Toxicology in the 21^st Century (Tox21) assay data provide a valuable resource for the prediction of in vivo toxicity using machine learning models. However, the performances of these models previously developed using the pre-existing Tox21 assay data were less than ideal, likely due to insufficient coverage of the biological response space by the assay targets.

This study aimed to assess whether expanding the Tox21 portfolio with new assays that probe under-represented targets/pathways related to unanticipated adverse drug effects could improve the predictive capacity of in vitro assay data for in vivo toxicity such as drug induced liver injury (DILI) and cardiotoxicity (DICT).

Models were constructed using data from the pre-existing panel of 36 assay targets and the expanded panel of 49 assay targets. A feature selection approach was used to determine the optimal number of assays needed for each model. The models were then applied to predict the potential hepatotoxicity and cardiotoxicity of compounds in the Tox21 10K compound library.

For both DILI and DICT prediction, the best-performing models developed using the expanded assay panel required a smaller number of assays to achieve the same level of performance compared to those based on the pre-existing assays. Models constructed by combining both assay data (pre-existing + expanded) and chemical structure consistently outperformed those constructed based on assay data alone, but showed similar performance to those constructed based on chemical structure. The compounds predicted to have the highest toxic potential were experimentally verified to demonstrate the effectiveness of our models in identifying new potentially toxic compounds.

The expansion of the Tox21 assay panel has significantly enhanced the predictive capacity of assay data for predicting DILI and DICT potential. This improvement underscores the importance of a diverse and comprehensive in vitro assay portfolio in advancing safety assessment. https://doi.org/10.1289/EHP16190