Title: MESSM: a framework for protein fold recognition using Neural Networks and Support Vector Machines

Authors: Nan Jiang, Wendy Wu, Ian Mitchell

Addresses: School of Computing Science, Middlesex University, London EN4 4BT, UK. ' School of Computing Science, Middlesex University, London EN4 4BT, UK. ' School of Computing Science, Middlesex University, London EN4 4BT, UK

Abstract: A new framework (called MESSM) for protein fold recognition with three key features is proposed in this paper. Being tested on three benchmark problems, the results show that the MESSM has a comparable performance on fold recognition to those more computational intensive, energy potential based fold recognition models. The MESSM leads to a better performance on alignment accuracy. The MESSM presents a new way to develop an efficient tool for protein fold recognition.

Keywords: protein fold recognition; neural networks; NNs; support vector machines; SVMs; substitution matrix; energy potential; bioinformatics research; bioinformatics applications; high performance computing.

DOI: 10.1504/IJBRA.2006.011037

International Journal of Bioinformatics Research and Applications, 2006 Vol.2 No.4, pp.381 - 393

Published online: 05 Oct 2006 *

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