Comparison of the Applicability Domain of a QSAR for Estrogenicity with a Large Chemical Inventory

The aim of this study was to illustrate that it is possible and relatively straightforward to compare the domain of applicability of a quantitative structure-activity relationship (QSAR) model in terms of its physicochemical descriptors with a large inventory of chemicals. A training set of 105 chemicals with data for relative estrogenic gene activation, obtained in a recombinant yeast assay, was used to develop the QSAR. A binary classification model for prediction of “active” versus ”inactive” chemicals was developed by using classification tree analysis and two descriptors with a clear physicochemical meaning (octanol-water partition coefficient – log Kow, and number of hydrogen bond donors – nHdon). The model demonstrated a high overall accuracy (95.9%) with a sensitivity of 96.3% and a specificity of 78.1%. The robustness of the model was evaluated by using the leave-many-out (LMO) cross-validation technique, while the predictivity was assessed by means of an artificial external test set, composed of 12 compounds. The domain of the QSAR training set was compared with the chemical space covered by the European Inventory of Existing Commercial Chemical Substances (EINECS) as incorporated in the OASIS software, in the log Kow and nHdon plane. The results showed that the training set and therefore the applicability domain of the QSAR model covers a small part of the physicochemical domain of the inventory, even though a simple method for defining the applicability domain (ranges in the descriptor space) was used. However, a large number of compounds are located within the narrow descriptor window.

NETZEVA Tatiana;  GALLEGOS SALINER Ana;  WORTH Andrew; 

2006-11-15

SETAC PRESS

JRC33550

https://publications.jrc.ec.europa.eu/repository/handle/JRC33550,