改进的遗传算法在蛋白质结构预测中的应用

摘要:为了提高蛋白质结构预测效率,针对蛋白质HP模型折叠问题,在标准遗传算法的基础上,本文提出了一系列改进的搜索策略:控制群体中全同体数目保持群体多样性;在交叉阶段实施单点交叉父子竞争提高个体生存竞争力;对最优个体实施系统变异局部优化等. 实验结果表明,与标准遗传算法相比,改进后的遗传算法较大幅度的提高了搜索效率和成功率,遗传算法在蛋白质空间结构预测上是一个有相当潜力的算法.

THE APPLICATION OF IMPROVED GENETIC ALGORITHMS FOR PREDICTING PROTEIN STRUCTURES

To improve efficiency of predicting protein structures,a series of improved search strategies is investigated based on the standard genetic algorithms(GA) for the hydrophobic-polar(HP) protein folding problem.The new strategies include the followings: to control the number of identical individuals for maintaining the diversity of populations,to combine with competing between parent and offspring at a single point crossover to enhance the survival level,to give a local search algorithm based on systematic mu...