计算机科学 ›› 2020, Vol. 47 ›› Issue (7): 161-165.doi: 10.11896/jsjkx.190600100

• 人工智能 • 上一篇    下一篇

蛋白质构象空间的多模态优化算法

李章维1, 肖璐倩1, 郝小虎1, 周晓根2, 张贵军1   

  1. 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
  • 收稿日期:2019-06-19 出版日期:2020-07-15 发布日期:2020-07-16
  • 通讯作者: 张贵军(zgj@zjut.edu.cn)
  • 作者简介:lzw@zjut.edu.cn
  • 基金资助:
    国家自然科学基金(61773346,61573317)

Multimodal Optimization Algorithm for Protein Conformation Space

LI Zhang-wei1, XIAO Lu-qian1, HAO Xiao-hu1, ZHOU Xiao-gen2, ZHANG Gui-jun1   

  1. 1 College of Information Engineering,Zhejiang University of Technology,Hangzhou 310023,China
    2 Department of Computational Medicine and Bioinformatics,University of Michigan,Ann Arbor,MI 48109-2218,USA
  • Received:2019-06-19 Online:2020-07-15 Published:2020-07-16
  • About author:LI Zhang-wei,born in 1976,Ph.D,associate professor,is a member of China Computer Federation.His main research interests include intelligent information processing.
    Zhang Gui-jun,born in 1974,Ph.D,professor,is a member of China Computer Federation.His main research interests include intelligent information processing,optimization theory and algorithm design and bioinformatics.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (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。

关键词: Rosetta, 粗粒度能量模型, 蛋白质结构预测, 多模态优化, 二面角相似度模型

Abstract: 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.

Key words: Coarse-grained energy model, Dihedral angular similarity model, Multimodal optimization, Protein structure prediction, Rosetta

中图分类号: 

  • TP301.6
[1]WEBB B.Swarm Intelligence:From Natural to Artificial Systems[J].Connection Science,2002,14(2):163-164.
[2]KENNEDY J,EBERHART R.Particle swarm optimization[C]//Proceedings of the IEEE International Conference on Neural Networks.1995:1942-1948.
[3]YANG X S.Firefly algorithms for multimodal optimization[C]//International Symposium on Stochastic Algorithms.Berlin:Springer,2009:169-178.
[4]YANG X S,DEB S.Cuckoo search via Lévy flights[C]//2009 World Congress on Nature & Biologically Inspired Computing (NaBIC).IEEE Press,2009:210-214.
[5]MIRJALILI S,MIRJALILI S M,LEWIS A.Grey Wolf Optimizer[J].Advances in Engineering Software,2014,69:46-61.
[6]MIRJALILI S.Dragonfly algorithm:a new meta-heuristic optimization technique for solving single-objective,discrete,and multi-objective problems[J].Neural Computing and Applications,2016,27(4):1053-1073.
[7]MIRJALILI S,LEWIS A.The Whale Optimization Algorithm[J].Advances in Engineering Software,2016,95:51-67.
[8]LIU H,MOTODA H.Feature selection for knowledge discovery and data mining[M].Springer Science & Business Media,2012:73-95.
[9]MIRJALILI S,GANDOMI A H,MIRJALILI S Z,et al.Salp Swarm Algorithm:A bio-inspired optimizer for engineering design problems[J].Advances in Engineering Software,2017,114:163-191.
[10]CHEN T,WANG M X,HUANG X S.Passive TDOA location based on Bohai Sheath Swarm Algorithms [J].Chinese Journal of Electronics and Information,2018,40(7):72-78.
[11]HUSSIEN A G,HASSANIEN A E,HOUSSEIN E H.Swarming behaviour of salps algorithm for predicting chemical compound activities[C]//2017 Eighth International Conference on Intelligent Computing and Information Systems (ICICIS).IEEE Press,2017:315-320.
[12]WANG M Q,WANG Y,JI Z C.PMSM multi-parameter identification based on improved salp swarm algorithm [J].Chinese Journal of System Simulation,2018(11):4284-4291.
[13]QAIS M H,HASANIEN H M,ALGHUWAINEM S.Enhanced salp swarm algorithm:Application to variable speed wind genera-tors[J].Engineering Applications of Artificial Intelligence,2019,80:82-96.
[14]XING Z K,JIA H M,SONG W L.Multi-threshold image segmentation based on Levy’s Flying Bowl Sheath swarm optimization algorithm [J/OL].Chinese Journal of Automation. [2019-08-10].https://doi.org/10.16383/j.aas.c180140.
[15]HEGAZY A E,MAKHLOUF M A,EL-TAWEL G S.Improved salp swarm algorithm for feature selection[J].Journal of King Saud University-Computer and Information Sciences,2020,32(3):355-344.
[16]FARIS H,MAFARJA M M,HEIDARI A A,et al.An efficient binary salp swarm algorithm with crossover scheme for feature selection problems[J].Knowledge-Based Systems,2018,154:43-67.
[17]IBRAHIM R A,EWEES A A,OLIVA D,et al.Improved salp swarm algorithm based on particle swarm optimization for feature selection[J].Journal of Ambient Intelligence andHuma-nized Computing,2019,10(8):3155-3169.
[18]SAYED G I,KHORIBA G,HAGGAG M H.A novel chaotic salp swarm algorithm for global optimization and feature selection[J].Applied Intelligence,2018,48(10):3462-3481.
[19]YAN X F,YE D Y.An improved flora foraging algorithm based on Levy flight [J].Computer system applications,2015,24 (3):124-132.
[20]HÜSEYIN H,HARUN U.A novel particle swarm optimization algorithm with LeÜvy flight[J].Applied Soft Computing,2014,23:333-345.
[21]AYDOĞDU Î,AKIN A,SAKA M P.Design optimization of real world steel space frames using artificial bee colony algorithm with Levy flight distribution[J].Advances in Engineering Software,2016,92:1-14.
[22]LIU C P,YE C M.Bat algorithm with Levy flight characteristics [J].Chinese Journal of Intelligent Systems,2013,8(3):240-246.
[23]BIAGINI F.Stochastic calculus for fractional Brownian motion and applications[M].London:Springer,2008:5-20.
[24]ZHU X E,HAO X,XIA S R.Levy flight-based feature selection algorithm [J].Chinese Journal of Zhejiang University (Engineering Edition),2013(4):638-643.
[25]EDWARDS A M,PHILLIPS R A,WATKINS N W,et al.Revisiting Lévyflight search patterns of wandering albatrosses,bumblebees and deer [J].Nature,2007,449(7165):1044-1048.
[26]EMBRECHTS P,KLÜPPELBERG C,MIKOSCH T.Modelling extremal events:for insurance and finance[M]//Science &Busi-ness Media.Springer,2013:371-403.
[27]MANTEGNA R N.Fast,accurate algorithm for numerical simulation of Lévy stable stochastic processes[J].Physical Review.E,1994,49(5):4677-4689.
[1] 谢腾宇,周晓根,胡俊,张贵军.
基于接触图残基对距离约束的蛋白质结构预测算法
Contact Map-based Residue-pair Distances Restrained Protein Structure Prediction Algorithm
计算机科学, 2020, 47(1): 59-65. https://doi.org/10.11896/jsjkx.181202395
[2] 李章维,郝小虎,张贵军.
基于副本交换的局部增强差分进化蛋白质结构从头预测方法
Replica Exchange Based Local Enhanced Differential Evolution Searching Method in Ab-initio Protein Structure Prediction
计算机科学, 2017, 44(5): 211-217. https://doi.org/10.11896/j.issn.1002-137X.2017.05.038
[3] 董辉,郝小虎,张贵军.
蛋白质构象空间局部增强差分进化搜索方法
Local Enhancement Differential Evolution Searching Method for Protein Conformational Space
计算机科学, 2015, 42(Z11): 22-26.
[4] 郝小虎,张贵军,周晓根,程正华,张启鹏.
一种基于片段组装的蛋白质构象空间优化算法
Protein Conformational Space Optimization Algorithm Based on Fragment-assembly
计算机科学, 2015, 42(3): 237-240. https://doi.org/10.11896/j.issn.1002-137X.2015.03.049
[5] 程正华,张贵军,邓勇跃,金媚媚.
一种新的蛋白质结构预测多模态优化算法
Novel Multimodal Optimization Algorithm for Protein Structure Prediction
计算机科学, 2013, 40(9): 212-215.
[6] .
改进的势能曲面变平法在二维非格点模型中的应用

计算机科学, 2008, 35(10): 243-245.
[7] 吕志鹏 黄文奇.
求解蛋白质结构预测问题的局部搜索算法

计算机科学, 2005, 32(11): 148-149.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!