Title: PECB: prediction of enzyme catalytic residues based on Naive Bayes classification

Authors: Kunpeng Zhang, Yun Xu, Guoliang Chen

Addresses: Department of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, 230027, China. ' Department of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, 230027, China; Anhui Province – MOST Co-Key, Laboratory of High Performance Computing and Its Application, Hefei, Anhui, 230027, China. ' Department of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, 230027, China; Anhui Province – MOST Co-Key, Laboratory of High Performance Computing and Its Application, Hefei, Anhui, 230027, China

Abstract: In the post-genome era, huge numbers of protein structures accumulate, but little is known about their function. It is time consuming and labour intensive to investigate them, e.g., enzyme catalytic properties, through in vivo or in vitro work. So in silico predictions could be a promising strategy to greatly shrink the list of potential targets. This work incorporated both structural and physico-chemical information into a Naive Bayes classification system, and gained much better performance. The ten-fold cross validation results of this method could reach 88.6% of sensitivity and 93.7% of specificity. The improvement of prediction accuracy is detailed in this paper. The PECB is also applied to predict other important sites.

Keywords: PECB; sequence analysis; structure information; physico-chemical; Naive Bayes classification; enzyme catalytic residues; bioinformatics; protein function.

DOI: 10.1504/IJBRA.2008.019576

International Journal of Bioinformatics Research and Applications, 2008 Vol.4 No.3, pp.295 - 305

Available online: 17 Jul 2008 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article