Predicting CNS Permeability of Drug Molecules: Comparison of Neural Network and Support Vector Machine Algorithms

Abstract

Two different machine-learning algorithms have been used to predict the blood-brain barrier permeability of different classes of molecules, to develop a method to predict the ability of drug compounds to penetrate the CNS. The rst algorithm is based on a multilayer perceptron neural network and the second algorithm uses a support vector machine. Both algorithms are trained on an identical data set consisting of 179 CNS active molecules and 145 CNS inactive molecules. The training parameters include molecular weight, lipophilicity, hydrogen bonding, and other variables that govern the ability of a molecule to diffuse through a membrane. The results show that the support vector machine outperforms the neural network. Based on over 30 different validation sets, the SVM can predict up to 96% of the molecules correctly, averaging 81.5% over 30 test sets, which comprised of equal numbers of CNS positive and negative molecules. This is quite favorable when compared with the neural network's average performance of 75.7% with the same 30 test sets. The results of the SVM algorithm are very encouraging and suggest that a classi cation tool like this one will prove to be a valuable prediction approach.

In Silico Prediction of Pregnane X Receptor Activators by Machine Learning Approache

“…Most of the drug metabolism prediction efforts have been directed at the development of tools for predicting cytochrome P450 substrates and inhibitors (Ekins et al, 2000;Doniger et al, 2002). However, significantly fewer works have been devoted to the development of tools for identifying PXR activators.…”

A Review of Methods for Computational Prediction of Blood-Brain Partitioning

“…[29] In addition to simple multiple linear regression methods, a number of comprehensive computational approaches based on neural networks and genetic algorithms resulted in the development of logBB QSARs. [30][31][32][33][34] For example, Teixido and coworkers successfully developed a genetic algorithm to identify and design peptides that permeate through the BBB. [33] Recently, Fu and coworkers used computed values of the molecular volume, the sum of the absolute values of the net atomic charges of oxygen and nitrogen atoms which are hydrogen-bond acceptors, and the sum of the net atomic charges of hydrogen atoms attached to oxygen or nitrogen atoms to train and artificial neural network for logBB.…”

Towards integrated ADME prediction: past, present and future directions for modelling metabolism by UDP-glucuronosyltransferases

“…The variability between isoforms probably reflects differences in the size, structural diversity and quality of the datasets, and confirms the inherent complexity of defining relationships for enzymes with broad and overlapping selectivities. This work represents the first detailed assessment of SVM algorithms for ADME prediction, although an SVM has recently been successfully applied to classifying drug CNS-permeability for a single dataset [51].…”