Related Experiment Video
Updated: Jul 14, 2026
Human Liver Microphysiological System for Assessing Drug-Induced Liver Toxicity In Vitro
Published on: January 31, 2022
Development of an approach for ab initio estimation of compound-induced liver injury based on global gene
Xudong Dai1, Yudong D He, Hongyue Dai
1Rosetta Inpharmatics LLC, Merck & Co., Inc., Seattle, WA 98109, USA. xudong_dai@merck.com
Abstract:
Toxicity is a major cause of failure in drug development. A toxicogenomic approach may provide a powerful tool for better assessing the potential toxicity of drug candidates. Several approaches have been reported for predicting hepatotoxicity based on reference compounds with well-studied toxicity mechanisms. We developed a new approach for assessing compound-induced liver injury without prior knowledge of a compound's mechanism of toxicity. Using samples from rodents treated with 49 known liver toxins and 10 compounds without known liver toxicity, we derived a hepatotoxicity score as a single quantitative measurement for assessing the degree of induced liver damage. Combining the sensitivity of the hepatotoxicity score and the power of a machine learning algorithm, we then built a model to predict compound-induced liver injury based on 212 expression profiles. As estimated in an independent data set of 54 expression profiles, the built model predicted compound-induced liver damage with 90.9% sensitivity and 88.4% specificity. Our findings illustrate the feasibility of ab initio estimation of liver toxicity based on transcriptional profiles.
Insights
This study introduces a novel toxicogenomic method to predict drug-induced liver injury. The approach uses transcriptional profiles to assess liver toxicity without knowing the compound's mechanism, achieving high accuracy.
Area of Science:
- Toxicogenomics
- Computational Biology
- Drug Development
Background:
- Drug development frequently fails due to unforeseen toxicity, particularly hepatotoxicity.
- Existing methods for predicting hepatotoxicity often rely on known toxicity mechanisms of reference compounds.
- A need exists for predictive models that can assess liver injury without prior mechanistic knowledge.
Purpose of the Study:
- To develop a novel approach for assessing compound-induced liver injury (CILI) using toxicogenomic data.
- To create a predictive model for CILI that does not require prior knowledge of the compound's toxicity mechanism.
- To establish a quantitative hepatotoxicity score for measuring induced liver damage.
Main Methods:
- Collected rodent samples from treatment with 49 known liver toxins and 10 non-toxic compounds.
- Derived a hepatotoxicity score as a quantitative measure of liver damage.
- Developed a machine learning model using 212 expression profiles to predict CILI.
Main Results:
- The developed hepatotoxicity score effectively quantifies the degree of induced liver damage.
- The machine learning model, integrating the hepatotoxicity score and expression profiles, predicted CILI with 90.9% sensitivity and 88.4% specificity on an independent dataset.
- Demonstrated the feasibility of *ab initio* estimation of liver toxicity from transcriptional profiles.
Conclusions:
- The developed toxicogenomic approach enables accurate prediction of compound-induced liver injury.
- This method offers a powerful tool for early toxicity assessment in drug development, reducing failure rates.
- The findings support the utility of transcriptional profiling for *ab initio* toxicity evaluation.
