Prediction of dihydrofolate reductase inhibition and selectivity using computational neural networks and linear discriminant analysis

Abstract

A data set of 345 dihydrofolate reductase inhibitors was used to build QSAR models that correlate chemical structure and inhibition potency for three types of dihydrofolate reductase (DHFR): rat liver (rl), Pneumocystis carinii ( pc), and Toxoplasma gondii ( tg). Quantitative models were built using subsets of molecular structure descriptors being analyzed by computational neural networks. Neural network models were able to accurately predict log IC 50 values for the three types of DHFR to within ±0.65 log units (data sets ranged ∼5.5 log units) of the experimentally determined values. Classification models were also constructed using linear discriminant analysis to identify compounds as selective or nonselective inhibitors of bacterial DHFR ( pcDHFR and tgDHFR) relative to mammalian DHFR (rlDHFR). A leave- N-out training procedure was used to add robustness to the models and to prove that consistent results could be obtained using different training and prediction set splits. The best linear discriminant analysis (LDA) models were able to correctly predict DHFR selectivity for ∼70% of the external prediction set compounds. A set of new nitrogen and oxygen-specific descriptors were developed especially for this data set to better encode structural features, which are believed to directly influence DHFR inhibition and selectivity.