Summary
One of the largest available data sets for developing a quantitative structure-activity relationship (QSAR) — the inhibition of dihydrofolate reductase (DHFR) by 2,4-diamino-6,6-dimethyl-5-phenyl-dihydrotriazine derivatives — has been used for a sixfold cross-validation trial of neural networks, inductive logic programming (ILP) and linear regression. No statistically significant difference was found between the predictive capabilities of the methods. However, the representation of molecules by attributes, which is integral to the ILP approach, provides understandable rules about drug-receptor interactions.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Hirst, J.D., King, R.D. and Sternberg, M.J.E., J. Comput.-Aided Mol. Design, 8 (1994) 405.
Silipo, C. and Hansch, C., J. Am. Chem. Soc., 97 (1975) 6849.
Andrea, T.A. and Kalayeh, H., J. Med. Chem., 34 (1991) 2824.
Hansch, C. and Fukunga, J., CHEMTECH, (1977) 120.
Hansch, C. and Silipo, C., J. Med. Chem., 17 (1974) 661.
Minitab, release 7.2, VAX/VMS version, Minitab, Inc., Pennsylvania State University, Philadelphia, PA, 1989.
Muggleton, S. and Feng, C., In Arikawa, S., Goto, S., Ohsuga, S. and Yokomori, T. (Eds.) Proceedings of the First Conference on Algorithmic Learning Theory, Japanese Society of Artifical Intelligence, Ohmsha Press, Tokyo, 1990, pp. 368–381.
Silipo, C. and Hansch, C., J. Med. Chem., 19 (1976) 62.
So, S.-S. and Richards, W.G., J. Med. Chem., 35 (1992) 3201.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Hirst, J.D., King, R.D. & Sternberg, M.J.E. Quantitative structure-activity relationships by neural networks and inductive logic programming. II. The inhibition of dihydrofolate reductase by triazines. J Computer-Aided Mol Des 8, 421–432 (1994). https://doi.org/10.1007/BF00125376
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00125376