Summary
A new automated procedure to improve the predictive quality of CoMFA models for both training and test sets is described. A model of greater consistency is generated by performing small reorientations of the underlying molecules for which too low activities are calculated. In order to predict activities of test compounds, the most similar molecules in the previously optimized model are identified and used as a basis for the prediction. This method has been applied to two independent sets of dihydrofolate reductase inhibitors (80 compounds each, serving as training sets), resulting in a significant increase of the cross-validated r2 value. For both models, the predictive r2 value for a test set consisting of 70 compounds was improved substantially.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Cramer, III, R.D., Patterson, D.E. and Bunce, J.E., J. Am. Chem. Soc., 110 (1988) 5959.
Avery, M.A., Gao, F. and Chong, W.K.M., J. Med. Chem., 36 (1993) 4264.
Horwitz, J.P., Massova, I., Wiese, T.E., Besler, P.H. and Corbett, T.H., J. Med. Chem., 37 (1994) 781.
Waller, C.L., Oprea, T.I., Giolitti, A. and Marshall, G.R., J. Med. Chem., 36 (1993) 4152.
Waller, C.L. and Marshall, G.R., J. Med. Chem., 36 (1993) 2390.
DePriest, S.A., Mayer, D., Naylor, C.B. and Marshall, G.R., J. Am. Chem. Soc., 115 (1993) 5372.
Debnath, A.K., Hansch, C., Kim, K.H. and Martin, Y.C., J. Med. Chem., 36 (1993) 1007.
Wold, S., Ruhe, A., Wold, H. and Dunn, III, W.J., SIAM J. Sci. Stat. Comput., 5 (1984) 735.
Wold, S., Albano, C., Dunn, III, W.J., Edlund, U., Esbenson, K., Geladi, P., Hellberg, S., Johannson, E., Lindberg, W. and Sjörström, M., In Kowalski, B. (Ed.) Chemometrics: Mathematics and Statistics in Chemistry, Reidel, Dordrecht, 1984, pp. 17–95.
Stahle, L. and Wold, S., Prog. Med. Chem., 25 (1988) 292.
Cramer, III, R.D., Patterson, D.E. and Bunce, J.D., Quant. Struct.-Act. Relatsh., 7 (1988) 18.
Thibaut, U., Folkers, G., Klebe, G., Kubinyi, H., Merz, A. and Rognan, D., Quant. Struct.-Act. Relatsh., 13 (1994) 1.
Nicklaus, M.C., George, W.A. and Terrence, Jr., R.B., J. Comput.-Aided Mol. Design, 6 (1992) 487.
Silipo, C. and Hansch, C., J. Am. Chem. Soc., 97 (1975) 6849.
SYBYL Molecular Modelling Package, v. 6.04, TRIPOS Associates, Inc., St. Louis, MO, 1993.
Vinter, J.G., Davies, A. and Saunder, M.R., J. Comput.-Aided Mol. Design, 1 (1987) 31.
Powell, M.J.D., Math. Program., 12 (1977) 241.
Stewart, J.J.P. and Seiler, F.J., MOPAC (v. 5.00), QCPE Program No. 455, Quantum Chemistry Program Exchange, University of Indiana, Bloomington, IN, 1989.
Dewar, M.J.S. and Thiel, W., J. Am. Chem. Soc., 99 (1977) 4899.
SYBYL Molecular Modelling Software version 6.0 Command Manual, Tripos Associates, Inc., St. Louis, MO, 1992, p. 1259.
SYBYL Molecular Modelling Software version 6.0 Theory Manual, Tripos Associates, Inc., St. Louis, MO, 1992, p. 2225.
Nelder, J.A. and Mead, R., Comput. J., 7 (1965) 308.
Press, W.H., Flannery, B.P., Teukolsky, S.A. and Vetterling, W.T., Numerical Recipes, Cambridge University Press, Cambridge, 1987, pp. 289–293.
Johnson, M., Lajiness, M. and Maggiora, G., Prog. Clin. Biol. Res., 291 (1989) 167.
Kim, K.H., Greco, G., Novellino, E., Silipo, C. and Vittoria, A., J. Comput.-Aided Mol. Design, 7 (1993) 263.
Clark, M. and Cramer, III, R.D., Quant. Struct.-Act. Relatsh., 12 (1993) 137.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Kroemer, R.T., Hecht, P. A new procedure for improving the predictiveness of CoMFA models and its application to a set of dihydrofolate reductase inhibitors. J Computer-Aided Mol Des 9, 396–406 (1995). https://doi.org/10.1007/BF00123997
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00123997