Artificial intelligence-driven phenotyping of zebrafish psychoactive drug responses

Area of Science:

• Neuroscience
• Pharmacology
• Artificial Intelligence

Background:

• Zebrafish (Danio rerio) are increasingly used in biomedicine for disease modeling and drug discovery.
• Growing use in neuroscience research necessitates advanced, unbiased methods for neurophenotypic data analysis.
• Current neurophenotyping methods require improvement for efficiency and accuracy.

Purpose of the Study:

• To develop and validate artificial intelligence (AI) algorithms for classifying psychotropic drugs based on zebrafish behavior.
• To establish a novel framework for AI-driven neurophenotyping in zebrafish.
• To enhance the utility of zebrafish as a model organism in drug discovery and development.

Main Methods:

• Applied AI neural network algorithms to a large dataset of adult zebrafish locomotor tracks.
• Trained AI models to recognize distinct behavioral patterns induced by various psychotropic drugs.
• Validated AI prediction accuracy by comparing drug agents with known pharmacological profiles.

Main Results:

• AI algorithms successfully learned to differentiate between various psychotropic agents based on zebrafish locomotor data.
• The trained AI demonstrated high accuracy in predicting drug effects, correlating with known pharmacological actions.
• A robust framework for AI-driven movement pattern classification in zebrafish was established.

Conclusions:

• AI-powered neurophenotyping offers a reliable and unbiased approach for analyzing zebrafish behavior.
• This methodology can significantly accelerate drug discovery and development pipelines.
• Zebrafish, analyzed with AI, represent a powerful model organism for neuroscience research.