A new AI tool from University of Florida researchers generates detailed 3D mouse brain maps, offering a zoomable view of energy-producing molecules. Backed by NIH funding, this AI-driven tool brings scientists closer to uncovering how metabolism impacts Alzheimer’s and neurodegenerative disorders.
The team of researchers, led by Ramon Sun, developed the cutting-edge MetaVision3D tool with the power of UF’s HiPerGator supercomputer. To demonstrate its capabilities, they created a 3D interactive atlas of the brain in healthy mice and models of Alzheimer’s and Pompe disease. In support of research on metabolism and the brain, Sun’s lab has released its database and web server for public use.
“Using our methodology, we can map thousands of molecules in the brain and precisely where they are located inside each brain region. It is unprecedented,” stated Sun, director of the Center for Advanced Spatial Biomolecule Research and associate director for innovation of UF’s McKnight Brain Institute. “We couldn’t have done it without NIH funding. This funding fuels our efforts to uncover metabolic drivers of Alzheimer’s and pave the way for new interventions to prevent and treat this devastating disease.”
Users can navigate the 3D reconstruction to explore tissue sections in detail, revealing complexities hidden in traditional 2D maps and offering new insights into cellular metabolism and disease mechanisms influenced by diet, exercise, and genetics.
“On Google Earth, I can zoom in on a city and see what a house looks like, what the street looks like, what cars are there. That’s the level of resolution we provided for the mouse brain in this three-dimensional space, and how they change during diseases,” explained Sun. “You can explore and examine molecules that influence thinking, memory, and brain health, including those involved in neurodegenerative diseases. You can map all the different molecules and how they are organized and distributed in fine brain structures.”
To move from 2D to 3D, a leap Sun likened to transitioning from a flip phone to a smartphone, his lab scanned 79 brain sections layer by layer using advanced imaging to identify crucial molecules like fats and carbohydrates. “Then we used AI to align those images and stack them together to reconstruct the whole brain metabolome,” stated Xin Ma, the first author of the paper. The metabolome is a complex system of molecules responsible for fueling brain activity.
Next, in collaboration with Sara Burke, Ph.D., director of UF’s Center for Cognitive Aging and Memory, the team mapped brain anatomy to molecular data and applied mathematical methods to ensure an accuracy rate of 95–99%. In the future, researchers could combine this mapping tool with MRI imaging and genetic analysis to develop targeted treatments that focus on specific brain areas, unlike current therapies that may impact healthy regions as well.
“For disease prevention and treatment, we have opened a new angle for biologists to study,” stated Chen, a co-corresponding author of the paper and an associate professor at UF.
Publication Details
Ma, X., Shedlock, C.J., Medina, T. et al. AI-driven framework to map the brain metabolome in three dimensions. Nat Metab (2025). https://doi.org/10.1038/s42255-025-01242-9
The team of researchers, led by Ramon Sun, developed the cutting-edge MetaVision3D tool with the power of UF’s HiPerGator supercomputer. To demonstrate its capabilities, they created a 3D interactive atlas of the brain in healthy mice and models of Alzheimer’s and Pompe disease. In support of research on metabolism and the brain, Sun’s lab has released its database and web server for public use.
“Using our methodology, we can map thousands of molecules in the brain and precisely where they are located inside each brain region. It is unprecedented,” stated Sun, director of the Center for Advanced Spatial Biomolecule Research and associate director for innovation of UF’s McKnight Brain Institute. “We couldn’t have done it without NIH funding. This funding fuels our efforts to uncover metabolic drivers of Alzheimer’s and pave the way for new interventions to prevent and treat this devastating disease.”
Users can navigate the 3D reconstruction to explore tissue sections in detail, revealing complexities hidden in traditional 2D maps and offering new insights into cellular metabolism and disease mechanisms influenced by diet, exercise, and genetics.
“On Google Earth, I can zoom in on a city and see what a house looks like, what the street looks like, what cars are there. That’s the level of resolution we provided for the mouse brain in this three-dimensional space, and how they change during diseases,” explained Sun. “You can explore and examine molecules that influence thinking, memory, and brain health, including those involved in neurodegenerative diseases. You can map all the different molecules and how they are organized and distributed in fine brain structures.”
To move from 2D to 3D, a leap Sun likened to transitioning from a flip phone to a smartphone, his lab scanned 79 brain sections layer by layer using advanced imaging to identify crucial molecules like fats and carbohydrates. “Then we used AI to align those images and stack them together to reconstruct the whole brain metabolome,” stated Xin Ma, the first author of the paper. The metabolome is a complex system of molecules responsible for fueling brain activity.
Next, in collaboration with Sara Burke, Ph.D., director of UF’s Center for Cognitive Aging and Memory, the team mapped brain anatomy to molecular data and applied mathematical methods to ensure an accuracy rate of 95–99%. In the future, researchers could combine this mapping tool with MRI imaging and genetic analysis to develop targeted treatments that focus on specific brain areas, unlike current therapies that may impact healthy regions as well.
“For disease prevention and treatment, we have opened a new angle for biologists to study,” stated Chen, a co-corresponding author of the paper and an associate professor at UF.
Publication Details
Ma, X., Shedlock, C.J., Medina, T. et al. AI-driven framework to map the brain metabolome in three dimensions. Nat Metab (2025). https://doi.org/10.1038/s42255-025-01242-9