In Silico Prediction of Blood Brain Barrier Permeability: A Support Vector Machine Model

In Silico Prediction of Blood Brain Barrier Permeability: A Support Vector Machine Model

Zhi Wang (Beijing University of Chemical Technology, China), Aixia Yan (Beijing University of Chemical Technology, China) and Jiaxuan Li (Beijing University of Chemical Technology, China)
DOI: 10.4018/978-1-60960-064-8.ch014
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

The ability of penetration of the blood-brain barrier is an important property for the development of Central Nervous System drugs, which is commonly expressed by logBB (logBB = log(Cbrain/Cblood). In this work, a support vector machine was used to build quantitative models of blood brain barrier permeability. Molecular descriptors for 182 compounds were calculated by ADRIANA.Code and 12 descriptors were selected using the automatic variable selection function in Weka. Based on two common physicochemical descriptors (xlogP and Topological Polar Surface Area (TPSA)) and 10 2D property autocorrelation descriptors on atom pair properties, an SVM regression model was built. The built model was validated by an external test set. The reliable predictions of the test set demonstrate that this model performs well and can be used for estimation of logBB values for drug and drug-like molecules.
Chapter Preview
Top

Materials And Methods

Data Set

182 compounds with logBB experimental values and SMILES strings were collected from published work by Garg & Verma (2006). The experimental logBB of all these compounds were provided in Appendix. CORINA (CORINA, Molecular Networks GmbH, Erlangen, Germany, http://www.molecular-networks.com ) was used to add hydrogen atoms and to compute 3D structures. For each molecule, only a single 3D conformation was generated. Then the whole data set were spilt into as training set (122 compounds) and test set (60 compounds) randomly. The training set (122 compounds) was subjected to 10-fold cross validation, and the test set (60 compounds) was used as an external validation set.

Complete Chapter List

Search this Book:
Reset