A method for improving the accuracy of predicting RNA-protein binding sites

摘要

Protein-RNA interactions play a key role in a number of biological processes. This paper introduces a method for RNA-protein binding sites prediction. Feature extraction plays a key role in RNA-protein binding sites prediction, and can greatly improve the performance of a classifier. In this paper, we propose a novel semi-supervised dimensionality reduction method for extracting features. The experimental results show that the proposed method is efficient and feasible. Compared with other methods, our methods can achieve relatively higher prediction accuracy.