QSAR Prediction of BBB Permeability Based on Machine Learning upon PETBD: A Novel Data Set of PET Tracers

Assessing small-molecule blood-brain barrier permeability is laborious, yet critical in drug development. Quantitative prediction models are hindered by a lack of high-quality data set. To address this, we curated PETBD, a novel data set of drug concentrations for 1056 positron emission tomography tracers across 14 organs at 60 min post injection, as well as <i>in vivo</i> metadata. We developed machine learning models to predict the brain-to-blood concentration ratio (log BB), and for the first time, drug concentration in the brain. Extreme gradient boosting model reached the best performance in predicting <i>C</i>_brain (<i>R</i>² = 0.700) and also achieved state-of-the-art log BB prediction (<i>R</i>² = 0.770). Feature importance analysis was employed to explain the contributions of physicochemical-based features. The model's superior generalizability was validated against the B3DB benchmark and with unpublished PET tracers. The open-access PETBD data set (https://github.com/GDUT-Computer-Medical-Science-Team/PETBD-QSAR/) and models promise to accelerate CNS drug discovery by bridging computational predictions with empirical pharmacokinetic outcomes.