Development and validation of PAMPA-BBB QSAR model to predict brain penetration potential of novel drug candidates

This research presents the development and validation of a quantitative structure-activity relationship (QSAR) model using a large dataset from the Parallel Artificial Membrane Permeability Assay for the blood-brain barrier (PAMPA-BBB) to predict small molecule penetration into the central nervous system. The authors screened ~2,000 compounds from multiple NCATS projects and benchmarked machine learning methods, identifying a graph convolutional neural network with strong predictive performance. Correlation with in vivo rodent brain penetration and deployment of the model and dataset on public portals aim to aid early-stage CNS drug discovery and reduce dependency on costly experimental methods.

‍