A solution to protein folding problem using a genetic algorithm with modified keep best reproduction strategy

Genetic algorithms have proved to be a successful method for predicting the protein structure. In this paper, we propose a new intermediate selection strategy for genetic algorithms and we implement it for protein folding problem. In a standard genetic algorithm the children replace their parents. The idea behind this is that both parents pass on their good genetic material to their children. In practice however, children can have worse fitness than their parents. We therefore propose another intermediate selection step, which we call as modified keep-best reproduction (MKBR) that ensures that new genetic information is entered into the gene pool, as well as good previous genetic material is being preserved. We have demonstrated the superiority of modified keep-best reproduction on several instances of the proteinfolding problem, which not only finds the optimum solution, but also finds them faster than the standard generational replacement schemes.