Original JRC researchEuropean Union Reference Laboratory for Alternatives to Animal Testing, JRC (Italy)http://hdl.handle.net/10967/2332024-03-28T15:39:06Z2024-03-28T15:39:06ZPavan, M.; Worth, A.; Netzeva, T. Preliminary analysis of an aquatic toxicity dataset and assessment of QSAR models for narcosis. EUR 21749 EN. European Commission, Joint Research Centre, 2005.http://hdl.handle.net/10967/2192023-10-26T09:30:11Z2020-03-10T11:20:06ZThe purpose of the analyses presented in this report was to contribute to an evaluation of the possibility of using QSAR predictions for regulatory purposes. To this end QSAR predictions were compared with SIDS test data. Furthermore, the models were also assessed according to the extent to which they meet OECD principles for QSAR validation (OECD ENV/JM/Mono(2004)24). It is emphasized that the comparisons are not intended to be scientific validations, because the SIDS test chemicals were not selected to ensure that they are sufficiently diverse and representative for the entire applicability domain of the individual models. Nevertheless, many of the analyses presented here form the basis for scientific validation.
2020-03-10T11:20:06ZSaliner, A. G.; Netzeva, T. I.; Worth, A. P. Prediction of estrogenicity: validation of a classification model. SAR QSAR Environ. Res. 2006, 17, 195–223.http://hdl.handle.net/10967/2132020-05-08T10:14:14Z2020-01-10T08:46:28Z(Q)SAR models can be used to reduce animal testing as well as to minimise the testing costs. In particular, classification models have been widely used for estimating endpoints with binary activity. The aim of the present study was to develop and validate a classification-based quantitative structure-activity relationship (QSAR) model for endocrine disruption, based on interpretable mechanistic descriptors related to estrogenic gene activation. The model predicts the presence or absence of estrogenic activity according to a pre-defined cut-off in activity as determined in a recombinant yeast assay. The experimental data was obtained from the literature. A two-descriptor classification model was developed that has the form of a decision tree. The predictivity of the model was evaluated by using an external test set and by taking into account the limitations associated with the applicability domain (AD) of the model. The AD was determined as coverage of the model descriptor space. After removing the compounds present in the training set and the compounds outside of the AD, the overall accuracy of classification of the test chemicals was used to assess the predictivity of the model. In addition, the model was shown to meet the OECD Principles for (Q)SAR Validation, making it potentially useful for regulatory purposes.
2020-01-10T08:46:28Z