Protein Tertiary Structure Prediction with Hybrid Clonal Selection and Differential Evolution Algorithms

Abstract

The paper deals with the problem of protein tertiary structure prediction based on its primary sequence. From the point of view of the optimization problem, the problem of protein folding is reduced to the search for confirmation with minimal energy. To solve this problem, a hybrid artificial immune system has been proposed in the form of a combination of clonal selection and differential evolution algorithms. The developed hybrid algorithm uses special methods of encoding and decoding individuals, as well as an affinity function, which allows reducing the number of incorrect conformations (solutions with self-intersections). To test the algorithm, Dill’s hydrophobic-polar model on a two-dimensional square lattice was chosen. Experimental studies were conducted on test sequences, which showed the advantages of the developed algorithm over other existing methods.