Explainable AI to find gene and epigenetic changes in single brain cells linked to Alzheimer's
Interpretable Deep Learning Methods to Investigate Genetics and Epigenetics of Alzheimer's Disease at a Single-Cell Resolution
This project uses interpretable deep learning on single-cell brain data to find gene and epigenetic changes that may help explain Alzheimer's disease in older adults.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of California-Irvine NIH-funded |
| Lab location | 1 site (Irvine, United States) |
| Project ID | NIH-11135570 on NIH RePORTER |
What this research studies
The research team will build explainable deep learning models that combine multiple types of single-cell genomic information — such as gene activity, epigenetic marks, and chromatin structure — from brain tissue. They plan to create person- and cell-type-specific 'regulomes' that describe how genes are regulated in different brain cell types in people with and without dementia. The methods will explicitly handle missing data and complex feature interactions so results are scalable and robust across many samples. The investigators will release software tools so other researchers can apply these methods to additional Alzheimer's datasets.
Who could benefit from this research
Good fit: People with Alzheimer's disease or related dementias, or older adults willing to donate brain tissue or biospecimens for single-cell genomic studies, would be the most relevant candidates.
Not a fit: Patients seeking immediate changes in clinical care or those without neurodegenerative disease are unlikely to receive direct personal benefit from this computational research.
Why it matters
Potential benefit: If successful, this work could reveal specific genes, cell types, and epigenetic changes to guide new diagnostic markers or future therapies for Alzheimer's.
How similar studies have performed: Previous single-cell and machine-learning studies have uncovered Alzheimer-associated cell types and genes, but applying interpretable deep learning to multi-modal single-cell Alzheimer data at this scale is relatively new.
Where this research is happening
Irvine, United States
- University of California-Irvine — Irvine, United States (Active)
Researchers
- Principal investigator: Zhang, Jing — University of California-Irvine
- Study coordinator: Zhang, Jing
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.