Control of the population diversity in genetic algorithms applied to the protein structure prediction problem

Abstract

Genetic Algorithms (GAs), a successful approach for optimization problems, usually fail when employed in the standard configuration in the protein structure prediction problem, since the solution space is very large and the population converges before a reasonable percentage of the possible solutions is explored. Thus, this work investigates the effect of increasing the diversity of the population on this problem by using Hypermutation and Random Immigrants, two traditional population diversity control schemes, in the structure prediction of the proteins Crambin (PDB 1CRN), Met-Enkephalin (PDB 1PLW), and DNA-Ligand (PDB 1ENH). Results show a significant reduction of the minimal energy found, thanks to the diversity, but this does not necessarily means a higher similarity to the original structure.

Keywords: evolutionary computing, genetic algorithms, hypermutation, random immigrants, protein structure prediction.