Protein Secondary Structure Prediction using decision fusion of Genetic Algorithm and Simulated Annealing Algorithm

Neural networks can be combined with simulated annealing (SA) and genetic algorithm (GA) techniques along with decision fusion algorithms to further improve on the accuracy of protein secondary structure prediction. In order to obtain the three dimensional structure of a protein it is first essential to predict the secondary structure of a protein (alpha- helix, beta-sheet, coil). The fusion of these algorithms in combination with neural networks made way for the improvement in the prediction accuracy. In this research the RS126 data set was used for training and testing purposes. An 8% improvement was obtained in the prediction accuracy with the new technique proposed, compared to that of the traditional neural network approach