Predictive Human Intestinal Absorption QSAR Models Using Bayesian Regularized Neural Networks

Mitchell J. Polley; Frank R. Burden; David A. Winkler

doi:10.1071/CH05202

RESEARCH ARTICLE

Previous Next Contents Vol 58(12)

Predictive Human Intestinal Absorption QSAR Models Using Bayesian Regularized Neural Networks

Mitchell J. Polley ^A ^B , Frank R. Burden ^A ^B and David A. Winkler ^A ^B ^C

+ Author Affiliations

- Author Affiliations

^A Centre for Complexity in Drug Design, CSIRO Molecular and Health Technologies, Clayton South VIC 3168, Australia.

^B School of Chemistry, Monash University, Clayton VIC 3168, Australia.

^C Corresponding author. Email: david.winkler@csiro.au

Australian Journal of Chemistry 58(12) 859-863 https://doi.org/10.1071/CH05202
Submitted: 10 August 2005 Accepted: 14 November 2005 Published: 20 December 2005

Abstract

An oral dosage form is generally the most popular with patients. Many drug candidates fail in late development because of unfavourable absorption and pharmacokinetic profiles, or toxicity, among other factors (ADMET properties). This contributes to the fall in the efficiency of the pharmaceutical industry and to the rise in health costs. The ability to predict ADMET properties of drug leads can contribute to overcoming this problem. We have modelled intestinal absorption using several types of molecular descriptors and a non-linear Bayesian regularized neural network. Our models show very good predictive properties and are able to account for essentially all of the variance in the data that is not due to experimental error.

Acknowledgment

We thank Mike Abraham for providing the intestinal absorption data and structures used in his study.

References

Predictive Human Intestinal Absorption QSAR Models Using Bayesian Regularized Neural Networks

Abstract

Acknowledgment

Subscriber Login