Substitution matrix optimisation for peptide classification

Authors:
David C. Trudgian;Zheng Rong Yang
Affiliations:
School of Engineering, Computer Science and Mathematics, University of Exeter, Exeter, UK;School of Engineering, Computer Science and Mathematics, University of Exeter, Exeter, UK
Venue:
EvoBIO'07 Proceedings of the 5th European conference on Evolutionary computation, machine learning and data mining in bioinformatics
Year:
2007

Citing 3
Cited 3

Artificial neural network model for predicting HIV protease cleavage sites in protein

Advances in Engineering Software
Evolution strategies –A comprehensive introduction

Natural Computing: an international journal
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)

On Utilizing Optimal and Information Theoretic Syntactic Modeling for Peptide Classification

PRIB '09 Proceedings of the 4th IAPR International Conference on Pattern Recognition in Bioinformatics
A sparse Bayesian position weighted bio-kernel network

IDEAL'07 Proceedings of the 8th international conference on Intelligent data engineering and automated learning
Peptide classification using optimal and information theoretic syntactic modeling

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Bio-basis Function Neural Network (BBFNN) is a novel neural architecture for peptide classification that makes use of amino acid mutation matrices and a similarity function to model protein peptide data without encoding. This study presents an Evolutionary Bio-basis network (EBBN), an extension to the BBFNN that uses a self adapting Evolution Strategy to optimise a problem specific substitution matrix for much improved model performance. The EBBN is assessed against BBFNN and multi layer perceptron (MLP) models using three datasets covering cleavage sites, epitope sites, and glycoprotein linkage sites. The method exhibits statistically significant improvements in performance for two of these sets.