Advertisement

Genetic Algorithms for Classification of Olfactory Stimulants

  • Barry K. Lavine
  • Charles E. Davidson
  • Curt Breneman
  • William Kaat
Protocol
Part of the Methods in Molecular Biology™ book series (MIMB, volume 275)

Abstract

We have developed and tested a genetic algorithm (GA) for pattern recognition, which identifies molecular descriptors that optimize the separation of the activity classes of olfactory stimulants in a plot of the two or three largest principal components of the data. Because principal components maximize variance, the bulk of the information encoded by these descriptors is about differences between olfactory classes in the dataset. In addition, the GA focuses on those classes and or samples that are difficult to classify as it trains using a form of boosting to modify the fitness landscape. Boosting minimizes the problem of convergence to a local optimum, because the fitness function of the GA is changing as the population is evolving toward a solution. Over time, compounds that consistently classify correctly are not as heavily weighted in the analysis as compounds that are difficult to classify. The pattern recognition GA learns its optimal parameters in a manner similar to a neural network. The algorithm integrates aspects of both strong and weak learning to yield a “smart” one-pass procedure for feature selection and classification.

Key Words

Structure-activity relationship studies genetic algorithms pattern recognition olfaction musks classification molecular descriptors 

References

  1. 1.
    Breneman, C. M., Thompson, T. R., Rhem, M., and Dung, M. (1995) Electron density modeling of large systems using the transferable atom equivalent method. Comp. Chem. 19, 161–179.CrossRefGoogle Scholar
  2. 2.
    Hansch, C. and Leo, A. (1995) Exploring QSAR, fundamentals and applications in chemistry and biology. ACS National Meeting, Washington, DC.Google Scholar
  3. 3.
    Whitehead, C. E., Breneman, C. M., Sukumar, N., and Ryan, M. D. (2003) Transferable atom equivalent multi-centered expansion method. J. Comput. Chem. 24, 512–529.PubMedCrossRefGoogle Scholar
  4. 4.
    Lavine, B. K., Davidson, C. E., Vander Meer, R. K., Lahav, S., Soroker, V., and Hefetz, A. (2003) Genetic algorithms for deciphering the complex chemosensory code of social insects. Chemometrics Intell. Lab. Instrument. 66, 51–62.CrossRefGoogle Scholar
  5. 5.
    Lavine, B. K., Davidson, C. E., and Moores, A. J. (2002) Genetic algorithms for spectral pattern recognition. Vib. Spectros. 28, 83–95.CrossRefGoogle Scholar
  6. 6.
    Jolliffe, I. T. (1986) Principal component analysis, Springer Verlag, New York.Google Scholar
  7. 7.
    Beats, M. G. J. (1978) Structure activity relationships in human chemoreception, Applied Science Publishers, London, UK.Google Scholar
  8. 8.
    Wood, T. F. (1970) Chemistry of the aromatic musks, Givaudanian, Clifton, NJ, pp. 1–37.Google Scholar
  9. 9.
    Bersuker, I. B., Dimoglo, A. S., Gorbachov, M., Yu, Vlad, P. F., and Pesaro, M. (1991) Origin of musk fragrance activity: the Electron-opological approach. New J. Chem. 15, 307–320.Google Scholar
  10. 10.
    Ham, C. L. and Jurs, P. C. (1985) Structure activity studies of musk odorants using pattern recognition: monocyclic nitrobenzenes. Chem. Senses 10, 491–502.CrossRefGoogle Scholar
  11. 11.
    Theimer, E. T. (1982) Fragrance chemistry, the science of the sense of smell. Academic Press, New York.Google Scholar
  12. 12.
    Breneman, C., Bennett, Bi, J., Song, M., and Embrechts, M. (2002) New electron density-derived descriptors and machine learning techniques for computational ADME and molecular design. MidAtlantic Computational Chemistry Meeting, Princeton University, Princeton, NJ.Google Scholar
  13. 13.
    Breneman, C. M. and Rhem, M. (1997) QSPR Analysis of HPLC column capacity factors for a set of high-energy materials using electronic van der Waals surface property descriptors computed by transferable atom equivalent method. J. Comput. Chem. 18, 182–197.CrossRefGoogle Scholar
  14. 14.
    Bader, R. F. W. (1990) Atoms in molecules: a quantum theory. Oxford Univ. Press, Oxford, UK.Google Scholar
  15. 15.
    Zauhar, R. J. and Welsh, W. J. (2000) Application of the shape signatures approach to ligand-and-receptor based drug design. Abstracts of Papers of the American Chemical Society 220, 70-COMP, Part 1.Google Scholar
  16. 16.
    Michalewicz, Z. (1995) Genetic Algorithms + Data Structures = Evolution Programs. Springer Verlag, New York.Google Scholar
  17. 17.
    Mitchell, M. (1998) An Introduction to Genetic Algorithms. The MIT Press, Cambridge, MA.Google Scholar
  18. 18.
    Goldberg, D. E. (1989) Genetic Algorithms in Search, Optimization, and Machine Learning. Addison Wesley Publishing Company, Reading, MA.Google Scholar
  19. 19.
    James, M. (1992) Classification. John Wiley & Sons, New York.Google Scholar

Copyright information

© Humana Press Inc. 2004

Authors and Affiliations

  • Barry K. Lavine
    • 1
  • Charles E. Davidson
    • 1
  • Curt Breneman
    • 2
  • William Kaat
    • 2
  1. 1.Department of ChemistryClarkson UniversityPotsdamUSA
  2. 2.Department of ChemistryRensselaer Polytechnic InstituteTroyUSA

Personalised recommendations