Using Support Tensor Mechine for Predicting Cell Penetrating Peptides by Fusing DipC and TipC

Abstract

Cell penetrating peptides can carry a variety of bioactive substances into cells and play a biological activity and therapeutic role. Aiming at the prediction of cell penetrating peptides, this paper fused two feature extraction methods dipeptide composition (DipC) and tripeptide composition (TipC) as a new feature expression on the premise of sequence segmentation. Then, linear discriminant analysis (LDA) was used to reduce the dimensions of the three feature expressions, and support vector machine (SVM) was used to classify and predict. Besides, SVM is a kind of commonly used classification method in biological sequence-based classification and prediction. Taking into acount a fewer number of samples of cell penetrating peptides consideration, we introduced a novel classifier support sentor machine (STM) to compare with SVM. It's showed based on the results that the fusion of the TipC and DipC can get higher accurary than that of the single feature-based method and the accuracy of STM was higher than that of SVM in the identification of cell penetrating peptides under different feature expression, which brought a new idea for the prediction of cell penetrating peptides.