Prev. Article Next Article Table of Contents

Article

Effect of Selection of Molecular Descriptors on the Prediction of Blood−Brain Barrier Penetrating and Nonpenetrating Agents by Statistical Learning Methods

Supporting Info

Hu Li,^† Chun Wei Yap,^† Choong Yong Ung,^† Ying Xue,^†^‡ Zhi Wei Cao,^§ and Yu Zong Chen*^†^§

Bioinformatics and Drug Design Group, Department of Computational Science, National University of Singapore, Blk SOC1, Level 7, 3 Science Drive 2, Singapore 117543, College of Chemistry, Sichuan University, Chengdu 610064, P. R. China, and Shanghai Center for Bioinformation Technology, Shanghai 201203, P. R. China

J. Chem. Inf. Model., 2005, 45 (5), pp 1376–1384

DOI: 10.1021/ci050135u

Publication Date (Web): August 10, 2005

†

National University of Singapore.

‡

Sichuan University.

Shanghai Center for Bioinformation Technology.

Corresponding author tel.: 65−6874−6877, fax: 65−6774−6756, e-mail: csccyz@nus.edu.sg.

Abstract

The ability or inability of a drug to penetrate into the brain is a key consideration in drug design. Drugs for treating central nervous system (CNS) disorders need to be able to penetrate the blood−brain barrier (BBB). BBB nonpenetration is desirable for non-CNS-targeting drugs to minimize potential CNS-related side effects. Computational methods have been employed for the prediction of BBB-penetrating (BBB+) and -nonpenetrating (BBB−) agents at impressive accuracies of 7592% and 6080%, respectively. However, the majority of these studies give a substantially lower BBB− accuracy, and thus overall accuracy, than the BBB+ accuracy. This work examined whether proper selection of molecular descriptors can improve both the BBB− and the overall accuracies of statistical learning methods. The methods tested include logistic regression, linear discriminate analysis, k nearest neighbor, C4.5 decision tree, probabilistic neural network, and support vector machine. Molecular descriptors were selected by using a feature selection method, recursive feature elimination (RFE). Results by using 415 BBB+ and BBB− agents show that RFE substantially improves both the BBB− and the overall accuracy for all of the methods studied. This suggests that statistical learning methods combined with proper feature selection is potentially useful for facilitating a more balanced and improved prediction of BBB+ and BBB− agents.