Protein structure analysis and prediction is a core area of research in bioinformatics. Prediction of protein secondary structure from amino acid sequences is one of the most important problems in molecular biology, because the structure of a protein is related to its function. Thus high prediction accuracy of protein structure from its sequence is highly desirable. Considerable research effort has been devoted to predicting the secondary structure of proteins from their amino acid sequences that typically have 76% approximate level of accuracy on an average. Thus, there is a considerable room for improvement. Recently digital signal processing (DSP) tools have been successfully applied in solving problems in the field of bioinformatics. In this paper we have proposed an effective feature extraction method based on discrete wavelet transform (DWT) to detect informative proteins and radial basis function neural network (RBFNN) classifier is used to efficiently predict the sample class which has a low complexity than other classifier in which effective numerical representation based on physico-chemical parameters induces the prediction more accurately. The potential of the proposed approach is evaluated through an exhaustive study by benchmark non-redundant dataset and a prediction accuracy of 93% is achieved.
Determining the protein structure from amino acid sequence leads to better understanding of the functionality of the protein resulting in faster drug discovery. Proteins are fundamental components of all living cells, performing a variety of biological tasks. Each protein has a particular structure that determines its function. Protein structure is more conserved than protein sequence, and more closely related to function. Proteins are macromolecules that are responsible for a wide range of vital biochemical functions, which include acting as catalysts, oxygen transport, cell signaling, antibody production, nutrient transport and building up muscle fibers [1-2]. More specifically, proteins are chains of amino acids, of which there are twenty different types, joined by peptide bonds.
Contact DetailsEditor-in-Chief & Director,
Copyright (c) 2012, ijarst.com All rights reserved. | Design by Center for Advanced Research.