Validation of Counter Propagation Neural Network Models for Predictive Toxicology According to the OECD Principles. A Case Study
OECD adopted five principles for validation of QSAR models used for regulatory purposes. We present Kohonen neural networks and counter propagation neural networks, which are often used for QSAR modeling, in the light of these principles. As a case study we present a counter propagation network built on 541 compounds for modeling of toxicity toward fish fathead minnow.
VRACKO GROBELSEK Marjan;
BANDELJ Vinko;
BARBIERI Pierluigi;
BENFENATI Emilio;
CHAUDHRY Quasim;
CRONIN Mark;
DEVILLERS James;
GALLEGOS SALINER Ana;
GINI Guiseppina;
GRAMATICA Paola;
HELMA Christoph;
NEAGU Daniel;
NETZEVA Tatiana;
PAVAN Manuela;
TIER Grace;
RANDIC Milan;
WORTH Andrew;
TSAKOVSKA Ivanka;
2007-01-10
TAYLOR & FRANCIS INC
JRC31712
https://publications.jrc.ec.europa.eu/repository/handle/JRC31712,
10.1080/10659360600787650,
Additional supporting files
| File name | Description | File type | |
|---|
