2002
DOI: 10.1089/10665270260518317
|View full text |Cite
|
Sign up to set email alerts
|

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 w… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

6
127
0

Year Published

2004
2004
2023
2023

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 148 publications
(133 citation statements)
references
References 7 publications
6
127
0
Order By: Relevance
“…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.…”
mentioning
confidence: 99%
“…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.…”
mentioning
confidence: 99%
“…[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.…”
Section: Static Properties Of Entire Moleculesmentioning
confidence: 99%
“…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].…”
Section: Classificationmentioning
confidence: 99%