AI that finds which antibodies bind which targets
Machine learning for identifying antigen-antibody interactions from massive sequencing data
This project uses artificial intelligence trained on large antibody sequencing and structure data to predict which antibodies stick to which germs or abnormal proteins, helping people with immune-related conditions and those needing antibody-based treatments.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Tx Md Anderson Can Ctr NIH-funded |
| Lab location | 1 site (Houston, United States) |
| Project ID | NIH-11293440 on NIH RePORTER |
What this research studies
From my point of view as a patient, researchers will feed huge antibody sequencing datasets and protein-structure predictions into deep learning models so the computers learn patterns of antibody–antigen matching. They will combine data from high-throughput pairing methods and single-cell B cell sequencing with modern structure predictors to improve accuracy. The team will validate the models against held-out and experimentally paired data and refine them for diagnostic use and therapeutic antibody discovery. Over time this could make finding useful antibodies faster and cheaper than current lab-by-lab screening.
Who could benefit from this research
Good fit: Ideal candidates would be people with immune-related diseases or volunteers willing to donate blood or tissue for antibody sequencing and pairing studies.
Not a fit: People with conditions unrelated to the immune system or those unable to give biological samples are unlikely to see direct benefits from this project.
Why it matters
Potential benefit: If successful, this work could speed up discovery of therapeutic antibodies and improve tests that diagnose or monitor immune-related diseases.
How similar studies have performed: High-throughput antibody–antigen pairing technologies and protein-structure predictors have shown promise, but applying deep learning to reliably predict de novo interactions is still relatively new.
Where this research is happening
Houston, United States
- University of Tx Md Anderson Can Ctr — Houston, United States (Active)
Researchers
- Principal investigator: Wang, Tao — University of Tx Md Anderson Can Ctr
- Study coordinator: Wang, Tao
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.