Using advanced computer models to understand genes and personalize medicine
Official title: Advanced machine learning models to integrate multi-modal biomedical datasets for gene regulation and precision medicine
Funded at University of North Texas · NIH-11090901 · Data updated 2026-11-12
This work creates new computer tools to combine different types of health information, like genetic data and medical records, to better understand diseases and find new treatments for patients.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of North Texas NIH-funded |
| Lab location | 1 site (Denton, United States) |
| Project start | August 1, 2019 |
| Project end | June 30, 2030 |
| Funding year | 2025 |
| Award (this year) | $539,986 |
| NIH project number | 2R35GM133657-07 |
| Project ID | NIH-11090901 on NIH RePORTER |
Who could benefit from this research
✓Could help
This foundational work does not directly involve patient participation, but its future applications could benefit patients with various diseases by improving diagnosis and treatment strategies.
✕Less likely to help
Patients seeking immediate direct clinical intervention or participation in a treatment trial would not find direct benefit from this computational tool development.
What this research studies
Our team is building advanced computer programs that can bring together many different kinds of health data, such as information about your genes, how your body's cells work, and your electronic health records. These programs are designed to handle large amounts of complex information, even when some data is missing or noisy. By developing these smart computer models, we aim to uncover new insights into how diseases develop and how they might be treated. This approach helps us predict health outcomes and discover existing medicines that could be used for new purposes.
Why it matters
Potential benefit: If successful, this work could lead to more personalized treatment plans for patients and help identify new uses for existing medications, potentially improving health outcomes.
How similar studies have gone: While the integration of multi-modal biomedical datasets is an active area of research, this grant focuses on developing novel, generalizable, and interpretable machine learning solutions to address specific challenges in this field.
Where this research is happening
-
University of North Texas
Denton, United States Active
Researchers
- Principal investigator: Bozdag, Serdar — University of North Texas
- Study coordinator: Bozdag, Serdar
Related research
Other NIH-funded projects on the same topics.
-
Cataracts and Work Exposures in Denmark
A large Danish study will look at whether job-related exposures, both chemical and non-chemical, are linked to developing cataracts.
-
New approach to find noninvasive brain networks that predict epilepsy after brain injury
A study aims to identify noninvasive brain biomarkers that can forecast epileptogenesis after brain injury by linking MRI network patterns with EEG signals.
-
Off-the-shelf ADC-NK cell therapy platform for cancer and immune diseases
A universal, ready-to-use natural killer cell therapy armed with antibody-drug conjugates is being developed to target cancers and other diseases.
-
New and better ways to measure kids' exposure to air pollution and traffic
This project looks at how traffic-related air pollution and green space around homes may affect cancer risk in children and uses advanced exposure measurements to better understand these links.
-
Can a single model work for high-resolution 3D genome structure using generalizable methods
A grantfunds researchers to create high-resolution 3D genome models that can work across different cell types using advanced algorithms and machine learning.
-
How tissue stiffness and stretching affect nanoparticle delivery in cancer and other diseases
This grant studies how the physical properties of tissues, like stiffness and stretch, influence how nanoparticles are taken up by cancer-related cells to improve future therapies.
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.