UniProt’s AI-Enhanced Protein Knowledge for Biomedical Research
Official title: UniProt: AI-Driven Scaling of Protein Knowledge for Biomedical Research
Funded at Georgetown University · NIH-11600269 · Data updated 2026-11-12
A large-scale AI-enabled project to expand and improve a global protein knowledgebase to help researchers understand how proteins relate to human health and disease.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Georgetown University NIH-funded |
| Lab location | 1 site (Washington, United States) |
| Project start | September 18, 2014 |
| Project end | August 31, 2031 |
| Funding year | 2026 |
| Award (this year) | $2,134,460 |
| NIH project number | 3U24HG007822-13S2 |
| Project ID | NIH-11600269 on NIH RePORTER |
Who could benefit from this research
✓Could help
Not applicable to a specific patient population; the grant supports a knowledgebase used by researchers and clinicians working with protein data.
✕Less likely to help
Patients themselves are not direct participants in this project, and there is no patient-specific intervention.
What this research studies
This grant supports using artificial intelligence and large language models to help curators expand and annotate the UniProt protein knowledgebase, with a focus on human proteins, variants, pathogens, and microbiome interactions. By integrating AI tools with expert curation, the project aims to increase speed, consistency, and depth of protein annotations relevant to diseases and health. Researchers and clinicians could benefit from improved protein information that links genotypes to phenotypes and disease mechanisms. Collaboration with the scientific community will be used to crowdsource high-quality annotations and validate AI-assisted contributions. The effort includes addressing data quality, interoperability, and the needs of biomedical researchers who rely on accurate protein data.
Why it matters
Potential benefit: Improved, AI-assisted access to high-quality protein information could accelerate disease research, diagnostics, and therapeutic development.
How similar studies have gone: Prior bioinformatics knowledgebases with AI augmentation have shown improvements in curation speed and data consistency, suggesting potential gains for UniProt.
Where this research is happening
-
Georgetown University
Washington, United States Active
Researchers
- Principal investigator: Wu, Cathy H. — Georgetown University
- Study coordinator: Wu, Cathy H.
Related research
Other NIH-funded projects on the same topics.
-
UniProt uses AI to advance protein knowledge for biomedical research
A large NIH grant uses artificial intelligence to expand and improve a global protein knowledgebase to help understand human health and disease.
-
Multi-omics tools to predict late radiation organ injuries (DEARE-Watch)
Aims to create blood and urine tests that use multiple omics signals to forecast long-term damage to lungs and kidneys after acute radiation exposure, helping patients get early care.
-
National Capital Area NCORP: Expanding Access to Cancer Prevention, Screening, and Care in Underserved Washington DC Area
A community-focused program in the DC area partners with local hospitals to improve cancer prevention, screening, and access to advanced care for underserved populations.
-
Exercise and brain health in older adults with kidney disease
A study to see if a structured exercise program can slow cognitive decline in older adults with chronic kidney disease who are at risk for dementia.
-
AI tools to organize and predict immune-related side effects in cancer therapy
A concrete plan to build AI-powered tools that automatically pull together information about immune-related side effects from cancer immunotherapy to help doctors manage treatment.
-
Understanding how tiny blood vessels behave around dental implants
A study at Georgetown University looks at why blood vessels near dental implants leak and become inflamed, with the goal of spotting problems early in patients who have implants.
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.