Data Discretization for Dynamic Bayesian Network Based Modeling of Genetic Networks

  • Nguyen Xuan Vinh
  • Madhu Chetty
  • Ross Coppel
  • Pramod P. Wangikar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7664)


Dynamic Bayesian networks (DBN) are widely applied in Systems biology for modeling various biological networks, including gene regulatory networks and metabolic networks. The application of DBN models often requires data discretization. Although various discretization techniques exist, currently there is no consensus on which approach is most suitable. Popular discretization strategies within the bioinformatics community, such as interval and quantile discretization, are likely not optimal. In this paper, we propose a novel approach for data discretization for mutual information based learning of DBN. In this approach, the data are discretized so that the mutual information between parent and child nodes is maximized, subject to a suitable penalty put on the complexity of the discretization. A dynamic programming approach is used to find the optimal discretization threshold for each individual variable. Our approach iteratively learns both the network and the discretization scheme until a locally optimal solution is reached. Tests on real genetic networks confirm the effectiveness of the proposed method.


Dynamic Bayesian network Gene regulatory network Discretization Mutual information Microarray 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    de Campos, L.M.: A Scoring Function for Learning Bayesian Networks Based on Mutual Information and Conditional Independence Tests. J. Mach. Learn. Res. 7, 2149–2187 (2006)MathSciNetzbMATHGoogle Scholar
  2. 2.
    Cantone, I., et al.: A Yeast Synthetic Network for in Vivo Assessment of Reverse-engineering and Modeling Approaches. Cell 137, 172–181 (2009)CrossRefGoogle Scholar
  3. 3.
    Friedman, N., Goldszmidt, M.: Discretizing Continuous Attributes while Learning Bayesian Networks. In: Proc. ICML, pp. 157–165. Morgan Kaufmann (1996)Google Scholar
  4. 4.
    Grzegorczyk, M., Husmeier, D.: Improvements in the Reconstruction of Time-varying Gene Regulatory Networks: Dynamic Programming and Regularization by Information Sharing Among Genes. Bioinformatics 27(5), 693–699 (2011)CrossRefGoogle Scholar
  5. 5.
    Husmeier, D.: Sensitivity and Specificity of Inferring Genetic Regulatory Interactions from Microarray Experiments with Dynamic Bayesian Networks. Bioinformatics 19(17), 2271–2282 (2003)CrossRefGoogle Scholar
  6. 6.
    Murphy, K., Mian, S.: Modelling Gene Expression Data Using Dynamic Bayesian Networks. Tech. rep., Computer Science Division, University of California, Berkeley, CA (1999)Google Scholar
  7. 7.
    Myers, J.L., Well, A.: Research Design and Statistical Analysis, vol. 1. Psychology Press (2003)Google Scholar
  8. 8.
    Reshef, D.N., et al.: Detecting Novel Associations in Large Data Sets. Science 334(6062), 1518–1524 (2011)CrossRefGoogle Scholar
  9. 9.
    Ronen, M., Rosenberg, R., Shraiman, B.I., Alon, U.: Assigning Numbers to the Arrows: Parameterizing a Gene Regulation Network by Using Accurate Expression Kinetics. PNAS 99(16), 10555–10560 (2002)CrossRefGoogle Scholar
  10. 10.
    Vinh, N.X., Chetty, M., Coppel, R., Wangikar, P.P.: Gene Regulatory Network Modeling via Global Optimization of High-order Dynamic Bayesian Network. BMC Bioinformatics 13(1), 131 (2012)CrossRefGoogle Scholar
  11. 11.
    Vinh, N.X., Chetty, M., Coppel, R., Wangikar, P.P.: GlobalMIT: Learning Globally Optimal Dynamic Bayesian Network with the Mutual Information Test Criterion. Bioinformatics 27(19), 2765–2766 (2011)CrossRefGoogle Scholar
  12. 12.
    Vinh, N.X., Epps, J., Bailey, J.: Information Theoretic Measures for Clusterings Comparison: Variants, Properties, Normalization and Correction for Chance. Journal of Machine Learning Research 11, 2837–2854 (2010)MathSciNetzbMATHGoogle Scholar
  13. 13.
    Wilczynski, B., Dojer, N.: BNFinder: Exact and Efficient Method for Learning Bayesian Networks. Bioinformatics 25(2), 286–287 (2009)CrossRefGoogle Scholar
  14. 14.
    Yao, Y.Y.: Information-theoretic Measures for Knowledge Discovery and Data Mining. In: Karmeshu (ed.) Entropy Measures, Maximum Entropy Principle and Emerging Applications, pp. 115–136. Springer (2003)Google Scholar
  15. 15.
    Yu, J., Smith, V.A., Wang, P.P., Hartemink, A.J., Jarvis, E.D.: Advances to Bayesian Network Inference for Generating Causal Networks from Observational Biological data. Bioinformatics 20(18), 3594–3603 (2004)CrossRefGoogle Scholar
  16. 16.
    Zou, M., Conzen, S.D.: A New Dynamic Bayesian Network (DBN) Approach for Identifying Gene Regulatory Networks from Time Course Microarray Data. Bioinformatics 21(1), 71–79 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Nguyen Xuan Vinh
    • 1
  • Madhu Chetty
    • 1
  • Ross Coppel
    • 2
  • Pramod P. Wangikar
    • 3
  1. 1.Gippsland School of Information TechnologyMonash UniversityAustralia
  2. 2.Department of MicrobiologyMonash UniversityAustralia
  3. 3.Chemical Engineering DepartmentIndian Institute of TechnologyMumbaiIndia

Personalised recommendations