A hybrid genetic-neural model for predicting protein structural classes |
| |
Authors: | Samad Jahandideh Somayyeh Hoseini Mina Jahandideh Mohammad Reza Davoodi |
| |
Affiliation: | (1) Department of Biophysics, Faculty of Science, Tarbiat Modares University, P.O. Box, 14115/175 Tehran, Iran;(2) Department of Medical Physics, Shiraz University of Medical Sciences, Shiraz, Iran;(3) Department of Biochemistry, Division of Genetics, Tabriz University of Medical Sciences, Tabriz, Iran;(4) Department of Mathematics, Faculty of Science, Vali-E-Asr University, Rafsanjan, Iran;(5) Department of Electrical Engineering, Faculty of Engineering, Tarbiat Modares University, Tehran, Iran |
| |
Abstract: | A genetic algorithm (GA) for feature selection in conjunction with neural network was applied to predict protein structural classes based on single amino acid and all dipeptide composition frequencies. These sequence parameters were encoded as input features for a GA in feature selection procedure and classified with a three-layered neural network to predict protein structural classes. The system was established through optimization of the classification performance of neural network which was used as evaluation function. In this study, self-consistency and jackknife tests on a database containing 498 proteins were used to verify the performance of this hybrid method, and were compared with some of prior works. The adoption of a hybrid model, which encompasses genetic and neural technologies, demonstrated to be a promising approach in the task of protein structural class prediction. |
| |
Keywords: | genetic algorithm artificial neural networks sequence parameters amino acid composition |
本文献已被 SpringerLink 等数据库收录! |
|