International Science Index


10403

Combining Similarity and Dissimilarity Measurements for the Development of QSAR Models Applied to the Prediction of Antiobesity Activity of Drugs

Abstract:In this paper we study different similarity based approaches for the development of QSAR model devoted to the prediction of activity of antiobesity drugs. Classical similarity approaches are compared regarding to dissimilarity models based on the consideration of the calculation of Euclidean distances between the nonisomorphic fragments extracted in the matching process. Combining the classical similarity and dissimilarity approaches into a new similarity measure, the Approximate Similarity was also studied, and better results were obtained. The application of the proposed method to the development of quantitative structure-activity relationships (QSAR) has provided reliable tools for predicting of inhibitory activity of drugs. Acceptable results were obtained for the models presented here.
References:
[1] Rouvray, D.H.; Balaban, A.T. Chemical Applications of Graph Theory. Applications of Graph Theory. Wilson, R.J.; Beineke, L.W. (Eds.). Academic Press. 1979, 177-221.
[2] Ivanciuc, O.; Balaban, A.T. The Graph Description of Chemical Structures. In Topological Indices and Related Descriptors in QSAR and QSPR. Devillers, J., Balaban, A. T. (Eds.). Gordon and Breach Science Publishers. The Netherlands. 1999, 59-167.
[3] van de Waterbeemd, H.; Gifford, E. ADMET in silico modelling: towards prediction paradise? Nat. Rev. Drug Discov. 2003, 2, 192-204.
[4] Dimitrov, S.; Dimitrova, G.; Pavlov, T.; Dimitrova, N.; Patlewicz, G.; Niemela, J.; Mekenyan, O. A stepwise approach for defining the applicability domain of SAR and QSAR models. J. Chem. Inf. Model. 2005, 45, 839-849.
[5] Nikolova, N. and Jaworska, J. Approaches to measure chemical similarity - a review. QSAR Comb. Sci. 2004, 22, 1006-1026.
[6] Johnson, M.A.; Maggiora, G.M. eds. Concepts and Applications of Molecular Similarity. John Wiley, 1990.
[7] Willett, P. Chemical Similarity Searching. J. Chem. Inf. Comput. Sci. 1998, 38, 983-996.
[8] Urbano Cuadrado, M.; Luque Ruiz, I.; G├│mez-Nieto, M.A. A New Quantitative Structure-Property Relationship Based on Topological Distances on Nonisomorphic Subgraphs. In Lectures Series on Computer and Computational Sciences: Advances in Computational Methods in Sciences and Engineering. Brill Academic Publisher, 2005. 135-138.
[9] Deswal, S.; Roy, N. Quantitative structure activity relationship of benzoxazinone derivatives as neuropeptide Y Y5 receptor antagonists. European Journal of Medicinal Chemistry. 2006, 41 552-557.
[10] ChemAxon Ltd. http://www.chemaxon.com. Last acceded March, 2007.
[11] Cerruela García, G., Luque Ruiz, I., Gómez-Nieto, M.A. Step-by-Step Calculation of All Maximum Common Substructures through a Constraint Satisfaction Based Algorithm. J. Chem. Inf. Comput. Sci. 2004, 44, 30-41.
[12] Wold, S.; Sjostrom, M.; Eriksson, L. PLS-Regression: A Basic Tool of Chemometrics, Chemom. Intell. Lab. Syst. 2001, 58, 109-130.
[13] Urbano Cuadrado, M.; Luque Ruiz, I.; G├│mez-Nieto, M.A. A Steroids QSAR Approach Based on Approximate Similarities Measurements. J. Chem. Inf. Model. 2006, 46, 1678-1686.
[14] Urbano Cuadrado, M.; Luque Ruiz, I.; G├│mez-Nieto, M.A. QSAR Models Based on Isomorphic and Nonisomorphic Data Fusion for Predicting the Blood Brain Barrier Permeability. J. Comput. Chem. 2007, 28, 1252, 1260.
[15] Maggiora, G. F. On Outliers and Activity Cliffss - Why QSAR Often Disappoints. J. Chem. Inf. Model. 2006, 46, 1535-1535.