Related Experiment Video
Updated: Jun 12, 2025
Human Liver Microphysiological System for Assessing Drug-Induced Liver Toxicity In Vitro
Published on: January 31, 2022
High-Throughput Image-Based Assay for Identifying In Vitro Hepatocyte Microtubule Disruption
Yang Li1, Andrew J Bowling1, Audrey Lehman1
1Corteva Agriscience, Indianapolis, Indiana 46268, United States.
Abstract:
Disruption of microtubule stability in mammalian cells may lead to genotoxicity and carcinogenesis. The ability to screen for microtubule destabilization or stabilization is therefore a useful and efficient approach to aid in the design of molecules that are safe for human health. In this study, we developed a high-throughput 384-well assay combining immunocytochemistry with high-content imaging to assess microtubule disruption in the metabolically competent human liver cell line: HepaRG. To enhance analysis throughput, we implemented a supervised machine learning approach using a curated training library of 180 compounds. A majority voting ensemble of eight machine learning classifiers was employed for predicting microtubule disruptions. Our prediction model achieved over 99.0% accuracy and a 98.4% F1 score, which reflects the balance between precision and recall for in-sample validation and 93.5% accuracy and a 94.3% F1 score for out-of-sample validation. This automated image-based testing can provide a simple, high-throughput screening method for early stage discovery compounds to reduce the potential risk of genotoxicity for crop protection product development.
Insights
This study developed a high-throughput assay using machine learning to accurately predict microtubule disruption, a key factor in genotoxicity and cancer risk. This method aids in designing safer molecules for human health and crop protection.
Area of Science:
- Cell Biology
- Toxicology
- Computational Biology
Background:
- Microtubule stability is crucial for cellular function; disruptions can lead to genotoxicity and carcinogenesis.
- Screening for microtubule agents is vital for developing safe molecules for human health.
- HepaRG cells offer a metabolically competent model for liver-based toxicity studies.
Purpose of the Study:
- To develop a high-throughput screening assay for assessing microtubule disruption.
- To utilize machine learning for accurate prediction of microtubule-targeting compounds.
- To facilitate the design of safer molecules in drug and crop protection development.
Main Methods:
- A 384-well immunocytochemistry assay combined with high-content imaging was established using HepaRG cells.
- A supervised machine learning model, an ensemble of eight classifiers, was trained on 180 compounds.
- The model predicted microtubule disruption based on image analysis.
Main Results:
- The prediction model achieved high accuracy (>99.0% in-sample, 93.5% out-of-sample) and F1 scores (>98.4% in-sample, 94.3% out-of-sample).
- The automated image-based assay demonstrated efficiency and reliability in identifying microtubule disruptors.
- The method successfully validated its predictive power on unseen compounds.
Conclusions:
- This automated, image-based assay provides a simple and high-throughput method for screening compounds.
- The developed machine learning model accurately predicts microtubule disruption, aiding in early-stage compound assessment.
- This approach can significantly reduce the risk of genotoxicity in product development, particularly for crop protection agents.
