Combining brain images and gene maps to find what drives Alzheimer’s in tissue
Causal Representation Learning for the Spatial Analysis of Transcriptomic and Imaging Data in Tissue Contexts
Researchers will develop computer tools that link brain imaging with maps of gene activity to find biological processes that drive Alzheimer’s disease and help guide better diagnoses and treatments for people with Alzheimer’s.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Broad Institute, INC. NIH-funded |
| Lab location | 1 site (Cambridge, United States) |
| Project ID | NIH-11297096 on NIH RePORTER |
What this research studies
If you or a loved one has Alzheimer’s, this project aims to build new computer methods that connect detailed pictures of brain tissue with nearby gene activity to see how disease processes are organized in space. The team will use machine learning to learn shared patterns across imaging and gene maps, then apply causal reasoning to separate true disease drivers from misleading correlations. Techniques like image inpainting will help identify tissue structures and abnormal regions, and the methods will be tested across multiple tissue samples and datasets to look for consistent signals. The goal is to produce robust computational tools that can point researchers toward specific biological mechanisms in Alzheimer’s-affected tissue.
Who could benefit from this research
Good fit: People with Alzheimer’s (or their families) who can provide or consent to share brain tissue, imaging, or related clinical data through collaborating clinics would be most relevant to this work.
Not a fit: People without Alzheimer’s or those who cannot or do not share tissue or imaging data are unlikely to directly benefit from this computational project in the near term.
Why it matters
Potential benefit: If successful, this work could reveal biological targets and patterns that enable earlier diagnosis or new therapies for people with Alzheimer’s.
How similar studies have performed: Linking imaging and spatial transcriptomics is a recent and promising direction, but combining representation learning with causal inference to pinpoint disease drivers is largely novel and experimental.
Where this research is happening
Cambridge, United States
- Broad Institute, INC. — Cambridge, United States (Active)
Researchers
- Principal investigator: Uhler, Caroline — Broad Institute, INC.
- Study coordinator: Uhler, Caroline
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.