Counter propagation artificial neural network categorical models for prediction of carcinogenicity for non-congeneric chemicals

Abstract

One of the main goals of the new chemical regulation REACH (Registration, Evaluation and Authorization of Chemicals) is to fill the gaps on the toxicological properties of chemicals that affect human health. Carcinogenicity is one of the endpoints under consideration. The information obtained from (quantitative) structure–activity relationship ((Q)SAR) models is accepted as an alternative solution to avoid expensive and time-consuming animal tests. The reported results were obtained within the framework of the European project ‘Computer Assisted Evaluation of industrial chemical Substances According to Regulations (CAESAR)’. In this article, we demonstrate intermediate results for counter propagation artificial neural network (CP ANN) models for the prediction category of the carcinogenic potency using two-dimensional (2D) descriptors from different software programs. A total of 805 non-congeneric chemicals were extracted from the Carcinogenic Potency Database (CPDBAS). The resulting models had prediction accuracies for internal (training) and external (test) sets as high as 91–93% and 68–70%, respectively. The sensitivity and specificity of the test set were 69–73 and 63–72% correspondingly. High specificity is critical in models for regulatory use that are aimed at ensuring public safety. Thus, the errors that give rise to false negatives are much more relevant. We discuss how we can increase the number of correctly predicted carcinogens using the correlation between the threshold and the values of the sensitivity and specificity.

Keywords:

• REACH
• QSAR
• CP ANN
• categorical models
• ROC
• carcinogenicity

Acknowledgements

The financial support of the European Union through CAESAR project (SSPI-022674) as well as that of the Slovenian Ministry of Higher Education, Science and Technology (grant P1-017) is gratefully acknowledged. We would also like to thank G. Schüürmann, R. Kühne and Ralf-Uwe Ebert (Helmholtz Centre for Environmental Research, Leipzig, Germany (UFZ)) for their technical support in running the training/prediction set splitting. We would like to thank all partners of the CAESAR project for cooperation in the development of the carcinogenicity models, especially Q. Chaudry, the leader of the Central Science Laboratory (CSL DEFRA), UK, and Jane Cotterill who was involved in the project.