JAX Animal Behavior System (JABS), a genetics-informed, end-to-end advanced behavioral phenotyping platform for the...

Area of Science:

• Neuroscience
• Behavioral Genetics
• Computer Vision

Background:

• Automated detection of complex animal behavior is crucial for high-throughput studies but faces adoption challenges in non-computational labs.
• Existing methods require integrated hardware and software solutions for seamless adoption in behavioral neurogenetics.
• Previous work focused on specific behaviors like grooming, posture, and gait in open field arenas.

Purpose of the Study:

• To introduce the JAX Animal Behavior System (JABS), an integrated platform for rodent phenotyping.
• To facilitate automated behavior annotation, classification, sharing, and genetic analysis.
• To reduce the barrier to entry for advanced behavior analysis in neuroscience and genetics.

Main Methods:

• Developed the JAX Animal Behavior System (JABS) with modules for data acquisition (JABS-DA), active learning (JABS-AL), and analysis/integration (JABS-AI).
• Introduced 'ethograph', a novel graph-based framework for efficient classifier comparison.
• Utilized machine learning for behavior annotation and classification, enabling classifier sharing via a web application.

Main Results:

• JABS provides uniform data collection, real-time monitoring, and video data management.
• The platform supports classifier training, validation, and sharing, significantly reducing annotation effort.
• Publicly released three curated datasets (168 mouse strains) with associated genetic analyses (heritability, genetic correlation).

Conclusions:

• JABS is an open-source ecosystem that democratizes advanced behavior analysis for the neuroscience and genetics communities.
• The platform enables genetics to guide behavior classifier selection, fostering cross-disciplinary research.
• JABS lowers the barrier to entry for complex animal behavior analysis and high-throughput studies.