A computational framework to in silico screen for drug-induced hepatocellular toxicity
Related Experiment Video
Updated: Jun 23, 2025
Human Liver Microphysiological System for Assessing Drug-Induced Liver Toxicity In Vitro
Published on: January 31, 2022
Yueshan Zhao1, Ji Youn Park1, Da Yang1,2,3
1Department of Pharmaceutical Sciences, Center for Pharmacogenetics, University of Pittsburgh, Pittsburgh, PA 15261, United States.
Abstract:
Drug-induced liver injury (DILI) is the most common trigger for acute liver failure and the leading cause of attrition in drug development. In this study, we developed an in silico framework to screen drug-induced hepatocellular toxicity (INSIGHT) by integrating the post-treatment transcriptomic data from both rodent models and primary human hepatocytes. We first built an early prediction model using logistic regression with elastic net regularization for 123 compounds and established the INSIGHT framework that can screen for drug-induced hepatotoxicity. The 235 signature genes identified by INSIGHT were involved in metabolism, bile acid synthesis, and stress response pathways. Applying the INSIGHT to an independent transcriptomic dataset treated by 185 compounds predicted that 27 compounds show a high DILI risk, including zoxazolamine and emetine. Further integration with cell image data revealed that predicted compounds with high DILI risk can induce abnormal morphological changes in the endoplasmic reticulum and mitochondrion. Clustering analysis of the treatment-induced transcriptomic changes delineated distinct DILI mechanisms induced by these compounds. Our study presents a computational framework for a mechanistic understanding of long-term liver injury and the prospective prediction of DILI risk.
Insights
A new computational framework, INSIGHT, screens for drug-induced liver injury (DILI) by analyzing gene expression. It predicts high-risk compounds and reveals underlying toxicity mechanisms.
Area of Science:
- Hepatotoxicity and Drug Development
- Computational Toxicology
- Transcriptomics Analysis
Background:
- Drug-induced liver injury (DILI) is a major cause of acute liver failure and drug development failure.
- Accurate prediction of DILI risk is crucial for drug safety and development.
- Existing methods for DILI assessment have limitations in predicting long-term liver injury.
Purpose of the Study:
- To develop and validate an in silico framework, INSIGHT, for screening drug-induced hepatocellular toxicity.
- To identify molecular signatures associated with DILI using transcriptomic data.
- To provide a mechanistic understanding of DILI and predict its risk.
Main Methods:
- Integrated post-treatment transcriptomic data from rodent models and primary human hepatocytes.
- Developed a logistic regression model with elastic net regularization for early prediction.
- Identified 235 signature genes involved in metabolism, bile acid synthesis, and stress response pathways.
- Applied the INSIGHT framework to an independent dataset of 185 compounds.
- Integrated cell image data to assess morphological changes.
Main Results:
- The INSIGHT framework successfully screened for drug-induced hepatotoxicity.
- Predicted 27 out of 185 compounds as having a high DILI risk, including zoxazolamine and emetine.
- High DILI risk compounds induced abnormal endoplasmic reticulum and mitochondrial morphology.
- Clustering analysis revealed distinct DILI mechanisms for different compounds.
Conclusions:
- INSIGHT provides a computational framework for mechanistic understanding and prospective prediction of DILI risk.
- The framework integrates transcriptomic and cell imaging data for comprehensive toxicity assessment.
- This approach can aid in early identification of hepatotoxic compounds, reducing attrition in drug development.
