Bayesian Network Structure Inference with an Hierarchical Bayesian Model

  • Adriano Velasque Werhli
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6404)


Bayesian Networks (BNs) are applied to a wide range of applications. In the past few years great interest is dedicated to the problem of inferring the structure of BNs solely from the data. In this work we explore a probabilistic method which enables the inclusion of extra knowledge in the inference of BNs. We briefly present the theory of BNs and introduce our probabilistic model. We also present the method of Markov Chain Monte Carlo (MCMC) which is used to sample network structures and hyper-parameters of our probabilistic model. Finally we present and discuss the results focusing on aspects related with the accuracy of the reconstructed networks and how the proposed method behaves when provided with sources of knowledge of different quality.


Bayesian Networks Bayesian Hierarchical Model MCMC 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Heckerman, D.: Learning Gaussian networks. Technical Report MSR-TR-94-10, Microsoft Research, Redmond, Washington (July 1994)Google Scholar
  2. 2.
    Heckerman, D.: A tutorial on learning with Bayesian networks. Technical Report MSR-TR-95-06, Microsoft Research, Redmond, Washington (1995)Google Scholar
  3. 3.
    Madigan, D., York, J.: Bayesian graphical models for discrete data. International Statistical Review 63, 215–232 (1995)CrossRefzbMATHGoogle Scholar
  4. 4.
    Hastings, W.K.: Monte Carlo sampling methods using Markov chains and their applications. Biometrika 57, 97–109 (1970)CrossRefzbMATHGoogle Scholar
  5. 5.
    Husmeier, D., Dybowski, R., Roberts, S.: Probabilistic Modeling in Bioinformatics and Medical Informatics. In: Advanced Information and Knowledge Processing. Springer, New York (2005)Google Scholar
  6. 6.
    Imoto, S., Higuchi, T., Goto, T., Tashiro, K., Kuhara, S., Miyano, S.: Combining microarrays and biological knowledge for estimating gene networksvia Bayesian networks. In: Proceedings IEEE Computer Society Bioinformatics Conference (CSB 2003), pp. 104–113 (2003)Google Scholar
  7. 7.
    Werhli, A.V., Husmeier, D.: Reconstructing gene regulatory networks with Bayesian networks by combiningexpression data with multiple sources of prior knowledge. Statistical Applications in Genetics and Molecular Biology, Article 15 6(1) (May 2007)Google Scholar
  8. 8.
    Friedman, N., Linial, M., Nachman, I., Pe’er, D.: Using Bayesian networks to analyze expression data. Journal of Computational Biology 7(3/4), 601–620 (2000)CrossRefGoogle Scholar
  9. 9.
    Friedman, N., Koller, D.: Being Bayesian about network structure. Machine Learning 50, 95–126 (2003)CrossRefzbMATHGoogle Scholar
  10. 10.
    Husmeier, D.: Sensitivity and specificity of inferring genetic regulatory interactionsfrom microarray experiments with dynamic Bayesian networks. Bioinformatics 19, 2271–2282 (2003)CrossRefGoogle Scholar
  11. 11.
    Werhli, A.V., Husmeier, D.: Gene regulatory network reconstruction by Bayesian integration of prior knowledge and/or different experimental conditions. Journal of Bioinformatics and Computational Biology 6, 543–572 (2008)CrossRefGoogle Scholar
  12. 12.
    Heckerman, D.: A tutorial on learning with Bayesian networks. In: Jordan, M.I. (ed.) Learning in Graphical Models. Adaptive Computation and Machine Learning, pp. 301–354. MIT Press, Cambridge (1999)Google Scholar
  13. 13.
    Geiger, D., Heckerman, D.: Learning Gaussian networks. In: de Mantaras, R.L., Poole, D. (eds.) Uncertainty in Artificial Intelligence, pp. 235–243. Morgan Kaufmann, San Francisco (July 1994)Google Scholar
  14. 14.
    Yuh, C.H., Bolouri, H., Davidson, E.H.: Genomic cis-regulatory logic: experimental and computational analysis ofa sea urchin gene. Science 279, 1896–1902 (1998)CrossRefGoogle Scholar
  15. 15.
    Yuh, C.H., Bolouri, H., Davidson, E.H.: Cis-regulatory logic in the endo16 gene: switching from a specificationto a differentiation mode of control. Development 128, 617–629 (2001)Google Scholar
  16. 16.
    Werhli, A.V., Grzegorczyk, M., Husmeier, D.: Comparative evaluation of reverse engineering gene regulatory networks withrelevance networks, graphical Gaussian models and Bayesian networks. Bioinformatics 22(20), 2523–2531 (2006)CrossRefGoogle Scholar
  17. 17.
    Sachs, K., Perez, O., Pe’er, D., Lauffenburger, D., Nolan, G.P.: Causal protein-signaling networks derived from multiparameter single-celldata. Science 308(5721), 523–529 (2005)CrossRefGoogle Scholar
  18. 18.
    Pearl, J.: Causality: Models, Reasoning and Intelligent Systems. Cambridge University Press, London (2000)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Adriano Velasque Werhli
    • 1
  1. 1.Centro de Ciências Computacionais - C3Universidade Federal do Rio Grande, FURGRio GrandeBrazil

Personalised recommendations