基于结构域理化性质的蛋白质相互作用方向预测
|
摘要
为了更好地理解蛋白质相互作用,用蛋白质相互作用间信号传递方向进一步注释蛋白质相互作用网络,提出了一种基于结构域理化性质预测蛋白质相互作用方向的方法。首先提取蛋白质结构域的10种理化性质,构成表示方向信息的特征向量;然后建立支持向量机预测模型,并利用网格搜索对模型进行参数寻优;最后用拥有最优参数的模型进行预测。实验结果表明,该模型准确率达到88.17%,AUC值为0.837.与PIDS方法比较结果表明,蛋白质结构域的10种理化性质能够有效用于蛋白质相互作用方向的预测,为预测蛋白质相互作用方向提供了一种新思路。
For a better understanding about the protein interactions, the signal transmission direction between protein interactions is used to annotate the protein interaction network. A method based on the physicochemical properties of the domain is proposed to predict the protein interaction direction. Firstly, the physicochemical properties of protein domains is extracted to form the eigenvectors representing the direction information. Then a support vector machine prediction model can be established, and the model is optimized by a grid search method. Finally, the prediction is performed with this model and the optimized parameters. The experimental results show that the accuracy of the model is 88.17% and the AUC value is 0.837. Compared with the PIDS method, this method with the ten physicochemical properties of the protein domain is more efficient for the prediction of protein interaction direction. This work provides an effective new way to predict the protein interaction direction.
For a better understanding about the protein interactions, the signal transmission direction between protein interactions is used to annotate the protein interaction network. A method based on the physicochemical properties of the domain is proposed to predict the protein interaction direction. Firstly, the physicochemical properties of protein domains is extracted to form the eigenvectors representing the direction information. Then a support vector machine prediction model can be established, and the model is optimized by a grid search method. Finally, the prediction is performed with this model and the optimized parameters. The experimental results show that the accuracy of the model is 88.17% and the AUC value is 0.837. Compared with the PIDS method, this method with the ten physicochemical properties of the protein domain is more efficient for the prediction of protein interaction direction. This work provides an effective new way to predict the protein interaction direction.
引文
[1] HUGHEY J J,LEE T K,COVERT M W.Computational modeling of mammalian signaling networks[J].Wiley Interdisciplinary Reviews Systems Biology & Medicine,2010,2(2):194-209.
[2] VINAYAGAM A,ZIRIN J,ROESEL C,et al.Integrating protein-protein interaction networks with phenotypes reveals signs of interactions[J].Nature Methods,2014,11(1):94-99.
[3] GITTER A,KLEIN-SEETHARAMAN J,GUPTA A,et al.Discovering pathways by orienting edges in protein interaction networks[J].Nucleic Acids Research,2011,39(4):e22.
[4] LIU W,LI D,WANG J,et al.Proteome-wide prediction of signal flow direction in protein interaction networks based on interacting domains[J].Molecular & Cellular Proteomics,2009,8(9):2063-2070.
[5] MEI S,ZHU H.A simple feature construction method for predicting upstream/downstream signal flow in human protein-protein interaction networks[J].Scientific Reports,2015,5:17983.
[6] LI N F,DAI Y F,WANG R Q,et al.Study on action recognition based on Kinect and its application in rehabilitation training[C]//IEEE.5th International Conference on Big Data and Cloud Computing.IEEE,2015:265-269.
[7] JAMIE S,ANDREW F,MAT C,et al.Real-time human pose recognition in parts from single depth image[C]//IEEE.Conference on Computer Vision and Pattern Re-cognition.IEEE,2011:1297-1304.
[8] 陆林英.基于序列从头预测法的蛋白质相互作用研究[D].长春:东北师范大学,2008.LU L Y.Research on protein-protein interaction based on primary structure[D].Changchun:Northeast Normal University,2008.
[9] MARTIN S,ROE D,FAULON J L.Predicting protein-protein interactions using signature products[J].Current Opinion in Structural Biology,2005,15(4):441-446.
[10] 刘伟.大规模信号网络的结构属性分析和自动重建[D].长沙:国防科学技术大学,2009.LIU W.Structural property analyses and automated regeneration of large-scale signaling networks[D].Changsha:National University of Defense Technology,2009.
[11] LIU W,XIE H W.Prediction of regulation relationship between protein interactions in signaling networks[J].Biochemical and Biophysical Research Communications,2013,440(3):388-392.
[12] 边帅,赵月,白雪媛,等.梅花鹿抗病毒蛋白的生物信息学分析[J].科学技术与工程,2018,18(29):178-185.BIAN S,ZHAO Y,BAI X Y et al.Bioinformatic analysis of sika deer antiviral proteins[J].Science Technology and Engineering,2018,18(29):178-185.
[13] FINN R D,BATEMAN A,CLEMENTS J,et al.Pfam:the protein families database[J].Nucleic Acids Research,2014,42(D1):222-230.
[14] CHATTERJEE P,BASU S,KUNDU M,et al.PPI_SVM:Prediction of protein-protein interactions using machine learning,domain-domain affinities and frequency tables[J].Cellular & Molecular Biology Letters,2011,16(2):264-278.
[2] VINAYAGAM A,ZIRIN J,ROESEL C,et al.Integrating protein-protein interaction networks with phenotypes reveals signs of interactions[J].Nature Methods,2014,11(1):94-99.
[3] GITTER A,KLEIN-SEETHARAMAN J,GUPTA A,et al.Discovering pathways by orienting edges in protein interaction networks[J].Nucleic Acids Research,2011,39(4):e22.
[4] LIU W,LI D,WANG J,et al.Proteome-wide prediction of signal flow direction in protein interaction networks based on interacting domains[J].Molecular & Cellular Proteomics,2009,8(9):2063-2070.
[5] MEI S,ZHU H.A simple feature construction method for predicting upstream/downstream signal flow in human protein-protein interaction networks[J].Scientific Reports,2015,5:17983.
[6] LI N F,DAI Y F,WANG R Q,et al.Study on action recognition based on Kinect and its application in rehabilitation training[C]//IEEE.5th International Conference on Big Data and Cloud Computing.IEEE,2015:265-269.
[7] JAMIE S,ANDREW F,MAT C,et al.Real-time human pose recognition in parts from single depth image[C]//IEEE.Conference on Computer Vision and Pattern Re-cognition.IEEE,2011:1297-1304.
[8] 陆林英.基于序列从头预测法的蛋白质相互作用研究[D].长春:东北师范大学,2008.LU L Y.Research on protein-protein interaction based on primary structure[D].Changchun:Northeast Normal University,2008.
[9] MARTIN S,ROE D,FAULON J L.Predicting protein-protein interactions using signature products[J].Current Opinion in Structural Biology,2005,15(4):441-446.
[10] 刘伟.大规模信号网络的结构属性分析和自动重建[D].长沙:国防科学技术大学,2009.LIU W.Structural property analyses and automated regeneration of large-scale signaling networks[D].Changsha:National University of Defense Technology,2009.
[11] LIU W,XIE H W.Prediction of regulation relationship between protein interactions in signaling networks[J].Biochemical and Biophysical Research Communications,2013,440(3):388-392.
[12] 边帅,赵月,白雪媛,等.梅花鹿抗病毒蛋白的生物信息学分析[J].科学技术与工程,2018,18(29):178-185.BIAN S,ZHAO Y,BAI X Y et al.Bioinformatic analysis of sika deer antiviral proteins[J].Science Technology and Engineering,2018,18(29):178-185.
[13] FINN R D,BATEMAN A,CLEMENTS J,et al.Pfam:the protein families database[J].Nucleic Acids Research,2014,42(D1):222-230.
[14] CHATTERJEE P,BASU S,KUNDU M,et al.PPI_SVM:Prediction of protein-protein interactions using machine learning,domain-domain affinities and frequency tables[J].Cellular & Molecular Biology Letters,2011,16(2):264-278.