General prediction of T cell receptor antigen specificity from sequence using AlphaFold 3
4 affiliations
- 1The Translational Genomics Research Institute (TGen), Phoenix, AZ, USA.
- 2City of Hope Comprehensive Cancer Center, Duarte, CA, USA.
- 3The Translational Genomics Research Institute (TGen), Flagstaff, AZ, USA.
- 4Charles Perkins Centre, The University of Sydney, Camperdown, NSW 2006, Australia.
Abstract
The major histocompatibility complex (MHC):peptide:T cell receptor (TCR) complex is the most diverse trimolecular interface known in nature and a key trigger for adaptive immunity. TCRs are now routinely sequenced at scale; however, decoding their specificity for antigens remains a bottleneck. While in silico approaches have advanced considerably, none enables prediction against "unseen" epitopes, limiting their applicability to a tiny fraction of cases. Here, we show that AlphaFold 3 (AF3) predicts the structures of MHC:peptide:TCR triads with unprecedented accuracy. By applying AF3 to >9000 TCRs mapped to >1000 distinct epitopes restricted by >70 MHC class I/II alleles, we identify features that distinguish cognate triads from controls. The resulting model achieves median areas under the curve of 0.81 to 0.92 on validation triads unseen by AF3 or during feature selection. Our results reveal that generalized prediction of TCR specificity from sequence is possible, with the potential to greatly accelerate the decoding of immune responses.
Related
- Limitations of general protein language models and public TCRpMHC data in training specificity prediction models
- OmniTCR: a foundation model unifying T cell receptor recognition prediction and conditional sequence generation
- AlphaFold 3 Prediction Accuracy and Reliability across RNA Structures and Protein-RNA Interfaces
- Five decades of human H1N1 evolution reveal conserved glycan receptor specificity
- From neuropeptide and receptor annotation to ligand-receptor pairing: a sequence- and structure-based framework for mapping the neuropeptide-receptor interactome in Gryllus bimaculatus
BibTeX
@article{woods2026general,
title = {{General prediction of T cell receptor antigen specificity from sequence using AlphaFold 3}},
author = {Lawson J. Woods and Brandon Neff and Kamel Lahouel and Antoine Goursaud and Mete Mulazimoglu and Kameron Bates and Cristian Tomasetti and John A. Altin},
journal = {Science Advances},
year = {2026},
month = oct,
doi = {10.1126/sciadv.aef5674},
url = {https://www.science.org/doi/abs/10.1126/sciadv.aef5674},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - General prediction of T cell receptor antigen specificity from sequence using AlphaFold 3
AU - Lawson J. Woods
AU - Brandon Neff
AU - Kamel Lahouel
AU - Antoine Goursaud
AU - Mete Mulazimoglu
AU - Kameron Bates
AU - Cristian Tomasetti
AU - John A. Altin
PY - 2026
DA - 2026/10/30
JO - Science Advances
DO - 10.1126/sciadv.aef5674
UR - https://www.science.org/doi/abs/10.1126/sciadv.aef5674
AB - The major histocompatibility complex (MHC):peptide:T cell receptor (TCR) complex is the most diverse trimolecular interface known in nature and a key trigger for adaptive immunity. TCRs are now routinely sequenced at scale; however, decoding their specificity for antigens remains a bottleneck. While in silico approaches have advanced considerably, none enables prediction against "unseen" epitopes, limiting their applicability to a tiny fraction of cases. Here, we show that AlphaFold 3 (AF3) predicts the structures of MHC:peptide:TCR triads with unprecedented accuracy. By applying AF3 to >9000 TCRs mapped to >1000 distinct epitopes restricted by >70 MHC class I/II alleles, we identify features that distinguish cognate triads from controls. The resulting model achieves median areas under the curve of 0.81 to 0.92 on validation triads unseen by AF3 or during feature selection. Our results reveal that generalized prediction of TCR specificity from sequence is possible, with the potential to greatly accelerate the decoding of immune responses.
SN - 2375-2548
ER -