| 338 | 6 | 29 |
| 下载次数 | 被引频次 | 阅读次数 |
本文针对传统蛋白质相互作用预测模型预测精度不够高的问题,提出一种改进的深度玻尔兹曼机(DBM)模型以更精确地预测蛋白质的相互作用。首先,将多尺度特征组提取和自协方差编码方法结合编码序列特征,并利用DBM自动筛选有效特征。同时,为了避免采用sigmoid或tanh激活函数在深度网络中出现过饱和的问题,本文采用Re LU改进的深度玻尔兹曼机(RBM),使网络具备稀疏性,从而避免模型过拟合,加快收敛速度。在酵母菌PPIs数据集上,本文算法达到了92.27%的准确率,优于传统的方法。
Abstract：To address the problem that prediction accuracy is not high enough in traditional protein interaction prediction model, we present a new improved deep boltzmann machine model(DBM) to predict protein interactions accurately. Firstly, combining a novel Multi-scale Continuous and Discontinuous(MCD) feature representation and autocovariance approach to encoding protein sequence, and employing DBM to automatically select an effective feature. In addition, in order to avoid saturation by using sigmoid or tanh activation function in depth network, Re LU modified restricted boltzmann machine(RBM) is selected to improve the sparsity of the network, to avoid over-fitting,and to improve the convergence rate. The prediction accuracy of proposed model on yeast PPIs data set achieved92.27%, which indicates that our performance better than the previous related models.
Cai D.L.,and Guo H.,2014,Protein-protein interaction prediction method based on SVM witu hybrid kernel function,Fuzhoudaxue Xuebao(Zirankexue Ban)(Journal of Fuzhou\sUniversity(Natural Science Edition)),42(6):834-840(蔡丹莉,郭红,2014,基于混合核函数SVM的蛋白质相互作用预测方法,福州大学学报(自然科学版),42(6):834-840)
Chatterjee P.,Basu S.,Kundu M.,Nasipuri M.,and Plewczynski\sD.,2011,PPI_SVM:prediction of protein-protein interactions using machine learning,domain-domain affinities and\sfrequency tables,Cellular&Molecular Biology Letters,16(2):264-278
Glorot X.,Bordes A.,and Bengio Y.,2011,Deep sparse rectifier\snetworks,Proceedings of the 14th International Conference\son Artificial Intelligence and Statistics,JMLR W&CP,15:315-323
Gong P.T.,Xu R.S.,and Fang X.J.,2014,Proteogenomics:progress,strategy and problem,Jiyinzuxue Yu Yingyong Shengwuxue(Genomics and Applied Biology),33(6):1169-1180(巩鹏涛,徐润生,方宣钧,2014,蛋白质基因组学:进展,策略及问题,基因组学与应用生物学,33(6):1169-1180)
Guo Y.Z.,Yu L.Z.,Wen Z.N.,and Li M.L.,2008,Using support\svector machine combined with auto covariance to predict\sprotein-protein interactions from protein sequences,Nucleic\sAcids Res.,36(9):3025-3030
Jansen R.,Yu H.,Greenbaum D.,Kluger Y.,Krogan N.J.,Chung\sS.,Emili A.,Snyder M.,Greenblatt J.F.,and Gerstein M.,2003,A Bayesian networks approach for predicting protein-protein interactions from genomic data,Science,302(5644):449-453
Li B.Q.,Feng K.Y.,Chen L.,Huang T.,and Cai Y.D.,2012,Prediction of protein-protein interaction sites by random forest\salgorithm with m RMR and IFS,Plo S One,7(8):e43927
Li J.,Chen Y.,and Wang F.,2014,Wavelet analysis combined\swith artificial neural network for predicting protein-protein\sinteractions,Computer Engineering and Networking,Springer International Publishing,pp.47-53
Maas A.L.,Hannun A.Y.,and Ng A.Y.,2013,Rectifier nonlinearities improve neural network acoustic models,Proc.,ICML,pp.30
Martin S.,Roe D.,and Faulon J.L.,2005 Predicting protein-protein interactions using signature products,Bioinformatics,1(2):218-226
Qi Y.,Klein-Seetharaman J.,and Bar-Joseph Z.,2004,Random\sforest similarity for protein-protein interaction prediction\sfrom multiple sources,Pacific Symposium on Biocomputing,2005:531-542
Saha I.,Klingstr觟m T.,Forsberg S.,Wikander J.,Zubek J.,and\sKierczak M.,2014,Evaluation of machine learning algorithms on protein-protein interactions,Man-Machine Interactions 3,Springer International Publishing,242:211-218
Salakhutdinov R.,and Hinton G.E.,2009,Deep boltzmann machines,International Conference on Artificial Intelligence\sand Statistics,pp.448-455
Shen J.,Zhang J.,Luo X.,Zhu W.,Yu K.,Chen K.,Li Y.,and\sJiang H.,2007,Predicting protein-protein interactions based\sonly on sequences information,Proc.Natl.Acad.Sci.USA,104(11):4337-4341
Shi W.L.,Guo M.Z.,Li J.,and Liu X.Y.,2014,Protein-protein\sinteraction prediction combining active learning with SVM,Jisuanji Kexue(Computer Science),41(2):82-86(史文丽,郭茂祖,李晋,刘晓燕,2014,SVM与主动学习方法相结合的蛋白质相互作用预测,计算机科学,41(2):82-86)
Wang Y.Y.,Qi X.M.,Liu T.,Qi J.,Zhang C.,and Guo L.L.,2013,Expression of Tachypleus tridentatus factor recombinant CES peptide using intein-mediated protein trans-splicing,Jiyinzuxue Yu Yingyong Shengwuxue(Genomics and\sApplied Biology),32(6):707-712(王影影,齐兴梅,刘涛,祁静,张春,郭玲玲,2013,基于蛋白质反式剪接在大肠杆菌中表达鲎C因子CES多肽,基因组学与应用生物学,32(6):707-712)
Xia J.F.,Han K.,and Huang D.S.,2010,Sequence-based prediction of protein-protein interactins by means of rotation forest\sand autocorrelation descriptor,Protein Peptide Letters,17:137-145
Xu B.,Wei X.,Deng L.,Guan J.H.,and Zhou S.G.,2012,A semi-supervised boosting SVM for predicting hot spots at protein-protein Interfaces,BMC Systems Biology,6(Suppl 2):S6
Yang L.,Xia J.F.,and Gui J.,2010,Prediction of protein-protein\sinteractions form protein sequence using local descriptors,Protein and Peptide Letters,17(9):1085-1090
You Z.H.,Lei Y.K.,Zhu L.,Xia J.F.,and Wang B.,2013,Prediction\sof protein-protein interactions from amino acid sequences\swith ensemble extreme learning machines and principal component analysis,BMC Bioinformatics,14(Suppl 8):S10
You Z.H.,Zhu L.,Zheng C.H.,Yu H.J.,Deng S.P.,and Ji Z.,2014,Prediction of protein-protein interactions from amino acid sequences using a novel multi-scale continuous and discontinuous feature set,BMC Bioinformatics,15(Suppl 15):S9
Zhou Y.Z.,Gao Y.,and Zheng Y.Y.,2011,Prediction of protein-protein interactions using local description of amino\sacid sequence,Advances in Computer Science and Education Applications,Springer Berlin,Heidelberg,pp.254-262
基本信息:
DOI：10.13417/j.gab.034.001791
中图分类号:Q811.4;Q51
引用信息:
[1]薛燕娜,董洪伟,王兵,等.基于深度玻尔兹曼机的蛋白质相互作用预测[J].基因组学与应用生物学,2015,34(08):1791-1797.DOI:10.13417/j.gab.034.001791.
基金信息:
中央高校基本科研业务费专项资金资助
2015-08-25
2015-08-25