Validation of counter propagation neural network models for predictive toxicology according to the OECD principles: a case study

Abstract

The OECD has proposed five principles for validation of QSAR models used for regulatory purposes. Here we present a case study investigating how these principles can be applied to models based on Kohonen and counter propagation neural networks. The study is based on a counter propagation network model that has been built using toxicity data in fish fathead minnow for 541 compounds. The study demonstrates that most, if not all, of the OECD criteria may be met when modeling using this neural network approach.

Keywords:

• Validation of QSAR models
• Counter propagation neural network
• Duluth database

Acknowledgement

MV acknowledges receipt of Senior Researcher Visitor grant from the ECB, Institute for Health and Consumer Protection, European Commission Joint Research Centre. C. Helma was funded by a grant (1328-179) of the Centre for Documentation and Evaluation of Alternatives to Animal Experiments (ZEBET) of the Federal Institute for Risk Assessment (BfR).