Table of Contents Author Guidelines Submit a Manuscript
BioMed Research International
Volume 2014, Article ID 623149, 12 pages
http://dx.doi.org/10.1155/2014/623149
Research Article

iSS-PseDNC: Identifying Splicing Sites Using Pseudo Dinucleotide Composition

1Department of Physics, School of Sciences, Center for Genomics and Computational Biology, Hebei United University, Tangshan 063000, China
2Gordon Life Science Institute, Boston, MA 02478, USA
3School of Public Health, Hebei United University, Tangshan 063000, China
4Key Laboratory for Neuro-Information of Ministry of Education, Center of Bioinformatics, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China
5Center of Excellence in Genomic Medicine Research (CEGMR), King Abdulaziz University, Jeddah 21589, Saudi Arabia

Received 19 February 2014; Revised 22 April 2014; Accepted 23 April 2014; Published 21 May 2014

Academic Editor: Rita Casadio

Copyright © 2014 Wei Chen et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

In eukaryotic genes, exons are generally interrupted by introns. Accurately removing introns and joining exons together are essential processes in eukaryotic gene expression. With the avalanche of genome sequences generated in the postgenomic age, it is highly desired to develop automated methods for rapid and effective detection of splice sites that play important roles in gene structure annotation and even in RNA splicing. Although a series of computational methods were proposed for splice site identification, most of them neglected the intrinsic local structural properties. In the present study, a predictor called “iSS-PseDNC” was developed for identifying splice sites. In the new predictor, the sequences were formulated by a novel feature-vector called “pseudo dinucleotide composition” (PseDNC) into which six DNA local structural properties were incorporated. It was observed by the rigorous cross-validation tests on two benchmark datasets that the overall success rates achieved by iSS-PseDNC in identifying splice donor site and splice acceptor site were 85.45% and 87.73%, respectively. It is anticipated that iSS-PseDNC may become a useful tool for identifying splice sites and that the six DNA local structural properties described in this paper may provide novel insights for in-depth investigations into the mechanism of RNA splicing.