Comparison of Neural Network Optimization Approaches for Studies of Human Genetics

  • Alison A. Motsinger
  • Scott M. Dudek
  • Lance W. Hahn
  • Marylyn D. Ritchie
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3907)


A major goal of human genetics is the identification of susceptibility genes associated with common, complex diseases. The preponderance of gene-gene and gene-environment interactions comprising the genetic architecture of common diseases presents a difficult challenge. To address this, novel computational approaches have been applied to studies of human disease. These novel approaches seek to capture the complexity inherent in common diseases. Previously, we developed a genetic programming neural network (GPNN) to optimize network architecture for the detection of disease susceptibility genes in association studies. While GPNN was a successful endeavor, we wanted to address the limitations in its flexibility and ease of development. To this end, we developed a grammatical evolution neural network (GENN) approach that accounts for the drawbacks of GPNN. In this study we show that this new method has high power to detect gene-gene interactions in simulated data. We also compare the performance of GENN to GPNN, a traditional back-propagation neural network (BPNN) and a random search algorithm. GENN outperforms both BPNN and the random search, and performs at least as well as GPNN. This study demonstrates the utility of using GE to evolve NN in studies of complex human disease.


Random Search Back Propagation Neural Network Multifactor Dimensionality Reduction Grammatical Evolution Random Search Algorithm 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kardia, S., Rozek, L., Hahn, L., Fingerlin, T., Moore, J.: Identifying multilocus genetic risk profiles: a comparison of the multifactor data reduction method and logistic regression. Genetic Epidemiology (2000)Google Scholar
  2. 2.
    Moore, J.H., Williams, S.M.: New strategies for identifying gene-gene interactions in hypertension. Ann. Med. 34, 88–95 (2002)CrossRefGoogle Scholar
  3. 3.
    Culverhouse, R., Klein, T., Shannon, W.: Detecting epistatic interactions contributing to quantitative traits. Genet. Epidemiol. 27, 141–152 (2004)CrossRefGoogle Scholar
  4. 4.
    Hahn, L.W., Ritchie, M.D., Moore, J.H.: Multifactor dimensionality reduction software for detecting gene-gene and gene-environment interactions. Bioinformatics 19, 376–382 (2003)CrossRefGoogle Scholar
  5. 5.
    Kooperberg, C., Ruczinski, I., LeBlanc, M.L., Hsu, L.: Sequence analysis using logic regression. Genet. Epidemiol. 21(suppl. 1), S626–S631 (2001)Google Scholar
  6. 6.
    Moore, J.H.: The ubiquitous nature of epistasis in determining susceptibility to common human diseases. Hum. Hered. 56, 73–82 (2003)CrossRefGoogle Scholar
  7. 7.
    Nelson, M.R., Kardia, S.L., Ferrell, R.E., Sing, C.F.: A combinatorial partitioning method to identify multilocus genotypic partitions that predict quantitative trait variation. Genome. Res. 11, 458–470 (2001)CrossRefGoogle Scholar
  8. 8.
    Ritchie, M.D., Hahn, L.W., Roodi, N., Bailey, L.R., Dupont, W.D., Parl, F.F., et al.: Multifactordimensionality reduction reveals high-order interactions among estrogen-metabolism genes in sporadic breast cancer. Am J. Hum. Genet. 69, 138–147 (2001)CrossRefGoogle Scholar
  9. 9.
    Ritchie, M.D., Hahn, L.W., Moore, J.H.: Power of multifactor dimensionality reduction for detecting gene-gene interactions in the presence of genotyping error, missing data, phenocopy, and genetic heterogeneity. Genet. Epidemiol. 24, 150–157 (2003)CrossRefGoogle Scholar
  10. 10.
    Tahri-Daizadeh, N., Tregouet, D.A., Nicaud, V., Manuel, N., Cambien, F., Tiret, L.: Automated detection of informative combined effects in genetic association studies of complex traits. Genome. Res. 13, 1952–1960 (2003)Google Scholar
  11. 11.
    Zhu, J., Hastie, T.: Classification of gene microarrays by penalized logistic regression. Biostatistics 5, 427–443 (2004)zbMATHCrossRefGoogle Scholar
  12. 12.
    Schalkoff, R.: Artificial Neural Networks. McGraw-Hill Companies Inc., New York (1997)zbMATHGoogle Scholar
  13. 13.
    Bhat, A., Lucek, P.R., Ott, J.: Analysis of complex traits using neural networks. Genet. Epidemiol. 17, S503–S507 (1999)Google Scholar
  14. 14.
    Curtis, D., North, B.V., Sham, P.: Use of an artificial neural network to detect association between a disease and multiple marker genotypes. Annals of Human Genetics 65, 95–107 (2001)CrossRefGoogle Scholar
  15. 15.
    Li, W., Haghighi, F., Falk, C.: Design of artificial neural network and its applications to the analysis of alcoholism data. Genet. Epidemiol. 17, S223–S228 (1999)Google Scholar
  16. 16.
    Lucek, P., Hanke, J., Reich, J., Solla, S.A., Ott, J.: Multi-locus nonparametric linkage analysis of complex trait loci with neural networks. Hum. Hered. 48, 275–284 (1998)CrossRefGoogle Scholar
  17. 17.
    Lucek, P.R., Ott, J.: Neural network analysis of complex traits. Genet. Epidemiol. 14, 1101–1106 (1997)CrossRefGoogle Scholar
  18. 18.
    Marinov, M., Weeks, D.: The complexity of linkage analysis with neural networks. Human Heredity 51, 169–176 (2001)CrossRefGoogle Scholar
  19. 19.
    Ott, J.: Neural networks and disease association. American Journal of Medical Genetics (Neuropsychiatric Genetics) 105(60), 61 (2001)Google Scholar
  20. 20.
    Saccone, N.L., Downey, T.J., Meyer, D.J., Neuman, R.J., Rice, J.P.: Mapping genotype to phenotype for linkage analysis. Genet Epidemiol 17(suppl.), 703–708 (1999)Google Scholar
  21. 21.
    Sherriff, A., Ott, J.: Applications of neural networks for geen finding. Advances in Genetics 42, 287–297 (2001)CrossRefGoogle Scholar
  22. 22.
    Ritchie, M.D., White, B.C., Parker, J.S., Hahn, L.W., Moore, J.H.: Optimization of neural network architecture using genetic programming improves detection and modeling of gene-gene interactions in studies of human diseases. BMC Bioinformatics 4, 28 (2003)CrossRefGoogle Scholar
  23. 23.
    Koza, J., Rice, J.: Genetic generation of both the weights and architecture for a neural network. IEEE Transactions, II (1991)Google Scholar
  24. 24.
    Motsinger, A.A., Lee, S., Mellick, G., Ritchie, M.D.: GPNN: Power studies and applications of a neural network method for detecting gene-gene interactions in studies of human disease. BMC Bioinformatics (2005) (in press)Google Scholar
  25. 25.
    Bush, W.S., Motsinger, A.A., Dudek, S.M., Ritchie, M.D.: Can neural network constraints in GP provide power to detect genes associated with human disease? In: Rothlauf, F., Branke, J., Cagnoni, S., Corne, D.W., Drechsler, R., Jin, Y., Machado, P., Marchiori, E., Romero, J., Smith, G.D., Squillero, G. (eds.) EvoWorkshops 2005. LNCS, vol. 3449, pp. 44–53. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  26. 26.
    Ritchie, M.D., Coffey, C.S., Moore, J.H.: Genetic programming neural networks as a bioinformatics tool for human genetics. In: Deb, K., et al. (eds.) GECCO 2004. LNCS, vol. 3102, pp. 438–448. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  27. 27.
    O’Neill, M., Ryan, C.: Grammatical Evolution. IEEE Transactions on Evolutionary Computation 5, 349–357 (2001)CrossRefGoogle Scholar
  28. 28.
    O’Neill, M., Ryan, C.: Grammatical evolution: Evolutionary automatic programming in an arbitrary language. Kluwer Academic Publishers, Boston (2003)zbMATHGoogle Scholar
  29. 29.
    Moore, J.H., Hahn, L.W.: Petri net modeling of high-order genetic systems using grammatical evolution. BioSystems 72, 177–186 (2003)CrossRefGoogle Scholar
  30. 30.
    Mitchell, M.: An introduction to genetic algorithms. MIT Press, Cambridge (1996)Google Scholar
  31. 31.
    Cantu-Paz, E.: Efficient and accurate parallel genetic algorithms. Kluwer Academic Publishers, Boston (2000)zbMATHGoogle Scholar
  32. 32.
    Utans, J., Moody, J.: Selecting neural network architectures via the prediction risk application to corporate bond rating prediction. In: Conference Proceedings on the First International Conference on Artificial Intelligence Applications on Wall Street. IEEE Press, Los Alamitos (1991)Google Scholar
  33. 33.
    Moody, J.: Prediction risk and architecture selection for neural networks. In: Cherkassky, V., Friedman, J.H., Wechsler, H. (eds.) From Statistics to Nerual Networks: Theory and Pattern Recognition Applications. NATO ASI Series F, Springer, Heidelberg (1994)Google Scholar
  34. 34.
    Fahlman, S.E., Lebiere, C.: The Cascade-Correlation Learning Architecture. Masters from School of Computer Science. Carnegie Mellon University (1991)Google Scholar
  35. 35.
    Templeton, A.: Epistasis and complex traits. In: Wade, M., Broadie III, B., Wolf, J. (eds.) Epistasis and the Evolutionary Process, pp. 41–57. Oxford University Press, Oxford (2000)Google Scholar
  36. 36.
    Li, W., Reich, J.: A complete enumeration and classification of two-locus disease models. Hum.Hered. 50, 334–349 (2000)CrossRefGoogle Scholar
  37. 37.
    Moore, J., Hahn, L., Ritchie, M., Thornton, T., White, B.: Application of genetic algorithms to the discovery of complex models for simulation studies in human genetics. In: Langdon, W.B., Cantu-Paz, E., Mathias, K., Roy, R., Davis, D., Poli, R., Balakrishnan, K., Honavar, V., Rudolph, G., Wegener, J., Bull, L., Potter, M.A., Schultz, A.C., Miller, J.F., Burke, E., Jonoska, N. (eds.) Proceedings of the Genetic and Evolutionary Algorithm Conference, pp. 1150–1155. Morgan Kaufman Publishers, San Francisco (2002)Google Scholar
  38. 38.
    Anderson, J.: An Introduction to Neural Networks. MIT Press, Cambridge, Massachusetts (1995)zbMATHGoogle Scholar
  39. 39.
    Culverhouse, R., Suarez, B.K., Lin, J., Reich, T.: A perspective on epistasis: limits of models displaying no main effect. Am J. Hum. Genet. 70, 461–471 (2002)CrossRefGoogle Scholar
  40. 40.
    Frankel, W., Schork, N.: Who’s afraid of epistasis? Nat.Genet. 14, 371–373 (1996)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Alison A. Motsinger
    • 1
  • Scott M. Dudek
    • 1
  • Lance W. Hahn
    • 1
  • Marylyn D. Ritchie
    • 1
  1. 1.Center for Human Genetics Research, Department of Molecular Physiology & BiophysicsVanderbilt UniversityNashvilleUSA

Personalised recommendations