Expanded Tox21 biological assay panel improves prediction of drug-induced liver injury and cardiotoxicity

Authors

• T Xu
• D Ngan
• J Zhao
• M Ooka
• S Sakamuru
• L Zhang
• S Yang
• M Xia
• A Simeonov
• R Huang

Abstract

Toxicology in the 21st 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. To address this limitation, we expanded the Tox21 portfolio to incorporate new assays that probe under-represented targets/pathways related to unanticipated adverse drug effects such as drug induced liver injury (DILI) and cardiotoxicity (DICT). Models were constructed using the data from the pre-existing panel of 36 assay targets and the expanded panel of 49 assay targets. For both DILI and DICT prediction, the optimal 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 either assay data or chemical structure alone. Finally, we applied the optimal models to predict the potential hepatotoxicity and cardiotoxicity of compounds in the Tox21 10K compound library, and experimentally validated the lead compounds to demonstrate the effectiveness of our models in identifying new compounds with the potential to induce liver injury or cardiotoxicity. 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.

Scientific Focus Area: Computational Biology

This page was last updated on Tuesday, August 6, 2024