Predicting protein–protein interaction sites using modified support vector machine

Original Article


Protein–protein interaction plays a fundamental role in many biological processes and diseases. Characterizing protein interaction sites is crucial for the understanding of the mechanism of protein–protein interaction and their cellular functions. In this paper, we proposed a method based on integrated support vector machine (SVM) with a hybrid kernel to predict protein interaction sites. First, a number of features of the protein interaction sites were extracted. Secondly, the technique of sliding window was used to construct a protein feature space based on the influence of the adjacent residues. Thirdly, to avoid the impact of imbalance of the data set on prediction accuracy, we employed boost-strap to re-sample the data. Finally, we built a SVM classifier, whose hybrid kernel comprised a Gaussian kernel and a Polynomial kernel. In addition, an improved particle swarm optimization (PSO) algorithm was applied to optimize the SVM parameters. Experimental results show that the PSO-optimized SVM classifier outperforms existing methods.


Protein interaction sites Support vector machine Sliding window Boost-strap Particle swarm optimization 


  1. 1.
    Alberts BD, Bray D, Lewis J et al (1989) Molecular biology of the cell. Garland, New YorkGoogle Scholar
  2. 2.
    Ni QS, Wang ZZ, Wang GY et al (2008) Prediction of protein–protein interactions based on local support vector machine. J Biomed Eng Res 02(9):1106–1109Google Scholar
  3. 3.
    Yan CH, Dobbs D, Honavar V et al (2004) A two stage classifier for identification of protein–protein interface residues. Bioinformatics 20(1):371–378CrossRefGoogle Scholar
  4. 4.
    Chen XW, Jeong JC (2009) Sequence-based prediction of protein interaction sites with an integrative method. Bioinformatics 25(5):585–591CrossRefGoogle Scholar
  5. 5.
    Chen YH, Xu JR, Bin Yang et al (2012) A novel method for prediction of protein interaction sites based on integrated RBF neural networks. Comput Biol Med 42:402–407CrossRefGoogle Scholar
  6. 6.
    Meng W, Wang F, Peng X (2008) Prediction of protein–protein interaction sites using support vector machine. Appl Sci 26(4):403–408Google Scholar
  7. 7.
    Minakuehi Y, Satou K, Konagaya A (2002) Prediction of protein–protein interaction sites using support vector machines. Genome Inform 13:322–323Google Scholar
  8. 8.
    LiQin Jin (2007) Biological chemistry. Zhejiang University Press, Hangzhou (in Chinese) Google Scholar
  9. 9.
    Marangoni F, Barberis M, Botta M (2003) Large scale prediction of protein interactions by a SVM-based method. In: Neural Nets, vol 2859. Springer, Berlin Heidelberg, pp 296–301Google Scholar
  10. 10.
    Li Liu (2009) The research and validation of support vector machine (SVM) algorithm with different kernels. Jiangnan University, Wuxi, Jiangsu (in Chinese) Google Scholar
  11. 11.
    Cortes C, Vapnik V (1995) Support vector network. Mach, LearnGoogle Scholar
  12. 12.
    Chatterjee P, Basu S, Kundu M et al (2011) PPI_SVM: prediction of protein–protein interactions using machine learning domain–domain affinities and frequency tables. Cell Mol Biol Lett 16:264–278CrossRefGoogle Scholar
  13. 13.
    Aimin Zhou, Bo-Yang Qub, Hui Li et al (2011) Multiobjective evolutionary algorithms: a survey of the state of the art. Swarm Evol Comput 1(1):32–49CrossRefGoogle Scholar
  14. 14.
    Xing X, Chen Y, Yang B (2010) Dimensional reduction based on conservative adaptive K-nearest neighbor algorithm. Univ Jinan Sci Technol 2:159–162 (in Chinese) Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.College of Mathematics and Computer ScienceFuzhou UniversityFuzhouChina
  2. 2.College of Biological Science and TechnologyFuzhou UniversityFuzhouChina

Personalised recommendations