Title: Supervised classification of protein structures based on convex hull representation

Authors: Yong Wang, Ling-Yun Wu, Luonan Chen, Xiang-Sun Zhang

Addresses: Academy of Mathematics and Systems Science, CAS, Beijing 100080, China; State Information Center, Beijing 100045, China. ' Academy of Mathematics and Systems Science, CAS, Beijing 100080, China. ' Institute of Systems Biology, Shanghai University, Shanghai 200444, China; Department of Electrical Engineering and Electronics, Osaka Sangyo University, Osaka 574-8530, Japan; ERATO Aihara Complexity Modelling Project, JST, Tokyo 153-8505, Japan; Institute of Industrial Science, The University of Tokyo, Tokyo 153-8505, Japan. ' Academy of Mathematics and Systems Science, CAS, Beijing 100080, China

Abstract: One of the central problems in functional genomics is to establish the classification schemes of protein structures. In this paper the relationship of protein structures is uncovered within the framework of supervised learning. Specifically, the novel patterns based on convex hull representation are firstly extracted from a protein structure, then the classification system is constructed and machine learning methods such as neural networks, Hidden Markov Models (HMM) and Support Vector Machines (SVMs) are applied. The CATH scheme is highlighted in the classification experiments. The results indicate that the proposed supervised classification scheme is effective and efficient.

Keywords: protein structures; automatic classification; machine learning; convex hull representation; bioinformatics; functional genomics; supervised learning; pattern recognition; neural networks; hidden Markov models; HMM; support vector machines; SVMs.

DOI: 10.1504/IJBRA.2007.013598

International Journal of Bioinformatics Research and Applications, 2007 Vol.3 No.2, pp.123 - 144

Available online: 09 May 2007 *

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