Multilayer Neural Networks Applied to Structure-Activity Relationships

Part of the Eurocourses: Chemical and Environmental Science book series (EUCE, volume 2)


The human nervous system is anatomically subdivided into the central and peripheral nervous systems. The first includes the brain and spinal cord, and the second the cranial and spinal nerves. The cortex (i.e. ; cerebrum), cerebellum, midbrain, pons and medulla represent the five major anatomical units of the brain. Functionally the brain can be subdivided into small parts, such as the motor cortex, auditory cortex, hippocampus, and so on. A human brain contains one hundred billion computing elements called neurons which can be considered as the fundamental building blocks of the nervous system. A neuron is a cell similar to all the cells in the body ; however, certain critical specializations allow it to perform all of the computational and communication functions within the brain. As shown in figure 1, the neuron consists of three sections : the cell body, the dendrites, and the axon, each with separate but complementary functions.


Neural Network Hide Layer Molecular Descriptor Output Neuron Input Neuron 
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. Aleksander I. and Morton H. (Eds.) (1990). An Introduction to Neural Computing, Chapman and Hall, London.Google Scholar
  2. Anderson J.A., Gately M.T., Penz P.A., and Collins D.R. (1990). Proc. IEEE 78, 1646.CrossRefGoogle Scholar
  3. Aoyama T., Suzuki Y., and Ichikawa H. (1990). J. Med. Chem. 33, 905.Google Scholar
  4. Bochereau L. and Bourgine P. (1989). Conférence Neuro-Nîmes 1989, Nimes.Google Scholar
  5. Bochereau L. and Bourgine P. (1990). Proc. IJCNN, Washington, DC.Google Scholar
  6. Bondi A. (1964). J. Phys. Chem. 68, 441.CrossRefGoogle Scholar
  7. Borman S. (1989). Chem. Eng. News, April, 24.Google Scholar
  8. Borland International Inc. (1987). Turbo Basic (version 1. 1 ), Sèvres, France.Google Scholar
  9. Broto P. and Devillers J. (1990). Autocorrelation of properties distributed on molecular graph. In, Karcher W. and Devillers J. (Eds.). Practical Applications of Quantitative Structure-Activity Relationships (QSAR) in Environmental Chemistry and Toxicology, Kluwer Academic Publishers, Dordrecht, pp. 105–127.Google Scholar
  10. Broto P., Moreau G., and Vandycke C. (1984). Eur. J. Med. Chem. Ther. 19, 71.Google Scholar
  11. Chastrette M., Zskarya D., and Elmouaffek A. (1986). Eur. J. Med. Chem. 21, 505.Google Scholar
  12. Chastrette M. and de Saint Laumer J.Y. (1991). Submitted to Eur. J. Med. Chem..Google Scholar
  13. Davalo E. and Naïm P. (Eds.) (1990). Des Réseaux de Neurones. Second Edition, Eyrolles, Paris.Google Scholar
  14. Dubois J.E., Laurent D., and Vieillard H. (1966). C. R. Acad. Sci. 263C, 764.Google Scholar
  15. Elrod D.W., Maggiora G.M., and Trenary R.G.. In Borman (1989).Google Scholar
  16. Gevins A.S., Stone R.K., and Ragsdale S.D. (1988). Neuropsychobiology 19, 108.CrossRefGoogle Scholar
  17. Holley L.H. and Karplus M. (1989). Proc. Natl. Acad. Sci. USA 86, 152.CrossRefGoogle Scholar
  18. Kirkpatrick S., Gelatt C.D., and Vecchi M.P. (1983). Science 220, 671.CrossRefGoogle Scholar
  19. Lecun Y. (1987). Modèles connexionnistes de l’apprentissage. Thèse de doctorat, Paris.Google Scholar
  20. Mc Culloch W.W. and Pitts W. (1943). Bull. Math. Biophysics 5, 115.CrossRefGoogle Scholar
  21. Minsky M.L. and Papert S. (Eds.) (1969). Perceptrons MIT press, Cambridge.Google Scholar
  22. Miyashita Y., Takahashi Y.,Takayama C., Sumi K., Nakatsuka K.,Ohkubo T., Abe H., and Sasaki S.I. (1986). J. med. Chem. 29, 906.CrossRefGoogle Scholar
  23. Moriguchi I. (1986). In, Fujita T. (Ed.).Structure-Activity Relationship, Quantitative Approaches. Tokyo.Google Scholar
  24. Nguyen D. and Widrow B. (1989). Proc. Intl. Joint Conf. on Neural Networks, 2, 357. Washington, DC.CrossRefGoogle Scholar
  25. Paugam-Moisy H. (1989). Rapport 89–06, Laboratoire de l’informatique du parallélisme, Ecole Normale Supérieure de Lyon.Google Scholar
  26. Pauling L. (Ed.) (1960). The Nature of Chemical Bond, Third Edition, Cornell University Press, New York.Google Scholar
  27. Pitts W. and Mc Culloch W.W. (1947). Bull. Math. Biophysics 9, 127. books, Washington, DC.Google Scholar
  28. Rumelhart D.E., Hinton G.E., and Williams R.J. (1986). Nature 323, 533.CrossRefGoogle Scholar
  29. Sammon J.W. (1969). IEEE Trans. Comput. c-18, 401.Google Scholar
  30. Shea P.M. and Lin V. (1989). Proc. Intl. Joint Conf. on Neural Networks, 2, 31, Washington, DC.CrossRefGoogle Scholar
  31. Touretzky P. and Pomerleau D. (1989). Byte 14 n’8, 227.Google Scholar
  32. Verloop A., Hoogenstraaten W., and Tipkec J. (1976). Drug Design, 7, 165.Google Scholar
  33. Wasserman P.D. (Ed.) (1989). Neural Computing. Theory and Practice. Van Nostrand Reinhold, New York.Google Scholar
  34. Widrow B. and Angell J.B. (1962). Aerospace Eng. 21, 78.Google Scholar
  35. Widrow B. and Hoff M.E. (1960). Adaptive switching circuits. 1960 IRE WESCON Convention Record, part 4, pp. 96–104, Institute of Radio Engineers, New York.Google Scholar
  36. Widrow B. and Lehr A. (1990). Proc. IEEE, 78, 1415.CrossRefGoogle Scholar
  37. Wold S. and Sjostrom M. (1977). Chemometrics; Theory and Application. In, Kowalski B.R. (Ed.); American Chemical Society, Washington, DC.Google Scholar
  38. Yuhas B.P., Goldstein Jr M.H., Sejnowski T.J., and Jenkins R. E. (1990). Proc.IEEE 1658, 78.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 1991

Authors and Affiliations

  1. 1.Laboratoire de Chimie Organique Physique, URA N⋅ 463Université Lyon-IVilleurbanne CedexFrance
  2. 2.European Group for QSAR StudiesFrance
  3. 3.CTISLyonFrance

Personalised recommendations