Prediction of boiling points of organic compounds from molecular descriptors by using backpropagation neural network

  • G. Espinosa
  • A. Arenas
  • Francesc Giralt
Part of the Mathematical and Computational Chemistry book series (MACC)


The design and optimisation of industrial process require the knowledge of thermophysical properties. Available data banks can provide this information. However in specific cases, such as those related to drug activity or enviromental impact assessment, data are scarce and difficult or expensive to obtain experimentally. To overcome this lack of ready information, several thermodynamic models and correlations have been developed for a wide range of conditions. Among these models, the methods based on quantitative structure property relationships (QSPR) are promising. The basic concept of QSPR is to relate the structure of a compound with the property of interest. The compound’s structure is expressed in terms of molecular descriptors that characterise a given molecular feature. Molecular descriptors, such as the connectivity indices and the corresponding valence connectivity indices, that encode features such as size, branching, unsaturation, heteroatom content and cyclicity [1,2] are useful. For example, the first order connectivity index was used in 1982 to correlated the solubility of hydrocarbons in water [3]. The connectivity indices are based on local molecular properties and are bond-additive quantities so that in bonds of different kinds make different contribution to the overall molecular descriptors. The key step is to build the structure property relationship.


Boiling Point Molecular Descriptor Hide Unit Connectivity Index Average Relative Error 
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.
    L. Hall and L. Kier, J. Chem. Inf. Compt. Sci. 35, pp 1039(1995).CrossRefGoogle Scholar
  2. 2.
    M. Randic and N. Trinajstic, J. Mol Struct. 284, 209 (1993).CrossRefGoogle Scholar
  3. 3.
    M. Medir and F. Giralt, AICHE Journal 28, 341 (1982).CrossRefGoogle Scholar
  4. 4.
    Katritzky, M. Karelson and V. Lobanov, Pure Appl. Chem. 69, 245 (1997).CrossRefGoogle Scholar
  5. 5.
    P. Jurs, 214 th ACS National Meeting, 1997.Google Scholar
  6. 6.
    Katritzky, Lan Mu, and V. Lobanov, J. Phys. Chem. 100, 10400 (1996).CrossRefGoogle Scholar
  7. 7.
    Katritzky, Lan Mu, and M. Karelson, J. Chem. Inf. Compt. Sci. 38, 293 (1998).CrossRefGoogle Scholar
  8. 8.
    Patil,. J. Hazard. Mater. 19, 35 (1994)Google Scholar
  9. 9.
    R. Reid, J. Prausnitz and B. Poling, The Properties of Gases and liquids, 4th ed., McGraw-Hill, New York, 1987.Google Scholar
  10. 10.
    Joback and R. Reid, Chem. Eng. Commun. 57, 233 (1987).CrossRefGoogle Scholar
  11. 11.
    Bünz, B. Braun, and R. Janowsky, Ind. Eng. Chem. Res. 37, 3043 (1998).CrossRefGoogle Scholar
  12. 12.
    Hall and C. Story, J. Chem. Inf. Compt. Sci. 36, 1004 (1996).CrossRefGoogle Scholar
  13. 13.
    Hertz and K. Palmer, Introduction to the Theory of Neural Computation, Addison Wesley, The Advanced Book Program, pp. 115 (1991).Google Scholar
  14. 14.
    D. Rumelhart, G. Hinton, and R. Williams, Nature 323, 533 (1986).CrossRefGoogle Scholar
  15. 15.
    S. Falhman, An Empirical Study of Learning Speed in Backpropagation Networks, Technical Reports CMU-CS-88–162 (1988).Google Scholar
  16. 16.
    S. Fahlman, and C. Lebiere, The Cascade Correlation Learning Architecture, Advances in Neural Information Processing System II, pp. 524 (1990).Google Scholar
  17. 17.
    Squieres and J. Savlik, Experimental Analysis of Aspects of the Cascade Correlation Learning Architectures, Machine Learning Research Group Working, paper 91–1 (1991).Google Scholar
  18. 18.
    F. Tamburini and R. Davoli, An Algorithm Method to Build Good Training Sets for Neural Networks Classifiers, Technical Report UBLCS-94–18, (1994).Google Scholar
  19. 19.
    G. Carpenter and S. Grossberg, Computer Vision, Graphics, and Image Processing.37, 54 (1987).CrossRefGoogle Scholar
  20. 20.
    G. Carpenter and S. Grossberg, Computer, 21, 77 (1988).CrossRefGoogle Scholar
  21. 21.
    Espinosa G., Yaffe D., Cohen, Y., Arenas, A., and Giralt F., J. Chem. Inf. Compt. Sci. 40, 859 (2000).CrossRefGoogle Scholar
  22. 22.
    Giralt, F., Arenas, A., Ferre-Gine, J., Rallo, R. and Kopp, G., Physics of Fluids, 12, 1826 (2000).CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2001

Authors and Affiliations

  • G. Espinosa
    • 1
  • A. Arenas
    • 1
  • Francesc Giralt
    • 1
  1. 1.Departament d’Enginyeria Química, Escola Tècnica Superior d’Enginyeria Química (ETSEQ), Departament d’Enginyeria Informàtica i Matemática (ETSE)Universitat Rovira i VirgiliTarragona, CatalunyaSpain

Personalised recommendations