EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

nuTCRacker: Predicting the Recognition of HLA‐I–Peptide Complexes by αβTCRs for Unseen Peptides

Justin Barton, Trupti Gore, Meghna Phanichkrivalkosil, Adrian Shepherd, Michele Mishto iD

European Journal of Immunology · 2025-07 · 55 (7)

DOI: 10.1002/eji.202451607 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Immunology, online erschienen am 09.07.2025. Verfasst von Justin Barton und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Natural Sciences and Institute of Structural and Molecular Biology, Birkbeck, University of London, London, UK. Hauptthemen laut MEDLINE: Histocompatibility Antigens Class I, Receptors, Antigen, T-Cell, alpha-beta, Peptides, Deep Learning. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Cancer Research UK, CRUK City of London Centre (CoL) Award, Blood Cancer UK.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The ability to predict which antigenic peptide(s) the αβTCR of a given CD8 + T‐cell clone can recognise would represent a quantum leap in the understanding of T‐cell repertoire selection and development of targeted cell‐mediated immunotherapies. Current methods fail to make accurate predictions for antigenic peptides not present in the training dataset. Here, we propose a novel deep learning method called nuTCRacker that makes accurate predictions for a subset of unseen peptides, with an AUC > 0.7 for around a third of peptides evaluated using a large dataset compiled from curated public resources. An additional evaluation was undertaken using a small cellula‐validated dataset of αβTCR peptides associated with cancer. Our analysis suggests that it is possible to make useful predictions for an unseen peptide provided the training dataset contains: many samples with the same HLA class I molecule as that bound to the peptide; at least one peptide that is similar to the target peptide; and a small number of αβTCRs that are similar to those bound to the unseen peptide of interest.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Histocompatibility Antigens Class IReceptors, Antigen, T-Cell, alpha-betaPeptidesDeep LearningCD8-Positive T-LymphocytesHumansNeoplasms

Stichwörter der Autor:innen

MHCTCRantigen presentation/processingbioinformatics

Substanzen

Histocompatibility Antigens Class IReceptors, Antigen, T-Cell, alpha-betaPeptides

Autor:innen und Institutionen

  • School of Natural Sciences and Institute of Structural and Molecular Biology, Birkbeck, University of London, London, UK.
  • Centre for Inflammation Biology and Cancer Immunology & Peter Gorer Department of Immunobiology, King's College London, London, UK.
  • Francis Crick Institute, London, UK.

ORCID-Profile: Michele Mishto

Förderung

  • Cancer Research UK
  • CRUK City of London Centre (CoL) Award
  • Blood Cancer UK
  • Oracle for Research Cloud
  • MRC DTP-funded studentship
  • Biotechnology and Biological Sciences Research Council UKRI-funded studentship

Zitieren

APA

Barton, J., Gore, T., Phanichkrivalkosil, M., Shepherd, A., & Mishto, M. (2025). nuTCRacker: Predicting the Recognition of HLA‐I–Peptide Complexes by αβTCRs for Unseen Peptides. European Journal of Immunology, 55(7). https://doi.org/10.1002/eji.202451607

Vancouver

Barton J, Gore T, Phanichkrivalkosil M, Shepherd A, Mishto M. nuTCRacker: Predicting the Recognition of HLA‐I–Peptide Complexes by αβTCRs for Unseen Peptides. European Journal of Immunology. 2025;55(7). doi:10.1002/eji.202451607

BibTeX
@article{Barton2025,
  author = {Barton, Justin and Gore, Trupti and Phanichkrivalkosil, Meghna and Shepherd, Adrian and Mishto, Michele},
  title = {nuTCRacker: Predicting the Recognition of HLA‐I–Peptide Complexes by αβTCRs for Unseen Peptides},
  journal = {European Journal of Immunology},
  year = {2025},
  volume = {55},
  number = {7},
  doi = {10.1002/eji.202451607}
}
Kostenlos starten →