Real Valued and Hybird Genetic Algorithms for Polypeptide Structure Prediction

Energy minimization e orts to predict polypeptide structures assume their native conformation corre sponds to the global minimum free energy state Given this assumption the problem becomes that of develop ing e cient global optimization techniques applicable to polypeptide energy models This general structure prediction objective is also known as the protein fold ing problem Our prediction algorithms based on gen eral full atom potential energy models are expanded to incorporate domain knowledge into the search pro cess Speci cally we evaluate the e ectiveness of a real valued genetic algorithm exploiting domain knowledge about certain dihedral angle values inorder to limit the search space We contrast this approach with our hybrid binary genetic algorithms Various experiments apply these techniques to minimization of the potential energy for the speci c proteins Met Enkephalin and Polyala nine using the CHARMM energy model