A new hybrid genetic algorithm for protein structure prediction on the 2D triangular lattice

Abstract

The flawless functioning of the protein is essentially related to its three-dimensional structure. Therefore, predicting protein structure from its amino acid sequence is a fundamental problem that draws researchers’ attention in many areas. The protein structure prediction problem (PSP) can be formulated as a combinatorial optimization problem based on simplified lattice models such as the hydrophobic-polar model. In this paper, we propose a new hybrid algorithm that combines three different known heuristic algorithms: the genetic algorithm, the tabu search strategy, and the local search algorithm to solve the PSP problem. Regarding the evaluation of the proposed approach, we present an experimental study, where we consider the quality of the product solution as the main assessment criterion. Furthermore, we compared the proposed algorithm with state-of-the-art algorithms using a selection of well-studied benchmark instances.