Using advanced AI to find Alzheimer's genes and improve treatments
Ultrascale Machine Learning to Empower Discovery in Alzheimer’s Disease Biobanks
['FUNDING_U01'] · UNIVERSITY OF SOUTHERN CALIFORNIA · NIH-11200168
This project uses powerful AI to analyze large genomic, imaging, and clinical datasets to find Alzheimer's-related genetic signals and help tailor future treatments for people with Alzheimer's and related dementias.
Quick facts
| Phase | ['FUNDING_U01'] |
|---|---|
| Study type | Nih_funding |
| Sex | All |
| Sponsor | UNIVERSITY OF SOUTHERN CALIFORNIA (nih funded) |
| Locations | 1 site (Los Angeles, UNITED STATES) |
| Trial ID | NIH-11200168 on ClinicalTrials.gov |
What this research studies
You can expect advanced AI to analyze whole genomes, brain scans, and detailed clinical records from large Alzheimer's biobanks to discover genetic markers and disease subtypes. The team will adapt large-language-model techniques to DNA sequences and compare those results with other AI tools to improve prediction of symptom onset and disease progression. They plan to use the identified subtypes to design smarter clinical trials and to search for existing drugs that might work for specific patient groups. Much of the work analyzes real patient genomes and records from large consortia rather than testing treatments directly.
Who could benefit from this research
Good fit: People with Alzheimer's disease or related dementias, and individuals at risk who can provide or already have genetic, imaging, or clinical data, would be the most relevant participants or data-contributors.
Not a fit: People without genomic or imaging data, those whose cognitive symptoms are due to non-AD causes, or anyone seeking an immediate treatment are unlikely to benefit directly from this project right away.
Why it matters
Potential benefit: If successful, this work could lead to more accurate prediction of disease course, better-targeted clinical trials, and new or repurposed therapies matched to patient subtypes.
How similar studies have performed: Previous AI and genetic studies have shown promise in improving Alzheimer's prediction and subtyping, but applying large-language-model methods to whole genomes and linking that to drug repositioning is a newer and less-tested approach.
Where this research is happening
Los Angeles, UNITED STATES
- UNIVERSITY OF SOUTHERN CALIFORNIA — Los Angeles, UNITED STATES (ACTIVE)
Researchers
- Principal investigator: THOMPSON, PAUL M — UNIVERSITY OF SOUTHERN CALIFORNIA
- Study coordinator: THOMPSON, PAUL M
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.