A Bayesian Approach to in Silico Blood-Brain Barrier Penetration Modeling

Abstract

The human blood-brain barrier (BBB) is a membrane that protects the central nervous system (CNS) by restricting the passage of solutes. The development of any new drug must take into account its existence whether for designing new molecules that target components of the CNS or, on the other hand, to find new substances that should not penetrate the barrier. Several studies in the literature have attempted to predict BBB penetration, so far with limited success and few, if any, application to real world drug discovery and development programs. Part of the reason is due to the fact that only about 2% of small molecules can cross the BBB, and the available data sets are not representative of that reality, being generally biased with an over-representation of molecules that show an ability to permeate the BBB (BBB positives). To circumvent this limitation, the current study aims to devise and use a new approach based on Bayesian statistics, coupled with state-of-the-art machine learning methods to produce a robust model capable of being applied in real-world drug research scenarios. The data set used, gathered from the literature, totals 1970 curated molecules, one of the largest for similar studies. Random Forests and Support Vector Machines were tested in various configurations against several chemical descriptor set combinations. Models were tested in a 5-fold cross-validation process, and the best one tested over an independent validation set. The best fitted model produced an overall accuracy of 95%, with a mean square contingency coefficient (ϕ) of 0.74, and showing an overall capacity for predicting BBB positives of 83% and 96% for determining BBB negatives. This model was adapted into a Web based tool made available for the whole community at http://b3pp.lasige.di.fc.ul.pt.

In Silico Prediction of Blood–Brain Barrier Permeability of Compounds by Machine Learning and Resampling Methods

“…In this study, the data set was obtained and integrated from four recent studies . First, all these compounds containing noncovalent, inorganic, mixtures, or only salt were deleted and those with MW greater than 1000 Da were also removed.…”

“…Also, Martins et al. built a series of SVM and RF classification models using the Bayesian approach with improved results [accuracy rate (ACC)=0.947, sensitivity (SE)=0.826, and specificity (SP)=0.712] . Furthermore, Shen et al.…”

In silicoADME/T modelling for rational drug design

“…an HTS against an organic chemistry database), where a lower ratio of small molecules may be able to cross the BBB. To address the data biasing issue, Martins et al (2012) developed a Bayesian approach based on differentially sampling the available data for building training and testing datasets. The obtained model produced an overall capacity of recognizing 83% of BBB positives and 96% of BBB negatives.…”

In Vitro Cerebrovascular Modeling in the 21st Century: Current and Prospective Technologies

“…Most of the current in silico models within CNS drug development programs lack molecular descriptors of important biological functions of the BBB such as active drug transport, drug metabolism, endothelial enzymatic activity, and drug–drug interactions which hinder their translational significance. However, advances in this rapidly evolving field including the use of multiple linear regression (MLR) models incorporating additional molecular descriptors (such as plasma protein binding ratio -PPBR and high affinity P-glycoprotein substrate probability - HAPSP) (61), in vitro/in silico-in vivo data extrapolation (IVIVE) (62) and the use of bayesian statistic models (63) are closing the gap (64). At this stage, in silico models cannot be considered as standalone tools since in vivo and in vitro studies are required to validate the results and/or refine the working hypotheses the original computational algorithm(s) were built upon (65) (see also Fig.…”