Protein sequences classification using radial basis function (RBF) neural networks

Abstract

A protein super-family consists of proteins which share amino acid sequence homology and which may therefore be functionally and structurally related. Traditionally, two protein sequences are classified into the same class if they have high homology in terms of feature patterns extracted through sequence alignment algorithms. As the sizes of the protein sequence databases are very large, it is a very time consuming job to perform exhaustive comparison of existing protein sequence. Therefore, there is a need to build an improved classification system for effectively identifying protein sequences. This paper presents a modular neural classifier for protein sequences with improved classification criteria. The intelligent classification techniques described in the paper aims to enhance the performance of single neural classifiers based on a centralized information structure in terms of recognition rate generalization and reliability. The architecture of the proposed model is a modular RBF neural network with a compensational combination at the transition output layer. The connection weights between the final output layer and the transition output layer are optimized by delta rule, which serve as an integrator of the local neural classifiers. To enhance the classification reliability, we present two heuristic rules to apply to decisionmaking. Two sets of protein sequences with ten classes of superfamilies downloaded from a public domain database, Protein Information Resources (PIR), are used in our simulation study. Experimental results with performance comparisons are carried out between single neural classifiers and the proposed modular neural classifier.