1992/12/01 by Ross D. King, Stephen Muggleton, Richard A. Lewis +1 · 221 citations
Computer Science · Pharmacology, Toxicology and Pharmaceutics · Chemistry · Mathematics · #Computational Drug Discovery Methods #Pharmacogenetics and Drug Metabolism #Analytical Chemistry and Chromatography #Dihydrofolate reductase #Inductive logic programming #Flexibility (engineering) #Computer science #Quantitative structure–activity relationship #Machine learning #Trimethoprim #Artificial intelligence #Computational biology #Chemistry #Stereochemistry #Theoretical computer science #Biology #Biochemistry #Mathematics #Enzyme
paper · doi:10.1073/pnas.89.23.11322
published in Proceedings of the National Academy of Sciences 89(23), 11322-11326 (National Academy of Sciences)
openalex publication_date 1992/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/02
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.