Effects of Functional Bias on Supervised Learning of a Gene Network Model

  • Insuk Lee
  • Edward M. Marcotte
Part of the Methods in Molecular Biology book series (MIMB, volume 541)


Gene networks have proven to be an effective approach for modeling cellular systems, capable of capturing some of the extreme complexity of cells in a formal theoretical framework. Not surprisingly, this complexity, combined with our still-limited amount of experimental data measuring the genes and their interactions, makes the reconstruction of gene networks difficult. One powerful strategy has been to analyze functional genomics data using supervised learning of network relationships based upon reference examples from our current knowledge. However, this reliance on the set of reference examples for the supervised learning can introduce major pitfalls, with misleading reference sets resulting in suboptimal learning. There are three requirements for an effective reference set: comprehensiveness, reliability, and freedom from bias. Perhaps not too surprisingly, our current knowledge about gene function is highly biased toward several specific biological functions, such as protein synthesis. This functional bias in the reference set, especially combined with the corresponding functional bias in data sets, induces biased learning that can, in turn, lead to false positive biological discoveries, as we show here for the yeast Saccharomyces cerevisiae. This suggests that careful use of current knowledge and genomics data is required for successful gene network modeling using the supervised learning approach. We provide guidance for better use of these data in learning gene networks.

Key words

Gene network model supervised learning classification functional coupling functional bias reference set genomics data 



This work was supported by grants from the N.S.F. (IIS-0325116, EIA-0219061, 0241180), N.I.H. (GM06779-01), Welch (F-1515), and a Packard Fellowship (E.M.M.). We thank Cynthia V. Marcotte and Ray Hardesty for help with editing.


  1. 1.
    Jansen, R., Yu, H., et al. A Bayesian networks approach for predicting protein-protein interactions from genomic data. Science 2003; 302:449–53.PubMedCrossRefGoogle Scholar
  2. 2.
    Lee, I., Date, S. V., et al. A probabilistic functional network of yeast genes. Science 2004; 306:1555–8.PubMedCrossRefGoogle Scholar
  3. 3.
    Myers, C. L., Robson, D., et al. Discovery of biological networks from diverse functional genomic data. Genome Biol 2005; 6:R114.PubMedCrossRefGoogle Scholar
  4. 4.
    Rhodes, D. R., Tomlins, S. A., et al. Probabilistic model of the human protein-protein interaction network. Nat Biotechnol 2005; 23:951–9.PubMedCrossRefGoogle Scholar
  5. 5.
    Zhong, W., and Sternberg, P. W. Genome-wide prediction of C. elegans genetic interactions. Science 2006; 311:1481–4.PubMedCrossRefGoogle Scholar
  6. 6.
    Ashburner, M., Ball, C. A., et al. Gene ontology: tool for the unification of biology. The Gene Ontology Consortium. Nat Genet 2000; 25:25–9.PubMedCrossRefGoogle Scholar
  7. 7.
    Cherry, J. M., Adler, C., et al. SGD: Saccharomyces genome database. Nucleic Acids Res 1998; 26:73–9.PubMedCrossRefGoogle Scholar
  8. 8.
    Kanehisa, M., and Goto, S. KEGG: Kyoto encyclopedia of genes and genomes. Nucleic Acids Res 2000; 28:27–30.PubMedCrossRefGoogle Scholar
  9. 9.
    Efron, B., and Tibshirani, R. An introduction to the bootstrap. New York: Chapman & Hall, 1993.Google Scholar
  10. 10.
    Krogan, N. J., Cagney, G., et al. Global landscape of protein complexes in the yeast Saccharomyces cerevisiae. Nature 2006; 440:637–43.PubMedCrossRefGoogle Scholar
  11. 11.
    Reguly, T., Breitkreutz, A., et al. Comprehensive curation and analysis of global interaction networks in Saccharomyces cerevisiae. J Biol 2006; 5:11.PubMedCrossRefGoogle Scholar
  12. 12.
    Mewes, H. W., Amid, C., et al. MIPS: analysis and annotation of proteins from whole genomes. Nucleic Acids Res 2004; 32:D41–4.PubMedCrossRefGoogle Scholar
  13. 13.
    Jansen, R., Greenbaum, D., et al. Relating whole-genome expression data with protein-protein interactions. Genome Res 2002; 12:37–46.PubMedCrossRefGoogle Scholar
  14. 14.
    Watts, D. J., and Strogatz, S. H. Collective dynamics of 'small-world' networks. Nature 1998; 393:440–2.PubMedCrossRefGoogle Scholar
  15. 15.
    Jansen, R., and Gerstein, M. Analyzing protein function on a genomic scale: the importance of gold-standard positives and negatives for network prediction. Curr Opin Microbiol 2004; 7:535–45.PubMedCrossRefGoogle Scholar
  16. 16.
    Witten, I. H., and Frank, E. Data Mining: Practical Machine Learning Tools and Techniques. San Francisco, CA: Morgan Kaufmann, 2005.Google Scholar

Copyright information

© Humana Press, a part of Springer Science+Business Media, LLC 2009

Authors and Affiliations

  • Insuk Lee
    • 1
  • Edward M. Marcotte
    • 2
  1. 1.Center of Systems and Synthetic BiologyInstitute for Molecular Biology, University of Texas at AustinAustinUSA
  2. 2.Center for Systems and Synthetic Biology and Department of Chemistry and BiochemistryInstitute for Molecular Biology, University of Texas at AustinAustinUSA

Personalised recommendations