Related Experiment Video
Updated: Jul 18, 2025
Human Liver Microphysiological System for Assessing Drug-Induced Liver Toxicity In Vitro
Published on: January 31, 2022
Unraveling the mechanisms underlying drug-induced cholestatic liver injury: identifying key genes using machine
Jian Jiang1, Jonas van Ertvelde2, Gökhan Ertaylan3
1Entity of In Vitro Toxicology and Dermato‑Cosmetology, Department of Pharmaceutical and Pharmacological Sciences, Vrije Universiteit Brussel, Laarbeeklaan 103, 1090, Brussels, Belgium. jian.jiang@vub.be.
Abstract:
Drug-induced intrahepatic cholestasis (DIC) is a main type of hepatic toxicity that is challenging to predict in early drug development stages. Preclinical animal studies often fail to detect DIC in humans. In vitro toxicogenomics assays using human liver cells have become a practical approach to predict human-relevant DIC. The present study was set up to identify transcriptomic signatures of DIC by applying machine learning algorithms to the Open TG-GATEs database. A total of nine DIC compounds and nine non-DIC compounds were selected, and supervised classification algorithms were applied to develop prediction models using differentially expressed features. Feature selection techniques identified 13 genes that achieved optimal prediction performance using logistic regression combined with a sequential backward selection method. The internal validation of the best-performing model showed accuracy of 0.958, sensitivity of 0.941, specificity of 0.978, and F1-score of 0.956. Applying the model to an external validation set resulted in an average prediction accuracy of 0.71. The identified genes were mechanistically linked to the adverse outcome pathway network of DIC, providing insights into cellular and molecular processes during response to chemical toxicity. Our findings provide valuable insights into toxicological responses and enhance the predictive accuracy of DIC prediction, thereby advancing the application of transcriptome profiling in designing new approach methodologies for hazard identification.
Insights
This study identifies 13 key genes using machine learning to predict drug-induced intrahepatic cholestasis (DIC). This approach enhances early drug development by improving the accuracy of predicting liver toxicity in humans.
Area of Science:
- Toxicology
- Genomics
- Drug Development
Background:
- Drug-induced intrahepatic cholestasis (DIC) is a significant form of liver toxicity.
- Predicting DIC early in drug development is challenging, as animal models often fail to identify human-relevant risks.
- In vitro toxicogenomics using human liver cells offers a promising approach for predicting human-relevant DIC.
Purpose of the Study:
- To identify transcriptomic signatures for predicting drug-induced intrahepatic cholestasis (DIC).
- To develop and validate machine learning models for enhanced DIC prediction accuracy.
- To explore the mechanistic links between identified genes and the adverse outcome pathway network of DIC.
Main Methods:
- Applied machine learning algorithms, specifically supervised classification and sequential backward selection, to the Open TG-GATEs database.
- Selected nine DIC and nine non-DIC compounds for analysis.
- Identified 13 predictive genes using logistic regression and feature selection techniques.
Main Results:
- A predictive model using 13 genes achieved high internal validation performance (accuracy: 0.958, F1-score: 0.956).
- The model demonstrated an average prediction accuracy of 0.71 on an external validation set.
- The identified genes were mechanistically linked to the adverse outcome pathway network of DIC.
Conclusions:
- Transcriptomic profiling combined with machine learning can significantly enhance the prediction of drug-induced liver toxicity.
- The identified gene signatures provide insights into cellular responses to chemical toxicity.
- This approach advances new methodologies for hazard identification in drug development.
