Hybrid non-animal modeling: A mechanistic approach to predict chemical hepatotoxicity

Developing mechanistic non-animal testing methods based on the adverse outcome pathway (AOP) framework must incorporate molecular and cellular key events associated with target toxicity. Using data from an in vitro assay and chemical structures, we aimed to create a hybrid model to predict hepatotoxicants. We first curated a reference dataset of 869 compounds for hepatotoxicity modeling and profiled them against PubChem for existing in vitro toxicity data. Of the 2,560 resulting assays, we selected the mitochondrial membrane potential (MMP) assay, a high-throughput screening (HTS) tool that can test chemical disruptors for mitochondrial function. Then, machine learning was applied to develop quantitative structure-activity relationship (QSAR) models with 2,536 compounds tested in the MMP assay for screening new compounds. The MMP assay results, including QSAR model outputs, yielded hepatotoxicity predictions for reference set compounds with a Correct Classification Ratio (CCR) of 0.59. The predictivity improved by including 37 structural alerts (CCR = 0.8). We validated our model by testing 37 reference set compounds in human HepG2 hepatoma cells and reliably predicted these compounds for hepatotoxicity (CCR = 0.79). This study introduces a novel AOP modeling strategy that combines public HTS data, computational modeling, and experimental testing to predict chemical hepatotoxicity. Environmental implication This research advances computational toxicology using an Adverse Outcome Pathway (AOP) modeling strategy, integrating chemical structure and biological data for more accurate hepatotoxicity predictions. Our approach can identify potential liver toxicity risks associated with new chemicals, recognizing them as environmental hazards. By improving risk assessments through a combination of computational and experimental approaches, our study addresses environmental concerns by anticipating and mitigating the harmful impact of hazardous materials on human health. Furthermore, this approach helps develop safer chemical alternatives, thereby reducing overall environmental and health risks.