Skip to main content
NCBI home page
Proceedings of the National Academy of Sciences of the United States of America logoLink to Proceedings of the National Academy of Sciences of the United States of America
. 1992 Dec 1;89(23):11322–11326. doi: 10.1073/pnas.89.23.11322

Drug design by machine learning: the use of inductive logic programming to model the structure-activity relationships of trimethoprim analogues binding to dihydrofolate reductase.

R D King 1, S Muggleton 1, R A Lewis 1, M J Sternberg 1
PMCID: PMC50542  PMID: 1454814

Abstract

The machine learning program GOLEM from the field of inductive logic programming was applied to the drug design problem of modeling structure-activity relationships. The training data for the program were 44 trimethoprim analogues and their observed inhibition of Escherichia coli dihydrofolate reductase. A further 11 compounds were used as unseen test data. GOLEM obtained rules that were statistically more accurate on the training data and also better on the test data than a Hansch linear regression model. Importantly machine learning yields understandable rules that characterized the chemistry of favored inhibitors in terms of polarity, flexibility, and hydrogen-bonding character. These rules agree with the stereochemistry of the interaction observed crystallographically.

Full text

PDF
11322

Images in this article

11324Image
on p.11324

Selected References

These references are in PubMed. This may not be the complete list of references from this article.

  1. Andrea T. A., Kalayeh H. Applications of neural networks in quantitative structure-activity relationships of dihydrofolate reductase inhibitors. J Med Chem. 1991 Sep;34(9):2824–2836. doi: 10.1021/jm00113a022. [DOI] [PubMed] [Google Scholar]
  2. Champness J. N., Stammers D. K., Beddell C. R. Crystallographic investigation of the cooperative interaction between trimethoprim, reduced cofactor and dihydrofolate reductase. FEBS Lett. 1986 Apr 7;199(1):61–67. doi: 10.1016/0014-5793(86)81224-8. [DOI] [PubMed] [Google Scholar]
  3. Goodford P. J. Drug design by the method of receptor fit. J Med Chem. 1984 May;27(5):558–564. doi: 10.1021/jm00371a001. [DOI] [PubMed] [Google Scholar]
  4. Hansch C., Li R., Blaney J. M., Langridge R. Comparison of the inhibition of Escherichia coli and Lactobacillus casei dihydrofolate reductase by 2,4-diamino-5-(substituted-benzyl)pyrimidines: quantitative structure-activity relationships, X-ray crystallography, and computer graphics in structure-activity analysis. J Med Chem. 1982 Jul;25(7):777–784. doi: 10.1021/jm00349a003. [DOI] [PubMed] [Google Scholar]
  5. Marshall G. R., Cramer R. D., 3rd Three-dimensional structure-activity relationships. Trends Pharmacol Sci. 1988 Aug;9(8):285–289. doi: 10.1016/0165-6147(88)90012-0. [DOI] [PubMed] [Google Scholar]
  6. Matthews D. A., Bolin J. T., Burridge J. M., Filman D. J., Volz K. W., Kaufman B. T., Beddell C. R., Champness J. N., Stammers D. K., Kraut J. Refined crystal structures of Escherichia coli and chicken liver dihydrofolate reductase containing bound trimethoprim. J Biol Chem. 1985 Jan 10;260(1):381–391. [PubMed] [Google Scholar]
  7. Roth B., Aig E., Rauckman B. S., Strelitz J. Z., Phillips A. P., Ferone R., Bushby S. R., Sigel C. W. 2,4-Diamino-5-benzylpyrimidines and analogues as antibacterial agents. 5. 3',5'-Dimethoxy-4'-substituted-benzyl analogues of trimethoprim. J Med Chem. 1981 Aug;24(8):933–941. doi: 10.1021/jm00140a005. [DOI] [PubMed] [Google Scholar]
  8. Roth B., Rauckman B. S., Ferone R., Baccanari D. P., Champness J. N., Hyde R. M. 2,4-Diamino-5-benzylpyrimidines as antibacterial agents. 7. Analysis of the effect of 3,5-dialkyl substituent size and shape on binding to four different dihydrofolate reductase enzymes. J Med Chem. 1987 Feb;30(2):348–356. doi: 10.1021/jm00385a017. [DOI] [PubMed] [Google Scholar]

Articles from Proceedings of the National Academy of Sciences of the United States of America are provided here courtesy of National Academy of Sciences

RESOURCES