Evaluation of the OECD (Q)SAR Application Toolbox and Toxtree for predicting and profiling the carcinogenic potential of chemicals

Abstract

The OECD (Q)SAR Application Toolbox and Toxtree are software tools used in regulatory toxicology to fill gaps in (eco)toxicity data. They include different SAR and QSAR models for estimating (eco)toxicological endpoints. Among them, the Benigni/Bossa rule-based system is proposed to characterize the carcinogenic potential of chemicals. Our study evaluates the predictive performance that can be expected from the OECD (Q)SAR Toolbox and Toxtree when analysing chemicals by means of the structural alerts coded within the Benigni/Bossa rule-based system for carcinogenicity and the associated QSAR model (QSAR8). These evaluations have been carried out thanks to a large collection of chemicals retrieved from original publications and public databases. Overall, our findings confirm the performance of the system of structural alerts while suggesting that the sensitivity of QSAR8, as implemented in the two tools, is lower than what was previously reported. They also indicate that attention has to be paid when interpreting the output of the two tools because of possible malfunctions involving the coding of two-dimensional structures. A set of possible modulating factors for the structural alert identifying polycyclic aromatic hydrocarbons is also proposed together with candidates for putative new structural alerts not included in the tested tools.