基于改进的禁忌搜索的蛋白质三维结构预测  

Protein 3D Structure Prediction Based on Improved Tabu Search

作　　者：张晓龙[1] 程文[1] 

机构地区：[1]武汉科技大学计算机科学与技术学院,武汉430065

出　　处：《计算机工程》2009年第4期31-34,共4页Computer Engineering

基　　金：国家自然科学基金资助项目(60674115);留学回国人员科研启动基金资助项目"生物信息处理中的机器学习算法研究"

摘　　要：禁忌搜索算法是一种局部搜索能力很强的全局迭代优化算法,已经被成功地应用到各种组合优化问题中。基于AB非格模型,该文将一种改进的禁忌搜索算法应用于蛋白质三维折叠结构预测。实验结果表明改进的禁忌算法求得的蛋白质三维最低能量构形的最低能量值比已有的算法求得的最低能量值要低,同时三维构形中形成了一个疏水核,被亲水残基包围,反映了真实蛋白质的结构特征。该算法效率高,可以有效地用于蛋白质三维折叠预测。Tabu Search（TS） algorithm is one of the global optimization search methods which has strong local search and is applied for a large number of combinatorial optimization problems. In the paper, an improved TS algorithm is proposed for protein Three-Dimensional（3D） folding structure prediction in AB off-lattice model. Experimental results show that the lowest energies computed by improved TS algorithm are better than those obtained by previous methods. Given a protein sequence, its lowest-energy conformation obtained by the improved TS forms a single hydrophobic core, which suggests that AB model in three dimensions appears to reflect real protein reasonably. Compared with previous heuristic approaches, improved TS algorithm has higher performance and can be effectively used to predict 3D structure prediction of proteins.

关 键 词：禁忌搜索算法 蛋白质三维折叠 AB非格模型 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]