Explaining Blood–Brain Barrier Permeability of Small Molecules by Integrated Analysis of Different Transport Mechanisms

Abstract

The blood–brain barrier (BBB) represents a major obstacle to delivering drugs to the central nervous system (CNS), resulting in the lack of effective treatment for many CNS diseases including brain cancer. To accelerate CNS drug development, computational prediction models could save the time and effort needed for experimental evaluation. Here, we studied BBB permeability focusing on active transport (influx and efflux) as well as passive diffusion using previously published and self-curated data sets. We created prediction models based on physicochemical properties, molecular substructures, or their combination to understand which mechanisms contribute to BBB permeability. Our results show that features that predicted passive diffusion over membranes overlap with features that explain endothelial permeation of approved CNS-active drugs. We also identified physical properties and molecular substructures that positively or negatively predicted BBB transport. These findings provide guidance toward identifying BBB-permeable compounds by optimally matching physicochemical and molecular properties to BBB transport mechanisms.

Cleomin Exerts Acute Antinociceptive Effects in Mice via GABAB and Muscarinic Receptors

“…The presence of the blood-brain barrier exerts influence over the pharmacotherapy of drugs that necessitate access to the central nervous system. Given this context, the use of computational prediction models proves to be a time-and effort-saving approach, obviating the need for extensive experimental evaluations [32]. According to the estimated permeation model applied in SWISSADME [33], cleomin exhibits a high likelihood of being absorbed efficiently by the gastrointestinal tract and penetrating the blood-brain barrier.…”

Combining SILCS and Artificial Intelligence for High-Throughput Prediction of the Passive Permeability of Drug Molecules

“…With the rapid advancement of computational technology, various in silico prediction models have been developed to access ADME (absorption, distribution, metabolism, and excretion) properties of drug molecules, encompassing their ability to traverse biological membranes or the blood–brain barrier (BBB). Several studies have focused on using various machine learning (ML) algorithms, including logistic regression, support vector machine (SVM), , random forest (RF), ,− neural network (NN), graph neural network (GNN), GradientBoosting, XGBoost, and LightGBM, for permeability prediction. Among the conventional ML approaches, RF regression models offer several advantages.…”