EUVIMEDEUVIMED entdecken
Open Access

General prediction of T cell receptor antigen specificity from sequence using AlphaFold 3

Lawson J Woods iD, Brandon Neff, Kamel Lahouel iD, Antoine Goursaud, Mete Mulazimoglu iD, Kameron Bates iD, Cristian Tomasetti iD, John A Altin iD

Science Advances · 30.10.2026 · 12 (44)

DOI: 10.1126/sciadv.aef5674 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 30.10.2026. Verfasst von Lawson J Woods und 7 weiteren Autor:innen. Beteiligte Einrichtung: The Translational Genomics Research Institute (TGen), Phoenix, AZ, USA. Hauptthemen laut MEDLINE: Receptors, Antigen, T-Cell, T-Cell Antigen Receptor Specificity. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH HHS, NIH.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Receptors, Antigen, T-CellT-Cell Antigen Receptor SpecificityHumansImmunoinformaticsPrediction AlgorithmsAmino Acid SequenceAlgorithmsEpitopes, T-LymphocytePeptides

Substanzen

Receptors, Antigen, T-CellEpitopes, T-LymphocytePeptides

Autor:innen und Institutionen

  • The Translational Genomics Research Institute (TGen), Phoenix, AZ, USA.
  • City of Hope Comprehensive Cancer Center, Duarte, CA, USA.
  • The Translational Genomics Research Institute (TGen), Flagstaff, AZ, USA.
  • Charles Perkins Centre, The University of Sydney, Camperdown, NSW 2006, Australia.

ORCID-Profile: Lawson J Woods, Kamel Lahouel, Mete Mulazimoglu, Kameron Bates, Cristian Tomasetti, John A Altin

Förderung

  • NIH HHS
  • NIH

Zitieren

APA

Woods, L. J., Neff, B., Lahouel, K., Goursaud, A., Mulazimoglu, M., Bates, K., Tomasetti, C., & Altin, J. A. (2026). General prediction of T cell receptor antigen specificity from sequence using AlphaFold 3. Science Advances, 12(44). https://doi.org/10.1126/sciadv.aef5674

Vancouver

Woods LJ, Neff B, Lahouel K, Goursaud A, Mulazimoglu M, Bates K, et al. General prediction of T cell receptor antigen specificity from sequence using AlphaFold 3. Science Advances. 2026;12(44). doi:10.1126/sciadv.aef5674

BibTeX
@article{Woods2026,
  author = {Woods, Lawson J and Neff, Brandon and Lahouel, Kamel and Goursaud, Antoine and Mulazimoglu, Mete and Bates, Kameron and Tomasetti, Cristian and Altin, John A},
  title = {General prediction of T cell receptor antigen specificity from sequence using AlphaFold 3},
  journal = {Science Advances},
  year = {2026},
  volume = {12},
  number = {44},
  doi = {10.1126/sciadv.aef5674}
}
Kostenlos starten →