A Differential Evolution Approach for Protein Folding Using a Lattice Model  

作　　者：Heitor Silverio Lopes Reginaldo Bitello 

机构地区：[1]Bioinformatics Laboratory,Federal University of Technology-Paraná,Av.7 de setembro,3165 80230-901 Curitiba,Brazil

出　　处：《Journal of Computer Science & Technology》2007年第6期904-908,共5页计算机科学技术学报（英文版）

基　　金：This work is supported by the Brazilian National Research Council under Grant No.305720/04-0.

摘　　要：Protein folding is a relevant computational problem in Bioinformatics, for which many heuristic algorithms have been proposed. This work presents a methodology for the application of differential evolution （DE） to the problem of protein folding, using the bi-dimensional hydrophobic-polar model. DE is a relatively recent evolutionary algorithm, and has been used successfully in several engineering optimization problems, usually with continuous variables. We introduce the concept of genotype-phenotype mapping in DE in order to provide a mapping between the real-valued vector and an actual folding. The methodology is detailed and several experiments with benchmarks are done. We compared the results with other similar implementations. The proposed DE has shown to be competitive, statistically consistent and very promising.Protein folding is a relevant computational problem in Bioinformatics, for which many heuristic algorithms have been proposed. This work presents a methodology for the application of differential evolution （DE） to the problem of protein folding, using the bi-dimensional hydrophobic-polar model. DE is a relatively recent evolutionary algorithm, and has been used successfully in several engineering optimization problems, usually with continuous variables. We introduce the concept of genotype-phenotype mapping in DE in order to provide a mapping between the real-valued vector and an actual folding. The methodology is detailed and several experiments with benchmarks are done. We compared the results with other similar implementations. The proposed DE has shown to be competitive, statistically consistent and very promising.

关 键 词：BIOINFORMATICS differential evolution evolutionary computation protein folding 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]