根据经合组织原则对用于预测毒理学的反向传播神经网络模型进行验证：案例研究

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

作者信息

Vracko M, Bandelj V, Barbieri P, Benfenati E, Chaudhry Q, Cronin M, Devillers J, Gallegos A, Gini G, Gramatica P, Helma C, Mazzatorta P, Neagu D, Netzeva T, Pavan M, Patlewicz G, Randić M, Tsakovska I, Worth A

机构信息

European Chemical Beaureau, Institute for Health and Consumer Protection, European Commission Joint Research Centre, 21020 Ispra, Italy.

出版信息

SAR QSAR Environ Res. 2006 Jun;17(3):265-84. doi: 10.1080/10659360600787650.

DOI:10.1080/10659360600787650

PMID:16815767

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.

摘要

经济合作与发展组织（OECD）提出了五条用于监管目的的定量构效关系（QSAR）模型验证原则。在此，我们展示一个案例研究，探究这些原则如何应用于基于科霍宁（Kohonen）和反传神经网络的模型。该研究基于一个反传网络模型，此模型利用541种化合物对黑头呆鱼的毒性数据构建而成。该研究表明，使用这种神经网络方法进行建模时，即便不能满足经济合作与发展组织的所有标准，也能满足大部分标准。