Prediction of Protein Interaction with Neural Network-Based Feature Association Rule Mining

  • Jae-Hong Eom
  • Byoung-Tak Zhang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4234)


Prediction of protein interactions is one of the central problems in post–genomic biology. In this paper, we present an association rule-based protein interaction prediction method. We adopted neural network to cluster protein interaction data, and used information theory based feature selection method to reduce protein feature dimension. After model training, feature association rules are generated to interaction prediction by decoding a set of learned weights of trained neural network and by mining association rules. For model training, an initial network model was constructed with public Yeast protein interaction data considering their functional categories, set of features, and interaction partners. The prediction performance was compared with traditional simple association rule mining method. The experimental results show that proposed method has about 96.1% interaction prediction accuracy compared to simple association mining approach which achieved about 91.4% accuracy.


Feature Selection Association Rule Association Rule Mining Trained Neural Network Adaptive Resonance Theory 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Goffeau, A., Barrell, B.G., et al.: Life with 6000 genes. Science 274, 546–567 (1996)CrossRefGoogle Scholar
  2. 2.
    Eisen, M.B., Spellman, P.T., et al.: Cluster analysis and display of genomewide expression patterns. Proc. Natl. Acad. Sci. USA 95, 14863–14868 (1998)CrossRefGoogle Scholar
  3. 3.
    Pavlidis, P., Weston, J.: Gene functional classification from heterogeneous data. In: Pro. of the 5th Int’l Conf. on Comp. Molecular Biology, pp. 249–255 (2001)Google Scholar
  4. 4.
    Park, J., et al.: Mapping protein family interactions: intramolecular and intermolecular protein family interaction repertoires in the PDB and yeast. J. Mol. Biol. 307, 929–939 (2001)CrossRefGoogle Scholar
  5. 5.
    Iossifov, I., Krauthammer, M., et al.: Probabilistic inference of molecular networks from noisy data sources. Bioinformatics 20(8), 1205–1213 (2004)CrossRefGoogle Scholar
  6. 6.
    Ng, S.K., Zhang, Z., et al.: Integrative approach for computationally inferring protein domain interactions. Bioinformatics 19(8), 923–929 (2003)CrossRefGoogle Scholar
  7. 7.
    Eom, J.-H., et al.: Prediction of implicit protein–protein interaction by optimal associative feature mining. In: Yang, Z.R., Yin, H., Everson, R.M. (eds.) IDEAL 2004. LNCS, vol. 3177, pp. 85–91. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  8. 8.
    Carpenter, G.A., Grossberg, S.: A massively parallel architecture for a self-organizing neural pattern recognition machine. Computer Vision, Graphics and Image Processing 37, 54–115 (1987)CrossRefGoogle Scholar
  9. 9.
    Barbara, M.: ART1 and pattern clustering. In: Proceedings of the 1988 connectionist models summer 1988, pp. 174–185. Morgan Kaufmann, San Francisco (1988)Google Scholar
  10. 10.
    Heins, L.G., Tauritz, D.R.: Adaptive resonance theory (ART): an introduction. Internal Report 95-35, Dept. of Comp. Sci., Leiden University, Netherlands, 174–85 (1995)Google Scholar
  11. 11.
    Mewes, H.W., Amid, C., et al.: MIPS: analysis and annotation of proteins from whole genomes. Nucleic Acids Res. 32(1), D41–44 (2004)CrossRefGoogle Scholar
  12. 12.
    Christie, K.R., Weng, S., et al.: Saccharomyces Genome Database (SGD) provides tools to identify and analyze sequences from Saccharomyces cerevisiae and related sequences from other organisms. Nucleic Acids Res. 32(1), D311–314 (2004)CrossRefGoogle Scholar
  13. 13.
    Rangarajan, S.K., Phoha, V.V., et al.: Adaptive neural network clustering of web users. IEEE Computer 37(4), 34–40 (2004)Google Scholar
  14. 14.
    Yu, L., Liu, H.: Feature selection for high dimensional data: a fast correlation-based filter solution. In: Proceeding of ICML-03, pp. 856–863 (2003)Google Scholar
  15. 15.
    Csank, C., Costanzo, M.C., et al.: Three yeast proteome databases: YPD, PombePD, and CalPD (MycoPathPD). Methods Enzymol. 350, 347–373 (2002)CrossRefGoogle Scholar
  16. 16.
    Ito, T., Chiba, T., et al.: A comprehensive two-hybrid analysis to explore the yeast protein interactome. Proc. Natl Acad. Sci. USA 98, 4569–4574 (2001)CrossRefGoogle Scholar
  17. 17.
    Uetz, P., Giot, L., et al.: A comprehensive analysis of protein–protein interactions in Saccharomyces cerevisiae. Nature 403, 623–627 (2000)CrossRefGoogle Scholar
  18. 18.
    Press, W.H., Flannery, B.P., et al.: Numerical recipes in C: The Art of Scientific Computing, 2nd edn., pp. 633–634. Cambridge University Press, Cambridge (1992)Google Scholar
  19. 19.
    Eom, J.-H., et al.: Adaptive Neural Network based Clustering of Yeast Protein-Protein Interactions. In: Das, G., Gulati, V.P. (eds.) CIT 2004. LNCS, vol. 3356, pp. 49–57. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  20. 20.
    Oyama, T., Kitano, K., et al.: Extraction of knowledge on protein–protein interaction by association rule discovery. Bioinformatics 18, 705–714 (2002)CrossRefGoogle Scholar
  21. 21.
    Eom, J.-H., Zhang, B.-T.: Prediction of implicit protein–protein interaction using optimal associative feature rule. Journal of Korea Information Science Society: Software and Application 33(4), 365–377 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jae-Hong Eom
    • 1
  • Byoung-Tak Zhang
    • 1
  1. 1.Biointelligence Lab., School of Computer Science and EngineeringSeoul National UniversitySeoulSouth Korea

Personalised recommendations