Deep Learning Applications for Huntington's Disease
Research Mentor(s)
Kameron Harris
Description
Huntington’s Disease (HD) is a monogenic neurodegenerative disorder which leads to progressive loss of cognitive function, motor deficits, and psychiatric disturbances. HD is always fatal and no treatments currently exist to slow or modify the disease course. Traditional methods of collecting data regarding animal movement and behavior are labor-intensive and inefficient; the ability to track and quantify movement in HD mouse models has the potential to provide insight into disease mechanism, progression, and treatment. We use DeepLabCut, a free and open-source markerless pose estimation software, to annotate animal movements with minimal manual labor from the researcher. This has generated an extensive dataset of HD and wildtype mouse movements. By analyzing these data, we aim to quantify behavioral differences between HD and wildtype mice such as variations in velocity, thigmotaxis, and grooming behaviors. Discovering differences in HD mouse behavior provides insight into disease pathogenesis and may identify subtle changes that empower future preclinical trials.
Document Type
Event
Start Date
May 2022
End Date
May 2022
Location
Carver Gym (Bellingham, Wash.)
Department
CSE - Computer Science
Genre/Form
student projects; posters
Type
Image
Rights
Copying of this document in whole or in part is allowable only for scholarly purposes. It is understood, however, that any copying or publication of this document for commercial purposes, or for financial gain, shall not be allowed without the author’s written permission.
Language
English
Format
application/pdf
Deep Learning Applications for Huntington's Disease
Carver Gym (Bellingham, Wash.)
Huntington’s Disease (HD) is a monogenic neurodegenerative disorder which leads to progressive loss of cognitive function, motor deficits, and psychiatric disturbances. HD is always fatal and no treatments currently exist to slow or modify the disease course. Traditional methods of collecting data regarding animal movement and behavior are labor-intensive and inefficient; the ability to track and quantify movement in HD mouse models has the potential to provide insight into disease mechanism, progression, and treatment. We use DeepLabCut, a free and open-source markerless pose estimation software, to annotate animal movements with minimal manual labor from the researcher. This has generated an extensive dataset of HD and wildtype mouse movements. By analyzing these data, we aim to quantify behavioral differences between HD and wildtype mice such as variations in velocity, thigmotaxis, and grooming behaviors. Discovering differences in HD mouse behavior provides insight into disease pathogenesis and may identify subtle changes that empower future preclinical trials.