Related Experiment Video
Updated: Aug 12, 2025
Human Liver Microphysiological System for Assessing Drug-Induced Liver Toxicity In Vitro
Published on: January 31, 2022
Prediction of drug-induced hepatotoxicity based on histopathological whole slide images
Ran Su1, Hao He1, Changming Sun2
1School of Computer Software, College of Intelligence and Computing, Tianjin University, China.
Abstract:
Liver is an important metabolic organ in human body and is sensitive to toxic chemicals or drugs. Adverse reactions caused by drug hepatotoxicity will damage the liver and hepatotoxicity is the leading cause of removal of approved drugs from the market. Therefore, it is of great significance to identify liver toxicity as early as possible in the drug development process. In this study, we developed a predictive model for drug hepatotoxicity based on histopathological whole slide images (WSI) which are the by-product of drug experiments and have received little attention. To better represent the WSIs, we constructed a graph representation for each WSI by dividing it into small patches, taking sampled patches as nodes and calculating the correlation coefficients between node features as the edges of the graph structure. Then a WSI-level graph convolutional network (GCN) was built to effectively extract the node information of the graph and predict the toxicity. In addition, we introduced a gated attention global context vector (gaGCV) to combine the global context to make node features to contain more comprehensive information. The results validated on rat liver in vivo data from the Open TG-GATES show that the use of WSI for the prediction of toxicity is feasible and effective.
Insights
This study introduces a novel method to predict drug-induced liver toxicity using histopathology whole slide images (WSI). The approach utilizes graph convolutional networks (GCN) for early detection, improving drug safety.
Area of Science:
- Toxicology
- Computational Pathology
- Drug Development
Background:
- Drug-induced hepatotoxicity is a major reason for drug recalls.
- Early identification of liver toxicity is crucial in drug development.
- Histopathological whole slide images (WSI) are underutilized in toxicity prediction.
Purpose of the Study:
- To develop a predictive model for drug hepatotoxicity using WSI.
- To leverage WSI data, often a byproduct of drug experiments.
- To enhance early detection of liver damage during drug development.
Main Methods:
- Constructed graph representations for WSIs by dividing them into patches (nodes) and using correlation coefficients as edges.
- Developed a WSI-level graph convolutional network (GCN) for feature extraction.
- Incorporated a gated attention global context vector (gaGCV) to enrich node features.
Main Results:
- Demonstrated the feasibility and effectiveness of using WSI for toxicity prediction.
- Validated the model on rat liver in vivo data from the Open TG-GATES dataset.
- The GCN model successfully extracted relevant information from WSI for toxicity prediction.
Conclusions:
- Histopathological whole slide images (WSI) are a valuable data source for predicting drug hepatotoxicity.
- The developed GCN-based model offers a promising approach for early toxicity assessment.
- This method can contribute to improving drug safety and reducing market withdrawals.
More Related Videos
07:32Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis
Published on: April 12, 2024
08:59An Intestine/Liver Microphysiological System for Drug Pharmacokinetic and Toxicological Assessment
Published on: December 3, 2020