MESSM: a framework for protein fold recognition using neural networks and support vector machines.

Mitchell, Ian and Jiang, Nan and Wu, Wendy Xinyu (2006) MESSM: a framework for protein fold recognition using neural networks and support vector machines. International Journal of Bioinformatics Research and Applications, 2 (4). pp. 381-393. ISSN 1744-5493

Full text is not in this repository.

Abstract

This paper presents the results of a PhD project that developed a framework, known as MESSM, for protein fold recognition. The framework has 3 key features: i) an environment-specific amino acid substitution is generated, ii) a mixed substitution mapping is performed by linearly combining the structurally derived substitution mapping with a sequence profile from well-developed amino acid substitution matrices, iii) Support Vector Machines are employed to measure the significance of the sequence-structure alignment. Tested on benchmark problems, MESSM was shown to lead to a better performance of alignment accuracy.

Item Type: Article
Research Areas: A. > School of Science and Technology > Computer Science
A. > School of Science and Technology > Computer Science > Artificial Intelligence group
Item ID: 83
Useful Links:
Depositing User: Repository team
Date Deposited: 17 Oct 2008 14:56
Last Modified: 13 Oct 2016 14:11
URI: http://eprints.mdx.ac.uk/id/eprint/83

Actions (login required)

Edit Item Edit Item