Abstract
Classification methods based on linear discriminant analysis, recursive partitioning, and hierarchical agglomerative clustering are examined for their ability to separate active and inactive compounds in a diverse chemical database. Topology-based descriptions of chemical structure from the Molconn-X and ISIS programs are used in conjunction with these classification techniques to identify ACE inhibitors, β-adrenergic antagonists, and H_2 receptor antagonists. Overall, discriminant analysis misclassifies the smallest number of active compounds, while recursive partitioning yields the lowest rate of misclassification among inactives. Binary structural keys from the ISIS package are found to generally outperform the whole-molecule Molconn-X descriptors, especially for identification of inactive compounds. For all targets and classification methods, sensitivity toward active compounds is increased by making repetitive classifications using training sets that contain equal numbers of actives and inactives. These balanced training sets provide an average numerical class membership score which may be used to select subsets of compounds that are enriched in actives.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Salemme, F.R., Spurlino, J. and Bone, R., Structure, 5 (1997) 319.
Martin, Y.C., Brown, R.D. and Bures, M.G., In Kerwin, J.F. and Gordon, E.M. (Eds.) Combinatorial Chemistry and Molecular Diversity in Drug Discovery, Wiley, New York, NY, 1998, pp. 369–385.
Ferguson, A.M., Patterson, D.E., Garr, C. and Underiner, T., J. Biomol. Screen., 1 (1996) 65.
Patterson, D.E., Cramer, R.D., Ferguson, A.M., Clark, R.D. and Weinberger, L.E., J. Med. Chem., 39 (1996) 3049.
Chapman, D., J. Comput.-Aided Mol. Design, 10 (1996) 501.
Martin, E.J., Blaney, J.M., Siani, M.A., Spellmeyer, D.C., Wong, A.K. and Moos, W.H., J. Med. Chem., 38 (1995) 1431.
Shemtulskis, N.E., Dunbar, J.B., Dunbar, B.W., Moreland, D.W. and Humblet, C., J. Comput.-Aided Mol. Design, 9 (1995) 407.
Dean, P.M. (Ed.) Molecular Similarity in Drug Design, Chapman and Hall, London, 1995.
Barnard, J.M. and Down, G.M., J. Chem. Inf. Comput. Sci., 32 (1992) 644.
Johnson, M.A. and Maggiora, G.M., Concepts and Applications of Molecular Similarity, Wiley, New York, NY, 1990.
Willett, P., Similarity and Clustering in Chemical Information Systems, Research Studies Press, Letchworth, 1987.
Dillon, W.R. and Goldstein, M., Multivariate Analysis, Methods and Applications, Wiley, New York, NY, 1984.
Van de Waterbeemd, H., In van de Waterbeemd, H. (Ed.) ChemometricMethods in Molecular Design, VCH, New York, NY, 1995, pp. 283–293.
McFarland, J.W. and Gans, D.J., In Hansch, C., Sammes, P.G. and Taylor, J.B. (Eds.) Comprehensive Medicinal Chemistry, Vol. 4, Pergamon, New York, NY, 1990, pp. 667–689.
Breiman, L., Friedman, J.H., Olshen, R.A. and Stone, C.J., Classification and Regression Trees, Wadsworth International Group, Belmont, CA, 1984.
Hawkins, D.M. and Kass, G.V., In Hawkins, D.H. (Ed.) Topics in Applied Multivariate Analysis, Cambridge University Press, Cambridge, 1982, pp. 269–302.
Young, S.S. and Hawkins, D.M., J. Med. Chem., 38 (1995) 2784.
Murtagh, F., Multidimensional Clustering Algorithms, Vol. 4, Physica-Verlag, Heidelberg, 1985.
CMC database, MDL Information Systems, Inc., San Leandro, CA.
Molconn-X 2.0., Hall Associates Consulting, Quincy, MA.
ISISTM/Base 2.1.3, MDL Information Systems Inc., San Leandro, CA.
S-PLUS 3.4, StatSci Division, MathSoft Inc., Seattle, WA.
Brown, R.D. and Martin, Y.C., J. Chem. Inf. Comput. Sci., 36 (1996) 572.
S-Plus Guide to Statistical and Mathematical Analysis, Version 3.3, MathSoft Inc., Seattle, WA, 1995.
Banfield, J.D. and Raftery, A.E., Biometrics, 49 (1992) 803.
MACCS-II Menu Reference Version 2.2, MDL Information Systems, San Leandro, CA, 1994.
Sutter, J.M., Dixon, S.L. and Jurs, P.C., J. Chem. Inf. Comput. Sci., 35 (1995) 77.
Furnival, G. and Wilson, R., Technometrics, 16 (1974) 499.
Bravi, G., Gancia, E., Zaliani, A. and Pegna, M., J. Comput. Chem., 18 (1997) 1295.
Hall, L.H. and Kier, L.B., Molconn-X User' Guide, Hall Associates Consulting, Quincy, MA, 1993.
Dixon, S.L. and Villar, H.O., J. Chem. Inf. Comput. Sci., 38 (1998) 1192.
Willett, P. and Winterman, V.A., Quant. Struct.–Act. Relatsh., 5 (1986) 18.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Dixon, S.L., Villar, H.O. Investigation of classification methods for the prediction of activity in diverse chemical libraries. J Comput Aided Mol Des 13, 533–545 (1999). https://doi.org/10.1023/A:1008061017938
Issue Date:
DOI: https://doi.org/10.1023/A:1008061017938