蛋白质构象空间的多模态优化算法  

Multimodal Optimization Algorithm for Protein Conformation Space

作　　者：李章维[1] 肖璐倩 郝小虎[1] 周晓根 张贵军[1] LI Zhang-wei;XIAO Lu-qian;HAO Xiao-hu;ZHOU Xiao-gen;ZHANG Gui-jun(College of Information Engineering,Zhejiang University of Technology,Hangzhou 310023,China;Department of Computational Medicine and Bioinformatics,University of Michigan,Ann Arbor,MI 48109-2218,USA)

机构地区：[1]浙江工业大学信息工程学院,杭州310023 [2]密歇根大学计算医学和生物信息学系,安娜堡48109-2218

出　　处：《计算机科学》2020年第7期161-165,共5页Computer Science

基　　金：国家自然科学基金(61773346,61573317)。

摘　　要：蛋白质能量模型的不精确性导致数学上的最优解并不一定对应其稳定的天然态结构,同时其巨大的构象空间使得现有方法也极易收敛到局部最优解。针对蛋白质结构能量模型不精确和高维构象空间采样可靠性低的问题,在进化算法的基础上,提出了一种基于二面角相似度的蛋白质构象多模态优化方法。首先,执行模态探测,将Rosetta粗粒度能量模型作为筛选高质量新个体的标准,进行种群更新,增加种群构象的多样性;然后,建立二面角相似度模型,用于评价不同构象间的相似程度,以满足多模态优化算法中相似个体快速判定的要求,并基于排挤更新策略实现模态增强,获得结构更为合理的构象。10个测试蛋白质的实验结果表明:所提算法能够达到较高的预测精度,并且可以使种群具有良好的模态分布,得到尽可能多的高质量局部极值解,从而获得一些较好的蛋白质亚稳态结构。Due to the inaccuracy of protein energy model,the optimal solution in mathematics does not consistently correspond to the stable natural structure of a given protein.The existing methods tend to converge to local optimal solutions because of the huge conformational space.To address the problem of the inaccuracy of energy model in the field of protein structure prediction and the reliability of high-dimensional conformational space sampling,a dihedral angle similarity based multimodal conformation optimization method(DASOM)for ab-initio protein structure prediction is proposed in the framework of population based algorithm.Firstly,the modal exploration is conducted,knowledge-based Rosetta coarse-grained energy model is used as the standard to select new individuals with high quality,thus the diversity of the population can be increased.Then,a dihedral angular similarity model is established to meet the requirements of similar individual determination in the multi-modal optimization algorithm.Crowding update strategy is used for optimizing the existing modal to achieve the modal enhancement and more reasonable conformation is obtained.Experimental results on 10 test proteins show that the proposed method not only achieves high prediction accuracy,but also obtains many metastable protein conformations as well.

关 键 词：蛋白质结构预测 多模态优化 二面角相似度模型 ROSETTA 粗粒度能量模型 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]