Graph Machines and Their Applications to Computer-Aided Drug Design: A New Approach to Learning from Structured Data
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.
KeywordsRoot Node Directed Acyclic Graph Hide Neuron Node Function Pharmaceutical Activity
Unable to display preview. Download preview PDF.
- 5.Hammer, B.: Recurrent Networks for Structured Data - a Unifying Approach and its Properties. Cognitive Systems Res. 3, 145–165 (2002)Google Scholar
- 6.Jochum, C., Gasteiger, J.: Canonical Numbering and Constitutional Symmetry. J. Chem. Inf. Comput. Sci. 17, 113–117 (1977)Google Scholar
- 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.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
- 14.Huuskonen, J.: QSAR modeling with the electrotopological state: TIBO derivatives. J. Chem. Inf. Comput. Sci. 41, 425–429 (2001)Google Scholar
- 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.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.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.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