Related Experiment Video
Updated: May 23, 2025
06:19
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
Published on: August 16, 2024
357
Automatic quantification of disgust reactions in mice using machine learning
Shizuki Inaba1, Naofumi Uesaka2, Daisuke H Tanaka3
1Department of Cognitive Neurobiology, Graduate School of Medical and Dental Sciences, Institute of Science Tokyo, 1-5-45 Yushima, Bunkyo-ku, Tokyo, 113-8519, Japan.
Scientific Reports
|May 21, 2025
Summary
This study introduces a machine learning method to automatically count disgust reactions in mice, significantly reducing analysis time. The automated system accurately quantifies these reactions, aiding large-scale experiments.
Area of Science:
- Neuroscience
- Animal Behavior
- Machine Learning
Background:
- Disgust is a primary emotion crucial for protection against toxins and infections.
- Quantifying disgust reactions in rodents traditionally involves time-consuming manual video analysis.
- The taste reactivity test is a key method for assessing disgust in animal models.
Purpose of the Study:
- To develop and validate an automated method for quantifying disgust reactions in mice using machine learning.
- To reduce the labor and time associated with analyzing disgust responses in rodent studies.
Main Methods:
- Utilized DeepLabCut for automated tracking of mouse facial and paw movements.
- Employed a random forest classifier trained on manually labeled disgust reaction data.
- Validated the automated method against manual counting using a test dataset.
Main Results:
- The automated method achieved high correlation (Pearson's r = 0.97) with manual counts of disgust reactions.
- Machine learning significantly decreased the time and effort required for data analysis.
- The developed classifier accurately identified and quantified different types of disgust reactions.
Conclusions:
- The automated machine learning approach provides a reliable and efficient alternative to manual analysis of disgust reactions in mice.
- This method facilitates large-scale screening and long-term experiments requiring substantial quantification of disgust responses.
- The findings support the broader implementation of the taste reactivity test in behavioral neuroscience research.
