| Autor: |
Gadaleta D; Laboratory of Environmental Chemistry and Toxicology, Department of Environmental Health Sciences, Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 20156 Milan, Italy., Marzo M; Laboratory of Environmental Chemistry and Toxicology, Department of Environmental Health Sciences, Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 20156 Milan, Italy., Toropov A; Laboratory of Environmental Chemistry and Toxicology, Department of Environmental Health Sciences, Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 20156 Milan, Italy., Toropova A; Laboratory of Environmental Chemistry and Toxicology, Department of Environmental Health Sciences, Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 20156 Milan, Italy., Lavado GJ; Laboratory of Environmental Chemistry and Toxicology, Department of Environmental Health Sciences, Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 20156 Milan, Italy., Escher SE; Fraunhofer Institute for Toxicology and Experimental Medicine (ITEM), 30625 Hannover, Germany., Dorne JLCM; Scientific Committee and Emerging Risks Unit, European Food Safety Authority, 43126 Parma, Italy., Benfenati E; Laboratory of Environmental Chemistry and Toxicology, Department of Environmental Health Sciences, Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 20156 Milan, Italy. |
| Abstrakt: |
Repeated-dose toxicity (RDT) is a critical endpoint for hazard characterization of chemicals and is assessed to derive safe levels of exposure for human health. Here we present the first attempt to model simultaneously no-observed-(adverse)-effect level (NO(A)EL) and lowest-observed-(adverse)-effect level (LO(A)EL). Classification and regression models were derived based on rat sub-chronic repeated dose toxicity data for 327 compounds from the Fraunhofer RepDose database. Multi-category classification models were built for both NO(A)EL and LO(A)EL though a consensus of statistics- and fragment-based algorithms, while regression models were based on quantitative relationships between the endpoints and SMILES-based attributes. NO(A)EL and LO(A)EL models were integrated, and predictions were compared to exclude inconsistent values. This strategy improved the performance of single models, leading to R 2 greater than 0.70, root-mean-square error (RMSE) lower than 0.60 (for regression models), and accuracy of 0.61-0.73 (for classification models) on the validation set, based on the endpoint and the threshold applied for selecting predictions. This study confirms the effectiveness of the modeling strategy presented here for assessing RDT of chemicals using in silico models. |
