Using AI to find why genes are turned on or off in disease
Deep learning for understanding gene regulation in diseases via 'omics' integration
Advanced AI will combine DNA, chemical tags, 3D genome shape, and genetic variants to reveal how genes behave differently in people with disease.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Brown University NIH-funded |
| Lab location | 1 site (Providence, United States) |
| Project ID | NIH-11189805 on NIH RePORTER |
What this research studies
This project trains deep learning models to join multiple types of molecular data so computers can learn patterns that control gene activity. The team will build graph-based neural networks that represent how DNA folds in 3D and how distant regions interact. They will apply interpretation tools and a novel Bayesian explanation method to pinpoint which features most influence gene expression, and compare those signals between healthy and disease cell lines. The work will also extend to single-cell data to capture differences between individual cells.
Who could benefit from this research
Good fit: People with diseases linked to gene regulation problems, or healthy volunteers willing to provide blood or tissue samples, would be most relevant for any sample-donation or follow-up clinical efforts.
Not a fit: Patients seeking immediate changes to their medical care are unlikely to benefit directly, since this is computational and hypothesis-generating laboratory research.
Why it matters
Potential benefit: If successful, this work could identify biological signals that explain gene misregulation and point to new diagnostic markers or targets for future treatments.
How similar studies have performed: Related AI approaches have shown promise at finding regulatory signals in genomic data, but the proposed Bayesian interpretation of graph-based models is a novel and largely untested addition.
Where this research is happening
Providence, United States
- Brown University — Providence, United States (Active)
Researchers
- Principal investigator: Singh, Ritambhara — Brown University
- Study coordinator: Singh, Ritambhara
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.