Science Inventory

The CAESAR models for developmental toxicity

Citation:

Cassano, A., A. Manganaro, T. M. MARTIN, D. M. YOUNG, N. Piclin, M. Pintore, D. Bigoni, AND E. Benfenati. The CAESAR models for developmental toxicity. Chemistry Central Journal. BioMed Central Ltd, London, Uk, 4(Suppl 1):S4, (2010).

Impact/Purpose:

To inform the public.

Description:

The new REACH legislation requires assessment of a high number of chemicals in the European market for several endpoints. Developmental Toxicity results amongst the most difficult endpoint to assess, due to the complexity, length and costs of experiments. Following the encouragement toward QSAR (in silico) methods contained in the REACH itself, in the CAESAR project several models have been developed. Methods: Two QSAR models for Developmental Toxicity have been developed, using different statistical/mathematical methods and same dataset built from available studies. The first model makes a classification based on a random forest algorithm, while the second model is based on an adaptive fuzzy partition. The first model has been implemented and inserted into the CAESAR on-line application, which is Java-based software that allows everyone to freely use the models developed. Results/Conclusion: Both models showed good performance, and have been aimed to minimize false negatives. Thus, are useful for meeting REACH requirements. The CAESAR on-line application ensures both industries and regulators can easily access and use the Developmental Toxicity model (along with the models for the other four endpoints).

Record Details:

Record Type:DOCUMENT( JOURNAL/ PEER REVIEWED JOURNAL)
Product Published Date:07/29/2010
Record Last Revised:10/29/2010
OMB Category:Other
Record ID: 220392