Hidden Behavioral Fingerprints in Epilepsy

Abstract: Epilepsy is a major disorder affecting millions of people. While modern electrophysiological and imaging approaches provide high resolution access to the multi-scale brain circuit malfunctions in epilepsy, our understanding of how behavior changes with epilepsy has remained rudimentary. As a result, screening for new therapies for children and adults with devastating epilepsies still relies on the inherently subjective, semi-quantitative assessment of a handful of pre-selected behavioral signs of epilepsy in animal models. Here we used machine learning-assisted 3D video analysis to reveal hidden behavioral phenotypes in mice with acquired and genetic epilepsies, and tracked their alterations during post-insult epileptogenesis and in response to anti-epileptic drugs. These results show the persistent reconfiguration of behavioral fingerprint in epilepsy and indicate that they can be employed for rapid, automated anti-epileptic drug testing at scale.

------

This repository contains code from the manuscript "Hidden Behavioral Fingerprints in Epilepsy" (2023) to analyze behavioral fingerprints obtained from Motion Sequencing (MoSeq). For further details about the MoSeq pipeline, please refer to https://dattalab.github.io/moseq2-website/index.html. The code includes examples of analyses performed in this study. The example.py file can be run using e.g. a dataset of mice injected with anti-epileptic drugs (AEDs). For further details about these analyses and data, please refer to the "Methods" section in the manuscript.