Improving Pattern Recognition Based Pharmacological Drug Selection Through ROC Analysis

  • W. Díaz
  • María José Castro
  • F. J. Ferri
  • F. Pérez
  • M. Murcia
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3287)


The design of new medical drugs is a very complex process in which combinatorial chemistry techniques are used. The goal consists of discriminating between molecular compounds exhibiting or not certain pharmacological activities. Different machine learning approaches have been recently applied to different drug design problems leading to competitive results in pointing at particular compounds with high probability of exhibiting activity. The present work first deeps into the natural trade-off between accuracy in the much less populated active group and false alarm rate which could lead to too many expensive laboratory tests. Preliminary results show how different classification techniques are suited for this particular problem and throw light to keep improving the results by considering also the acceptance/rejection trade-off.


Receiver Operating Characteristic Receiver Operating Characteristic Curve False Positive Rate False Alarm Rate True Positive Rate 
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.


  1. 1.
    Balaban, A.T., Motoc, I., Bonchev, D., Makenyan, O.: Topological indices for structure-activity correlations. Top. Curr. Chem. 114, 21–55 (1983)CrossRefGoogle Scholar
  2. 2.
    Basak, S.C., Bertelsen, S., Grunwald, G.: Application of graph theoretical parameters in quantifying molecular similarity and structure-activty studies. J. Chem. Inf. Comput. Sci. 34, 270–276 (1994)Google Scholar
  3. 3.
    Castro, M.J., Díaz, W., Aibar, P., Domínguez, J.L.: Prediction and Discrimination of Pharmacological Activity by Using Artificial Neural Networks. In: Perales, F.J., Campilho, A.C., Pérez, N., Sanfeliu, A. (eds.) IbPRIA 2003. LNCS, vol. 2652, pp. 184–192. Springer, Heidelberg (2003) ISSN 0302-9743CrossRefGoogle Scholar
  4. 4.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. John Wiley and Sons, Chichester (2001)zbMATHGoogle Scholar
  5. 5.
    Fawcett, T.: Roc graphs: Notes and practical considerations for researchers. Machine Learning, submitted (2004),
  6. 6.
    Gálvez, J., García-Domenech, R., de Julián-Ortiz, J.V., Soler, R.: Topological approach to drug design. J. Chem. Inf. Comput. Sci. 35, 272–284 (1995)Google Scholar
  7. 7.
    Jaén-Oltra, J., Salabert-Salvador, M.T., García-March, F.J., Péz-Giménez, F., Tomás-Vert, F.: Artificial neural network applied to prediction of fluorquinolone antibacterial activity by topological methods. J. Med. Chem. 43, 1143–1148 (2000)CrossRefGoogle Scholar
  8. 8.
    Murcia-Soler, M., Pérez-Giménez, F., García-March, F.J., Salabert-Salvador, M.T., Díaz-Villanueva, W., Medina-Casamayor, P.: Discrimination and selection of new potential antibacterial compounds using simple topological descriptors. J. Mol. Graph. Model 21, 375–390 (2003)CrossRefGoogle Scholar
  9. 9.
    Seybold, P.G., May, M., Bagal, U.A.: Molecular structure-propertiy relationships. J. Chem. Educ. 64, 575–581 (1987)CrossRefGoogle Scholar
  10. 10.
    Tomás-Vert, F., Pérez-Giménez, F., Salabert-Salvador, M.T., García-March, F.J., Jaén-Oltra, J.: Artificial neural network applied to the discrimination of antibacterial activity by topological methods. J. Mol. Struct (THEOCHEM) 504, 272–276 (2000)CrossRefGoogle Scholar
  11. 11.
    Witten, I.H., Frank, E.: Data Mining: Practical machine learning tools with Java implementations. Morgan Kaufmann, San Francisco (2000)Google Scholar
  12. 12.
    Zell, A., et al.: SNNS: Stuttgart Neural Network Simulator. User Manual, Version 4.2. Institute for Parallel and Distributed High Performance Systems, University of Stuttgart, Germany (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • W. Díaz
    • 1
  • María José Castro
    • 2
  • F. J. Ferri
    • 1
  • F. Pérez
    • 3
  • M. Murcia
    • 3
  1. 1.Dept. InformàticaUniversitat de ValènciaBurjassotSpain
  2. 2.Dept. Sistemes Informàtics i ComputacióUniversitat Politècnica de ValènciaValènciaSpain
  3. 3.Dept. Química Física, F. FarmàciaUniversitat de ValènciaBurjassotSpain

Personalised recommendations