Differential evolution for protein folding optimization based on a three-dimensional AB off-lattice model

Abstract

This paper presents a differential evolution algorithm that is adapted for the protein folding optimization on a three-dimensional AB off-lattice model. The proposed algorithm is based on a self-adaptive differential evolution that improves the algorithm efficiency and reduces the number of control parameters. A mutation strategy for the fast convergence is used inside the algorithm. A temporal locality is used in order to speed up the algorithm convergence additionally and to find amino-acid conformations with the lowest free energy values. Within this mechanism a new vector is calculated when the trial vector is better than the corresponding vector from the population. This new vector is likely better than the trial vector and this accelerates convergence speed. Because of the fast convergence the algorithm has some chance to be trapped into the local optima. To mitigate this problem the algorithm includes reinitialization. The proposed algorithm was tested on amino-acid sequences that are used frequently in literature. The obtained results show that the proposed algorithm is superior to the algorithms from the literature and the obtained amino-acid sequences have significantly lower free energy values. Graphical Abstract Protein folding optimization on a three-dimensional AB off-lattice model using the differential evolution algorithm.

Protein folding optimization using differential evolution extended with local search and component reinitialization

“…In this paper, we extend our Differential Evolution algorithm [4] with two new mechanisms. The first mechanism is a local search that improves convergence speed and reduces runtime complexity for solution evaluation within a specific neighborhood.…”

Construction of Heuristic for Protein Structure Optimization Using Deep Reinforcement Learning

“…To test whether this is true protein structure optimization using DE was implemented. DE was shown to be the best known optimization method for this problem [7]. Specifications of implemented DE algorithm was taken from [7], but without parameter control.…”

“…DE was shown to be the best known optimization method for this problem [7]. Specifications of implemented DE algorithm was taken from [7], but without parameter control. DE type was best/1/bin, population size was 100, mutation with dithering was employed with mutation constant taken between 0.1 and 1 and recombination constant was 0.9.…”

“…Heuristics from this category include annealing contour Monte Carlo [4] and conformational space annealing [5]. Another approach to developing a specialized optimization algorithm is to modify known metaheuristics such as artificial bee colony [6] or evolutionary algorithm [7].…”

Aplicação de Evolução Diferencial em GPU Para o Problema de Predição de Estrutura de Proteínas com Modelo 3D AB Off-Lattice

“…Na literatura, diversas meta-heurísticas foram propostas para otimizar o modelo 3D AB Off-Lattice. Os autores [Bošković and Brest 2016] propuseram o DE PFO , que consiste no algoritmo DE com autoajuste de parâmetros (jDE) e com técnica de reinicialização global para poder contornar a perda de diversidade. Em [Bošković and Brest 2018], o algoritmo DE LSRC aperfeiçoa a rotina de reinicialização e adiciona um método de busca local que desloca aminoácidos e preserva o restante da conformação da proteína.…”