature vectors are reduced by using Principal Component Analysis (PCA) and, final or last stage use Support Vector Machine (SVM) with Gaussian kernel for classification. When the results of the proposed algorithm are compared with the existing algorithm of Splice site recognition, it has indicated remarkable performance and accuracy.