Prediction of Chemical-Protein Binding Activity Using Contrast Graph Patterns

  • Andrzej Dominik
  • Zbigniew Walczak
  • Jacek Wojciechowski
Part of the Advances in Experimental Medicine and Biology book series (AEMB, volume 696)


The problem of classifying chemical compounds is studied in this chapter. Compounds are represented as two-dimensional topological graphs of atoms (corresponding to nodes) and bonds (corresponding to edges). We use a method called contrast common pattern classifier (CCPC) to predict chemical-protein binding activity. This approach is strongly associated with the classical emerging patterns techniques known from decision tables. It uses two different types of structural patterns (subgraphs): contrast and common. Results show that the considered algorithm outperforms all other existing methods in terms of classification accuracy.


Classification Accuracy High Classification Accuracy Positive Class Subgraph Isomorphic Test Graph 
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.


  1. 1.
    Borgelt, C., Berthold, M.R.: Mining molecular fragments: finding relevant substructures of molecules. In: Proceedings of the 2nd IEEE International Conference on Data Mining, pp. 51–58. IEEE Computer Society, Washington, DC (2002)Google Scholar
  2. 2.
    Fei, H., Huan, J.: Structure feature selection for graph classification. In: CIKM ’08, pp. 991–1000. ACM, California (2008)Google Scholar
  3. 3.
    Jorissen, R.N., Gilson, M.K.: Virtual screening of molecular databases using a support vector machine. Journal of Chemical Information and Modeling 45, 549–561 (2005)PubMedCrossRefGoogle Scholar
  4. 4.
    Smalter, A., Huan, J., Lushington, G.: CPM: A graph pattern matching kernel with diffusion for accurate graph classification. Information Telecommunication and Technology Center, University of Kansas, Lawrence (2008)Google Scholar
  5. 5.
    Swamidass, S.J., Chen, J., Bruand, J., Phung, P., Ralaivola, L., Baldi, P.: Kernels for small molecules and the prediction of mutagenicity, toxicity and anti-cancer activity. Bioinformatics 21, 359–368 (2005)CrossRefGoogle Scholar
  6. 6.
    Dominik, A., Walczak, Z., Wojciechowski, J.: Classification of web documents using a graph-based model and structural patterns. In: Kok, J.N., Koronacki, J., López de Mántaras, R., Matwin, S., Mladenic D., Skowron, A. (eds.) Knowledge Discovery in Databases: PKDD 2007, pp. 67–78. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  7. 7.
    Dominik, A., Walczak, Z., Wojciechowski, J.: Classifying chemical compounds using contrast and common patterns. In: Beliczynski, B., Dzielinski, A., Iwanowski, M., Ribeiro, B. (eds.) Adaptive and Natural Computing Algorithms, pp. 772–781. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  8. 8.
    Dominik, A., Walczak, Z., Wojciechowski, J.: Detection of mutagenicity, toxicity and anti-cancer activity using structural contrast graph patterns. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J. (eds.) Computational Intelligence: Methods and Applications, pp. 255–266. Academic Publishing House EXIT, Warsaw (2008)Google Scholar
  9. 9.
    Dominik, A., Walczak, Z., Wojciechowski, J.: Classification of graph structures. In: Wang, J. (eds.) Encyclopedia of Data Warehousing and Mining, 2nd Ed., pp. 202–207. Information Science Reference, Hershey (2008)Google Scholar
  10. 10.
    Dominik, A.: Graph classification using structural contrast patterns. Warsaw University of Technology, Warsaw (2009)Google Scholar
  11. 11.
    Fortin, S.: The graph isomorphism problem. University of Alberta, Alberta (1996)Google Scholar
  12. 12.
    Ralaivola, L., Swamidass, S.J., Saigo, H., Baldi, P.: Graph kernels for chemical informatics. Neural Networks 18, 1093–1110 (2005)PubMedCrossRefGoogle Scholar
  13. 13.
    Ramamohanarao, K., Bailey, J.: Discovery of emerging patterns and their use in classification. In: Gedeon, T.D., Fung, L.C.C. (eds.) Australian Conference on Artificial Intelligence, pp. 1–12. Springer, Heidelberg (2003)Google Scholar
  14. 14.
    Schenker, A., Last, M., Bunke, H., Kandel, A.: Classification of web documents using graph matching. International Journal of Pattern Recognition and Artificial Intelligence 18, 475–496 (2004)CrossRefGoogle Scholar
  15. 15.
    Ting, R.M.H., Bailey, J.: Mining minimal contrast subgraph patterns. In: Ghosh, J., Lambert, D., Skillicorn, D.B., Srivastava, J. (eds.) SDM, pp. 202–207. SIAM, Maryland (2006)Google Scholar
  16. 16.
    Ullmann, J.R.: An algorithm for subgraph isomorphism. JACM 23, 31–42 (1976)CrossRefGoogle Scholar
  17. 17.
    Plasma protein binding – Wikipedia, The Free Encyclopedia (2009)Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Andrzej Dominik
    • 1
  • Zbigniew Walczak
  • Jacek Wojciechowski
  1. 1.Institute of RadioelectronicsWarsaw University of TechnologyWarsawPoland

Personalised recommendations