Cell Reports (Nov 2024)
Machine learning reveals prominent spontaneous behavioral changes and treatment efficacy in humanized and transgenic Alzheimer's disease models
- Stephanie R. Miller,
- Kevin Luxem,
- Kelli Lauderdale,
- Pranav Nambiar,
- Patrick S. Honma,
- Katie K. Ly,
- Shreya Bangera,
- Mary Bullock,
- Jia Shin,
- Nick Kaliss,
- Yuechen Qiu,
- Catherine Cai,
- Kevin Shen,
- K. Dakota Mallen,
- Zhaoqi Yan,
- Andrew S. Mendiola,
- Takashi Saito,
- Takaomi C. Saido,
- Alexander R. Pico,
- Reuben Thomas,
- Erik D. Roberson,
- Katerina Akassoglou,
- Pavol Bauer,
- Stefan Remy,
- Jorge J. Palop
Affiliations
- Stephanie R. Miller
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA; Department of Neurology, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA 94158, USA; Corresponding author
- Kevin Luxem
- German Center for Neurodegenerative Diseases (DZNE), 39118 Bonn and Magdeburg, Germany; Department of Cellular Neuroscience, Leibniz Institute for Neurobiology, 39118 Magdeburg, Germany; Center for Behavioral Brain Sciences (CBBS), 39106 Magdeburg, Germany
- Kelli Lauderdale
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA; Department of Neurology, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA 94158, USA
- Pranav Nambiar
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA
- Patrick S. Honma
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA; Department of Neurology, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA 94158, USA
- Katie K. Ly
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA; Department of Neurology, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA 94158, USA
- Shreya Bangera
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA; Department of Neurology, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA 94158, USA
- Mary Bullock
- Center for Neurodegeneration and Experimental Therapeutics, Alzheimer’s Disease Center, Department of Neurology, University of Alabama at Birmingham, Birmingham, AL 35233, USA
- Jia Shin
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA; Department of Neurology, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA 94158, USA
- Nick Kaliss
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA
- Yuechen Qiu
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA
- Catherine Cai
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA
- Kevin Shen
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA
- K. Dakota Mallen
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA
- Zhaoqi Yan
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA; Center for Neurovascular Brain Immunology at Gladstone and UCSF, San Francisco, CA 94158, USA
- Andrew S. Mendiola
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA; Center for Neurovascular Brain Immunology at Gladstone and UCSF, San Francisco, CA 94158, USA
- Takashi Saito
- Department of Neurocognitive Science, Nagoya City University Graduate School of Medical Sciences, Nagoya 467-8601, Japan
- Takaomi C. Saido
- Laboratory for Proteolytic Neuroscience, RIKEN Center for Brain Science, Wako-shi 351-0198, Japan
- Alexander R. Pico
- Gladstone Institute of Data Science and Biotechnology, San Francisco, CA 94158, USA
- Reuben Thomas
- Gladstone Institute of Data Science and Biotechnology, San Francisco, CA 94158, USA
- Erik D. Roberson
- Center for Neurodegeneration and Experimental Therapeutics, Alzheimer’s Disease Center, Department of Neurology, University of Alabama at Birmingham, Birmingham, AL 35233, USA
- Katerina Akassoglou
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA; Department of Neurology, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA 94158, USA; Center for Neurovascular Brain Immunology at Gladstone and UCSF, San Francisco, CA 94158, USA
- Pavol Bauer
- German Center for Neurodegenerative Diseases (DZNE), 39118 Bonn and Magdeburg, Germany; Department of Cellular Neuroscience, Leibniz Institute for Neurobiology, 39118 Magdeburg, Germany; Center for Behavioral Brain Sciences (CBBS), 39106 Magdeburg, Germany
- Stefan Remy
- German Center for Neurodegenerative Diseases (DZNE), 39118 Bonn and Magdeburg, Germany; Department of Cellular Neuroscience, Leibniz Institute for Neurobiology, 39118 Magdeburg, Germany; Center for Behavioral Brain Sciences (CBBS), 39106 Magdeburg, Germany; German Center for Mental Health (DZPG), 39118 Magdeburg, Germany
- Jorge J. Palop
- Gladstone Institute of Neurological Disease, San Francisco, CA 94158, USA; Department of Neurology, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA 94158, USA; Corresponding author
- Journal volume & issue
-
Vol. 43,
no. 11
p. 114870
Abstract
Summary: Computer-vision and machine-learning (ML) approaches are being developed to provide scalable, unbiased, and sensitive methods to assess mouse behavior. Here, we used the ML-based variational animal motion embedding (VAME) segmentation platform to assess spontaneous behavior in humanized App knockin and transgenic APP models of Alzheimer’s disease (AD) and to test the role of AD-related neuroinflammation in these behavioral manifestations. We found marked alterations in spontaneous behavior in AppNL-G-F and 5xFAD mice, including age-dependent changes in motif utilization, disorganized behavioral sequences, increased transitions, and randomness. Notably, blocking fibrinogen-microglia interactions in 5xFAD-Fggγ390–396A mice largely prevented spontaneous behavioral alterations, indicating a key role for neuroinflammation. Thus, AD-related spontaneous behavioral alterations are prominent in knockin and transgenic models and sensitive to therapeutic interventions. VAME outcomes had higher specificity and sensitivity than conventional behavioral outcomes. We conclude that spontaneous behavior effectively captures age- and sex-dependent disease manifestations and treatment efficacy in AD models.
