Using Expert Knowledge to Guide Covering and Mutation in a Michigan Style Learning Classifier System to Detect Epistasis and Heterogeneity

  • Ryan J. Urbanowicz
  • Delaney Granizo-Mackenzie
  • Jason H. Moore
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7491)

Abstract

Learning Classifier Systems (LCSs) are a unique brand of multifaceted evolutionary algorithms well suited to complex or heterogeneous problem domains. One such domain involves data mining within genetic association studies which investigate human disease. Previously we have demonstrated the ability of Michigan-style LCSs to detect genetic associations in the presence of two complicating phenomena: epistasis and genetic heterogeneity. However, LCSs are computationally demanding and problem scaling is a common concern. The goal of this paper was to apply and evaluate expert knowledge-guided covering and mutation operators within an LCS algorithm. Expert knowledge, in the form of Spatially Uniform ReliefF (SURF) scores, was incorporated to guide learning towards regions of the problem domain most likely to be of interest. This study demonstrates that expert knowledge can improve learning efficiency in the context of a Michigan-style LCS.

Keywords

Expert Knowledge Learning Classifier System Genetics Epistasis Heterogeneity Evolutionary Algorithm Mutation Covering 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Urbanowicz, R., Moore, J.: LCSs: A Complete Introduction, Review, and Roadmap. Journal of Artificial Evolution and Applications 2009 (2009)Google Scholar
  2. 2.
    Bacardit, J., Goldberg, D.E., Butz, M.V., Llorà, X., Garrell, J.M.: Speeding-Up Pittsburgh Learning Classifier Systems: Modeling Time and Accuracy. In: Yao, X., Burke, E.K., Lozano, J.A., Smith, J., Merelo-Guervós, J.J., Bullinaria, J.A., Rowe, J.E., Tiňo, P., Kabán, A., Schwefel, H.-P. (eds.) PPSN VIII. LNCS, vol. 3242, pp. 1021–1031. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  3. 3.
    Bacardit, J., Stout, M., Hirst, J., Sastry, K., Llorà, X., Krasnogor, N.: Automated alphabet reduction method with evolutionary algorithms for protein structure prediction. In: Proceedings of the 9th Annual Conference on Genetic and Evolutionary Computation, pp. 346–353. ACM (2007)Google Scholar
  4. 4.
    Llorà, X., Sastry, K.: Fast rule matching for lcss via vector instructions. In: Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation, pp. 1513–1520. ACM (2006)Google Scholar
  5. 5.
    Bacardit, J., Burke, E., Krasnogor, N.: Improving the scalability of rule-based evolutionary learning. Memetic Computing 1(1), 55–67 (2009)CrossRefGoogle Scholar
  6. 6.
    Franco, M., Krasnogor, N., Bacardit, J.: Speeding up the evaluation of evolutionary learning systems using gpgpus. In: Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation, pp. 1039–1046. ACM (2010)Google Scholar
  7. 7.
    Shriner, D., Vaughan, L., Padilla, M., et al.: Problems with genome-wide association studies. Science 316(5833) (2007) 1840cGoogle Scholar
  8. 8.
    Eichler, E., Flint, J., Gibson, G., Kong, A., Leal, S., Moore, J., Nadeau, J.: Missing heritability and strategies for finding the underlying causes of complex disease. Nature Reviews Genetics 11(6), 446–450 (2010)CrossRefGoogle Scholar
  9. 9.
    Thornton-Wells, T., Moore, J., Haines, J.: Genetics, statistics and human disease: analytical retooling for complexity. TRENDS in Genetics 20(12), 640–647 (2004)CrossRefGoogle Scholar
  10. 10.
    Urbanowicz, R., Moore, J.: The application of michigan-style lcss to address genetic heterogeneity and epistasis in association studies. In: Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation, pp. 195–202. ACM (2010)Google Scholar
  11. 11.
    Urbanowicz, R., Granizo-Mackenzie, A., Moore, J.: An Analysis Pipeline with Visualization-Guided Knowledge Discovery for Michigan-Style LCSs. IEEE CIM Special Issue on Computational Intelligence in Bioinformatics (2012)Google Scholar
  12. 12.
    Urbanowicz, R., Granizo-Mackenzie, A., Moore, J.: Instance-Linked Attribute Tracking and Feedback for Michigan-Style Supervised LCSs. In: Proceedings of the 14th Annual Conference on Genetic and Evolutionary Computation (2012)Google Scholar
  13. 13.
    Jamshidi, M., et al.: Incorporating a-priori expert knowledge in genetic algorithms. In: Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 1997, pp. 300–305. IEEE (1997)Google Scholar
  14. 14.
    Moore, J.H., White, B.C.: Exploiting Expert Knowledge in Genetic Programming for Genome-Wide Genetic Analysis. In: Runarsson, T.P., Beyer, H.-G., Burke, E.K., Merelo-Guervós, J.J., Whitley, L.D., Yao, X. (eds.) PPSN IX. LNCS, vol. 4193, pp. 969–977. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  15. 15.
    Greene, C.S., White, B.C., Moore, J.H.: An Expert Knowledge-Guided Mutation Operator for Genome-Wide Genetic Analysis Using Genetic Programming. In: Rajapakse, J.C., Schmidt, B., Volkert, L.G. (eds.) PRIB 2007. LNCS (LNBI), vol. 4774, pp. 30–40. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  16. 16.
    Greene, C.S., White, B.C., Moore, J.H.: Sensible initialization using expert knowledge for genome-wide analysis of epistasis using genetic programming. In: IEEE Congress on Evolutionary Computation, CEC 2009, pp. 1289–1296. IEEE (2009)Google Scholar
  17. 17.
    Greene, C.S., Penrod, N., Kiralis, J., Moore, J.: Spatially uniform relieff (surf) for computationally-efficient filtering of gene-gene interactions. BioData Mining 2(1), 1–9 (2009)CrossRefGoogle Scholar
  18. 18.
    Bernadó-Mansilla, E., Garrell-Guiu, J.: Accuracy-based LCSs: models, analysis and applications to classification tasks. Evolutionary Computation 11(3), 209–238 (2003)CrossRefGoogle Scholar
  19. 19.
    Wilson, S.: Classifier fitness based on accuracy. Evolutionary Computation 3(2), 149–175 (1995)CrossRefGoogle Scholar
  20. 20.
    Orriols-Puig, A., Bernadó-Mansilla, E.: Revisiting ucs: Description, fitness sharing, and comparison with xcs. Learning Classifier Systems, 96–116 (2008)Google Scholar
  21. 21.
    Moore, J.H., White, B.C.: Tuning ReliefF for Genome-Wide Genetic Analysis. In: Marchiori, E., Moore, J.H., Rajapakse, J.C. (eds.) EvoBIO 2007. LNCS, vol. 4447, pp. 166–175. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  22. 22.
    Urbanowicz, R.J., Moore, J.H.: The Application of Pittsburgh-Style Learning Classifier Systems to Address Genetic Heterogeneity and Epistasis in Association Studies. In: Schaefer, R., Cotta, C., Kołodziej, J., Rudolph, G. (eds.) PPSN XI. LNCS, vol. 6238, pp. 404–413. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  23. 23.
    Urbanowicz, R., Kiralis, J., Fisher, J., Moore, J.: Predicting Difficulty in Simulated Genetic Models: Metrics for Model Architecture Selection. BMC Bioinformatics (submitted)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Ryan J. Urbanowicz
    • 1
  • Delaney Granizo-Mackenzie
    • 1
  • Jason H. Moore
    • 1
  1. 1.Computational Genetics Laboratory, Department of GeneticsDartmouth Medical SchoolLebanonUSA

Personalised recommendations