Graph Machines and Their Applications to Computer-Aided Drug Design: A New Approach to Learning from Structured Data

  • Aurélie Goulon
  • Arthur Duprat
  • Gérard Dreyfus
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4135)


The recent developments of statistical learning focused on vector machines, which learn from examples that are described by vectors of features. However, there are many fields where structured data must be handled; therefore, it would be desirable to learn from examples described by graphs.Graph machines learn real numbers from graphs. Basically, for each graph, a separate learning machine is built, whose algebraic structure contains the same information as the graph. We describe the training of such machines, and show that virtual leave-one-out, a powerful method for assessing the generalization capabilities of conventional vector machines, can be extended to graph machines. Academic examples are described, together with applications to the prediction of pharmaceutical activities of molecules and to the classification of properties; the potential of graph machines for computer-aided drug design are highlighted.


Root Node Directed Acyclic Graph Hide Neuron Node Function Pharmaceutical Activity 
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.
    Pollack, J.B.: Recursive Distributed Representations. Artificial Intell. 46, 77–106 (1990)CrossRefGoogle Scholar
  2. 2.
    Sperduti, A.: Encoding Labeled Graphs by Labeling RAAM. Connection Science 6, 429–459 (1994)CrossRefGoogle Scholar
  3. 3.
    Frasconi, P., Gori, M., Sperduti, A.: A General Framework for Adaptive Processing of Data Structures. IEEE Trans. on Neural Networks 9, 768–786 (1998)CrossRefGoogle Scholar
  4. 4.
    Goulon-Sigwalt-Abram, A., Duprat, A., Dreyfus, G.: From Hopfield Nets to Recursive Networks to Graph Machines: Numerical Machine Learning for Structured Data. Th. Comp. Sci. 344, 298–334 (2005)CrossRefMathSciNetMATHGoogle Scholar
  5. 5.
    Hammer, B.: Recurrent Networks for Structured Data - a Unifying Approach and its Properties. Cognitive Systems Res. 3, 145–165 (2002)Google Scholar
  6. 6.
    Jochum, C., Gasteiger, J.: Canonical Numbering and Constitutional Symmetry. J. Chem. Inf. Comput. Sci. 17, 113–117 (1977)Google Scholar
  7. 7.
    Wiener, H.: Structural Determination of Paraffin Boiling Point. J. Amer. Chem. Soc. 69, 17–20 (1947)CrossRefGoogle Scholar
  8. 8.
    Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, Heidelberg (2000)MATHGoogle Scholar
  9. 9.
    Monari, G., Dreyfus, G.: Local Overfitting Control via Leverages. Neural Computation 14, 1481–1506 (2002)CrossRefMATHGoogle Scholar
  10. 10.
    Oussar, Y., Monari, G., Dreyfus, G.: Reply to the Comments on Local Overfitting Control via Leverages in Jacobian Conditioning Analysis for Model Validation by I. Rivals and L. Personnaz. Neural Computation 16, 419–443 (2004)CrossRefMATHGoogle Scholar
  11. 11.
    Balaban, A.T., Basak, S.C., Colburn, T., Grunwald, G.D.: Correlation between Structure and Normal Boiling Points of Haloalkanes C1-C4 Using Neural Networks. J. Chem. Inf. Comput. Sci. 34, 1118–1121 (1994)Google Scholar
  12. 12.
    Rücker, C., Meringer, M., Kerber, A.: QSPR Using MOLGEN-QSPR: The Example of Haloalkane Boiling Points. J. Chem. Inf. Comput. Sci. 44, 2070–2076 (2004)Google Scholar
  13. 13.
    Douali, L., Villemin, D., Cherqaoui, D.: Exploring QSAR of Non-Nucleoside Reverse Transcriptase Inhibitors by Neural Networks: TIBO Derivatives. Int. J. Mol. Sci. 5, 48–55 (2004)CrossRefGoogle Scholar
  14. 14.
    Huuskonen, J.: QSAR modeling with the electrotopological state: TIBO derivatives. J. Chem. Inf. Comput. Sci. 41, 425–429 (2001)Google Scholar
  15. 15.
    Zhou, Z., Madura, J.D.: CoMFA 3D-QSAR Analysis of HIV-1 RT Nonnucleoside Inhibitors, TIBO Derivatives Based on Docking Conformation and Alignment. J. Chem. Inf. Comput. Sci. 44, 2167–2178 (2004)Google Scholar
  16. 16.
    Solov’ev, V.P., Varnek, A.: Anti-HIV Activity of HEPT, TIBO, and Cyclic Urea Derivatives: Structure-Property Studies, Focused Combinatorial Library Generation, and Hits Selection Using Substructural Molecular Fragments Method. J. Chem. Inf. Comput. Sci. 43, 1703–1719 (2003)Google Scholar
  17. 17.
    Goulon, A., Picot, T., Duprat, A., Dreyfus, G.: Predicting Activities without Computing Descriptors: Graph Machines for QSAR (submitted to SAR and QSAR in Environmental Research)Google Scholar
  18. 18.
    Duprat, A.F., Huynh, T., Dreyfus, G.: Toward a Principled Methodology for Neural Network Design and Performance Evaluation in QSAR. Application to the Prediction of LogP. J. Chem. Inf. Comput. Sci. 38, 586–594 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Aurélie Goulon
    • 1
  • Arthur Duprat
    • 1
    • 2
  • Gérard Dreyfus
    • 1
  1. 1.Laboratoire d’Électronique 
  2. 2.Laboratoire de Chimie Organique, (CNRS UMR 7084)École Supérieure de Physique et de Chimie Industrielles de la Ville de Paris, (ESPCI-ParisTech)PARISFrance

Personalised recommendations