Skip to main content
Log in

Data modelling with neural networks: Advantages and limitations

  • Published:
Journal of Computer-Aided Molecular Design Aims and scope Submit manuscript

Abstract

The origins and operation of artificial neural networks are briefly described and their early application to data modelling in drug design is reviewed. Four problems in the use of neural networks in data modelling are discussed, namely overfitting, chance effects, overtraining and interpretation, and examples are given of the means by which the first three of these may be avoided. The use of neural networks as a variable selection tool is shown and the advantage of networks as a nonlinear data modelling device is discussed. The display of multivariate data in two dimensions employing a neural network is illustrated using experimental and theoretical data for a set of charge transfer complexes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Eberhart, R.C. and Dobbins, R.W., Neural Network PC Tools, Academic Press, San Diego, CA, U.S.A., 1990, p. 1.

    Google Scholar 

  2. McCulloch, W.C. and Pitts, W., Bull. Math. Biophys., 5 (1943) 115.

    Google Scholar 

  3. Minsky, M. and Papert, S., Perceptrons, MIT Press, Cambridge, MA, U.S.A., 1969.

    Google Scholar 

  4. Livingstone, D.J., Data Analysis for Chemists: Applications to QSAR and Chemical Product Design, Oxford University Press, Oxford, U.K., 1995, p. 183.

    Google Scholar 

  5. Manallack, D.T. and Livingstone, D.J., In Van de Waterbeemd, H. (Ed.) Advanced Computer-Assisted Techniques in Drug Design, VCH, Weinheim, Germany, 1994, pp. 293–318.

    Google Scholar 

  6. Livingstone, D.J. and Salt, D.W., In Dean, P.M. (Ed.) Molecular Similarity in Drug Design, Blackie Academic & Professional, Glasgow, U.K., 1995, pp. 187–214.

    Google Scholar 

  7. Aoyama, T., Suzuki, Y. and Ichikawa, H., J. Med. Chem., 33 (1990) 905.

    Google Scholar 

  8. Aoyama, T., Suzuki, Y. and Ichikawa, H., J. Med. Chem., 33 (1990) 2583.

    Google Scholar 

  9. Andrea, T.A. and Kalayeh, H., J. Med. Chem., 34 (1991) 2824.

    Google Scholar 

  10. Salt, D.W., Yildiz, N., Livingstone, D.J. and Tinsley, C.J., Pestic. Sci., 36 (1992) 161.

    Google Scholar 

  11. Topliss, J.G. and Edwards, R.P., J. Med. Chem., 22 (1979) 1238.

    Google Scholar 

  12. Manallack, D.T. and Livingstone, D.J., Med. Chem. Res., 2 (1992) 181.

    Google Scholar 

  13. Livingstone, D.J. and Manallack, D.T., J. Med. Chem., 36 (1993) 1295.

    Google Scholar 

  14. Manallack, D.T., Ellis, D.D. and Livingstone, D.J., J. Med. Chem., 37 (1994) 3758.

    Google Scholar 

  15. Campbell, J.L.E. and Johnson, K.E., Can. J. Chem., 71 (1993) 1800.

    Google Scholar 

  16. Lewis, D.F.V., J. Comput. Chem., 10 (1989) 145.

    Google Scholar 

  17. Smolensky, P., Artif. Intel. Rev., 1 (1987) 95.

    Google Scholar 

  18. Goonatilake, S. and Khebbal, S. (Eds.) Intelligent Hybrid Systems, Wiley, Chichester, U.K., 1995.

    Google Scholar 

  19. Tetko, I.V., Livingstone, D.J. and Luik, A.I., J. Chem. Inf. Comput. Sci., 35 (1995) 826.

    Google Scholar 

  20. Livingstone, D.J., Data Analysis for Chemists: Applications to QSAR and Chemical Product Design, Oxford University Press, Oxford, U.K., 1995, pp. 65–89.

    Google Scholar 

  21. Tetko, I.V., Villa, A.E.P. and Livingstone, D.J., J. Chem. Inf. Comput. Sci., 36 (1996) 794.

    Google Scholar 

  22. Tetko, I.V., Tanchuk, V.Yu., Chentsova, N.P., Antonenko, S.V., Poda, G.I., Kukhar, V.P. and Luik, A.I., J. Med. Chem., 37 (1994) 2520.

    Google Scholar 

  23. Livingstone, D.J., Evans, D.A. and Saunders, M.R., J. Chem. Soc. Perkin Trans. II, (1992) 1545.

    Google Scholar 

  24. Wikel, J.H. and Dow, E.R., Bioorg. Med. Chem. Lett., 3 (1993) 645.

    Google Scholar 

  25. Livingstone, D.J., Methods Enzymol., 203 (1991) 613.

    Google Scholar 

  26. Hudson, B., Livingstone, D.J. and Rahr, E., J. Comput.-Aided Mol. Design, 3 (1988) 55.

    Google Scholar 

  27. Livingstone, D.J., Hesketh, G. and Clayworth, D., J. Mol. Graph., 9 (1991) 31.

    Google Scholar 

  28. Livingstone, D.J., In Devillers, J. (Ed.) Neural Networks in QSAR and Drug Design, Academic Press, London, U.K., 1996, pp. 157–176.

    Google Scholar 

  29. Livingstone, D.J., In Sanz, F., Giraldo, J. and Manaut, F. (Eds.) QSAR and Molecular Modelling: Concepts, Computational Tools and Biological Applications, J.R. Prous, Barcelona, Spain, 1995, pp. 18–26.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Livingstone, D., Manallack, D. & Tetko, I. Data modelling with neural networks: Advantages and limitations. J Comput Aided Mol Des 11, 135–142 (1997). https://doi.org/10.1023/A:1008074223811

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1008074223811

Navigation