Computational Prediction of Blood-Brain Barrier Permeability Using Decision Tree Induction
Predicting blood-brain barrier (BBB) permeability is essential to drug development, as a molecule cannot exhibit pharmacological activity within the brain parenchyma without first transiting this barrier. Understanding the process of permeation, however, is complicated by a combination of both limit...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2012-08-01
|
Series: | Molecules |
Subjects: | |
Online Access: | http://www.mdpi.com/1420-3049/17/9/10429 |
id |
doaj-44623545e1c944108ff51a16fa3eb12d |
---|---|
record_format |
Article |
spelling |
doaj-44623545e1c944108ff51a16fa3eb12d2020-11-24T22:51:49ZengMDPI AGMolecules1420-30492012-08-01179104291044510.3390/molecules170910429Computational Prediction of Blood-Brain Barrier Permeability Using Decision Tree InductionJörg HuwylerFelix HammannClaudia SuenderhaufPredicting blood-brain barrier (BBB) permeability is essential to drug development, as a molecule cannot exhibit pharmacological activity within the brain parenchyma without first transiting this barrier. Understanding the process of permeation, however, is complicated by a combination of both limited passive diffusion and active transport. Our aim here was to establish predictive models for BBB drug permeation that include both active and passive transport. A database of 153 compounds was compiled using <em>in vivo</em> surface permeability product (logPS) values in rats as a quantitative parameter for BBB permeability. The open source Chemical Development Kit (CDK) was used to calculate physico-chemical properties and descriptors. Predictive computational models were implemented by machine learning paradigms (decision tree induction) on both descriptor sets. Models with a corrected classification rate (CCR) of 90% were established. Mechanistic insight into BBB transport was provided by an Ant Colony Optimization (ACO)-based binary classifier analysis to identify the most predictive chemical substructures. Decision trees revealed descriptors of lipophilicity (aLogP) and charge (polar surface area), which were also previously described in models of passive diffusion. However, measures of molecular geometry and connectivity were found to be related to an active drug transport component.http://www.mdpi.com/1420-3049/17/9/10429blood brain barrierdrug transportdecision tree inductionQSAR modeling |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jörg Huwyler Felix Hammann Claudia Suenderhauf |
spellingShingle |
Jörg Huwyler Felix Hammann Claudia Suenderhauf Computational Prediction of Blood-Brain Barrier Permeability Using Decision Tree Induction Molecules blood brain barrier drug transport decision tree induction QSAR modeling |
author_facet |
Jörg Huwyler Felix Hammann Claudia Suenderhauf |
author_sort |
Jörg Huwyler |
title |
Computational Prediction of Blood-Brain Barrier Permeability Using Decision Tree Induction |
title_short |
Computational Prediction of Blood-Brain Barrier Permeability Using Decision Tree Induction |
title_full |
Computational Prediction of Blood-Brain Barrier Permeability Using Decision Tree Induction |
title_fullStr |
Computational Prediction of Blood-Brain Barrier Permeability Using Decision Tree Induction |
title_full_unstemmed |
Computational Prediction of Blood-Brain Barrier Permeability Using Decision Tree Induction |
title_sort |
computational prediction of blood-brain barrier permeability using decision tree induction |
publisher |
MDPI AG |
series |
Molecules |
issn |
1420-3049 |
publishDate |
2012-08-01 |
description |
Predicting blood-brain barrier (BBB) permeability is essential to drug development, as a molecule cannot exhibit pharmacological activity within the brain parenchyma without first transiting this barrier. Understanding the process of permeation, however, is complicated by a combination of both limited passive diffusion and active transport. Our aim here was to establish predictive models for BBB drug permeation that include both active and passive transport. A database of 153 compounds was compiled using <em>in vivo</em> surface permeability product (logPS) values in rats as a quantitative parameter for BBB permeability. The open source Chemical Development Kit (CDK) was used to calculate physico-chemical properties and descriptors. Predictive computational models were implemented by machine learning paradigms (decision tree induction) on both descriptor sets. Models with a corrected classification rate (CCR) of 90% were established. Mechanistic insight into BBB transport was provided by an Ant Colony Optimization (ACO)-based binary classifier analysis to identify the most predictive chemical substructures. Decision trees revealed descriptors of lipophilicity (aLogP) and charge (polar surface area), which were also previously described in models of passive diffusion. However, measures of molecular geometry and connectivity were found to be related to an active drug transport component. |
topic |
blood brain barrier drug transport decision tree induction QSAR modeling |
url |
http://www.mdpi.com/1420-3049/17/9/10429 |
work_keys_str_mv |
AT jorghuwyler computationalpredictionofbloodbrainbarrierpermeabilityusingdecisiontreeinduction AT felixhammann computationalpredictionofbloodbrainbarrierpermeabilityusingdecisiontreeinduction AT claudiasuenderhauf computationalpredictionofbloodbrainbarrierpermeabilityusingdecisiontreeinduction |
_version_ |
1725668541160488960 |