Predicting which TCRs recognize cancer peptides using advanced AI models
Official title: Optimization of structure-guided models of peptide presentation and T-cell receptor specificity
Funded at Sloan-Kettering Inst Can Research · NIH-11434375 · Data updated 2026-11-12
A patient-focused grant that aims to improve how we predict which T cells recognize cancer-related peptides, using advanced AI to guide personalized immunotherapies.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Sloan-Kettering Inst Can Research NIH-funded |
| Lab location | 1 site (New York, United States) |
| Project start | August 11, 2026 |
| Project end | July 31, 2030 |
| Funding year | 2026 |
| Award (this year) | $731,937 |
| NIH project number | 1R01CA318448-01 |
| Project ID | NIH-11434375 on NIH RePORTER |
Who could benefit from this research
✓Could help
Patients with cancers where neoantigen-targeted immunotherapies are being explored, especially those whose tumors express predictable peptide-MHC targets.
✕Less likely to help
Some patients may not benefit if their tumor antigens or immune environment are not compatible with the predicted targets.
What this research studies
This project develops an AI-powered approach to forecast which T-cell receptors will recognize specific peptide-MHC targets, a key step in making precision immunotherapies more reliable. Using structure-aware AI tools, the team creates ensembles of predicted TCR:pMHC structures to extract meaningful biophysical signals that help distinguish similar epitopes, even when only a single amino acid changes. The work aims to generalize across human and mouse data to better predict neoantigen responses, with the goal of guiding future treatments tailored to each patient’s tumor. The research builds on high-throughput modeling to reduce false positives and improve the selection of actionable targets for immunotherapies.
Why it matters
Potential benefit: If successful, this could lead to more accurate tailoring of personalized cancer immunotherapies by predicting which T cells will best target a patient’s tumor.
How similar studies have gone: Early AI-based methods struggled with generalization, but this project builds on prior structure-guided modeling that showed promise in cross-species generalization and peptide discrimination.
Where this research is happening
-
Sloan-Kettering Inst Can Research
New York, United States Active
Researchers
- Principal investigator: Morris, Quaid — Sloan-Kettering Inst Can Research
- Study coordinator: Morris, Quaid
Related research
Other NIH-funded projects on the same topics.
-
Understand how skeletal muscle nuclei specialize and arrange themselves for proper muscle function
A study to uncover how the hundreds of nuclei in skeletal muscle fibers acquire different roles and positions to keep muscles strong and healthy.
-
Genomic profiling and outcomes of cancers in World Trade Center-exposed survivors and responders
This project looks at the genetic makeup and real-world cancer outcomes in people exposed to the World Trade Center disaster to understand how their cancers behave and respond to treatments.
-
Meaning-Centered Psychotherapy for Mexican Patients with Advanced Cancer
A cancer center in Mexico will test a culturally adapted therapy to help Mexican patients with advanced cancer find meaning, peace, and purpose at the end of life.
-
High-specificity genome-scale cell-surface proteomics to find tumor targets
A cancer research project is trying to map all the proteins on the surface of ultra-rare sarcoma cells to find safe, targeted ways to treat them.
-
Priorities for testing and choosing combination therapies in rhabdoid tumors to guide clinical trials
A coordinated, multi-site effort will rigorously test promising drug combinations in rhabdoid tumors to identify the most promising options for future patient trials.
-
ecDNA in Cancer: Understanding and targeting circular DNA that drives tumor growth
A cancer-focused project to understand how extrachromosomal DNA helps tumors grow and resist treatment, and to develop new ways to target these mechanisms.
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.