Prediction of Protein Structures using a Hopfield Network

Under proper conditions, a globular protein adopts a unique three-dimensional structure that is encoded in this amino acid sequence. The theoretical prediction of this structure, and the pathways followed during the folding process constitute the most challenging and still unsolved problems of structural molecular biology. Computersimulated neural networks have recently gained much attention and the application of neural networks models toward a variety of problems associated with protein structure prediction. Several works have been explored the application of genetic algorithms and neural networks to the determination of the protein structure. There are several techniques of computational simulation that can be used to study structure os proteins as methods of Monte Carlo, Simulated Annealing, Genetic Algorithms and Neural Networks. This work aims discusses the possibilities to use neural networks in the study of macromolecule structures and presents a example of a Hopfield Network to predict the structure of a protein and discusses the results and possible future works using neural networks and genetic algorithms to design new proteins and drugs. This paper used a Hopfield Network to predict a primary sequence and the tertiary structure of the core of the Cytochrome b562. The neural network was implemented using the language of programming C and the simulations was running in a Silicon Graphics.