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:School of Science and Technology > Computer and Communications Engineering
ID Code:83
Useful Links:
Deposited On:17 Oct 2008 14:56
Last Modified:13 May 2014 15:37

Repository staff only: item control page

Full text downloads (NB count will be zero if no full text documents are attached to the record)

Downloads per month over the past year