High-Throughput Image-Based Assay for Identifying In Vitro Hepatocyte Microtubule Disruption.

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.