DNA adducts as link between in vitro and in vivo carcinogenicity - A case study with benzo[a]pyrene

To reduce the need for animal tests, in vitro assays ar e often used as alternative methods. To derive toxic doses for higher tier organisms from in vitro assay results, quantitative in vitro-in vivo extrapolation (qIVIVE) based on physiological-based toxicokinetic (PBTK) models is typically the preferred approach. Such PBTK models require many input parameters to address the route from dose to target site concentration. However, respective data is ve r y often not available. Hence, our aim is to ca l l attention to an alternative w a y to build a li n k between animal (in vivo) and cell-derived (in vitro) toxicity data. To this end, we selected the carcinogenic chemical benzo[a]pyrene (BaP) for our study. Our approach relates both in vitro assay and in vivo data to a main intermediat e marker structu r e for carcinogenicity on the subcellula r level - the BaP-DNA adduct BaP-7,8-dihydrodiol-9,10-epoxide-deoxyguanosine. Thus, BaP dose is directly linked to a measure of the toxicity-initiatin g event. We used Syrian hamster embryo (SHE) and Balb/c 3T3 cel l transformation assay as in vitro data and compared these data to outcomes of in vivo carcinogenicity tests in rodents. In vitro and in vivo DNA adduct levels range within three orders of magnitude. Especially metabolic saturation at higher doses and interspecies variabilities ar e identified and critically discussed as possible sources of errors in our simplified approach. Finally, ou r study point s out possible routes t o overcome limitations of the envisaged approach in order t o allow for a reliable qIVIVE in the future.