Protein Structure Prediction in Soybeans using Neural Networks

Abstract

Proteins are a definite kind of biological macromolecules that is present in all biological organisms. Amino acids are the building blocks of proteins. They are primary structure, secondary structure, tertiary structure and quaternary structure. Most of the existing algorithms for predicting the content of the protein secondary structure elements have been based on the conventional amino acid composition, where no sequence coupling effects are taken into consideration. Prediction of three dimensional structure, secondary structure, and functional sites of proteins from primary structure are the three major problems in structural bioinformatics. More than a few different approaches have been previously used in these kind of predictions among which, artificial neural networks have been of great interest due to their capability of learning from observations and prediction of the structures for non classified instances. This paper proposes a technique for prediction of protein structure in soybeans using neural networks. This paper uses RBFNN in order to predict the secondary structure. In our approach, genetic encoding scheme is used to generate the centers and widths of radial basis function. In our approach, genetic encoding scheme is used to generate the centers and widths of radial basis function. The neural network architecture used in our approach is a feed forward and fully connected neural network whose Gaussian centers are optimized by genetic algorithm. Experimental are carried on dataset obtained from Protein Data Bank (PDB) to predict the structure of the protein present in it.