EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PepTCR-Net: prediction of multi-class antigen peptides by T-cell receptor sequences with deep learning

Phi Le, Leah Ung, Hai Yang, Anwen Huang, Tao He, Peter Bruno, David Y Oh, Bridget P Keenan, Li Zhang iD

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf351 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Phi Le und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine, University of California San Francisco, 550 16th Street, San Francisco, CA 94158, United States. Hauptthemen laut MEDLINE: Deep Learning, Receptors, Antigen, T-Cell, Peptides. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS, NIH HHS, National Cancer Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting T-cell receptor (TCR) recognizing antigen peptides is crucial for understanding the immune system and developing new treatments for cancer, infectious and autoimmune diseases. As experimental methods for identifying TCR–antigen recognition are expensive and time-consuming, machine-learning approaches are increasingly used. However, existing computational tools often struggle with generalization due to limited data and challenges in acquiring true non-recognition pairs and rarely integrate multiple biological features into unified frameworks. To address these challenges, we propose a two-step framework for predicting TCR–antigen recognition. The first step focuses on feature engineering: neural network-based embeddings of letter-based TCR and peptide sequences inspired by language models, and categorical encoding of Human Leukocyte Antigen types and Variable/Joining genes. In the second step, we built a prediction model to assess the likelihood of TRC–antigen recognition by a Bayesian Feedforward Neural Network. We trained and validated the framework using large public databases. Our results demonstrate that our advanced feature engineering delivers strong predictive performance both internally and externally. We applied the framework to a real-world case for predicting whether specific TCRs can recognize SARS-CoV-2 epitope peptides, demonstrating that our framework can function as a de novo TCR–antigen prediction tool applicable to infectious diseases.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningReceptors, Antigen, T-CellPeptidesHumansNeural Networks, ComputerComputational BiologySARS-CoV-2COVID-19Bayes Theorem

Stichwörter der Autor:innen

Atchley factorT-cell receptor networkantigen peptidesencoder–decodergraph embeddingneural networks

Substanzen

Receptors, Antigen, T-CellPeptides

Autor:innen und Institutionen

  • Department of Medicine, University of California San Francisco, 550 16th Street, San Francisco, CA 94158, United States.
  • Helen Diller Family Comprehensive Cancer Center, University of California San Francisco, 1450 3rd St. San Francisco, CA 94158, United States.
  • University of California Berkeley, 110 Sproul Hall, Berkeley, CA 94720, United States.
  • Department of Mathematics, San Francisco State University, 1600 Holloway AvenueSan Francisco, CA 94132, United States.
  • Department of Urology, University of California San Francisco, 1450 3rd StreetSan Francisco, CA 94158, United States.
  • Department of Epidemiology & Biostatistics, University of California San Francisco, 550 16th Street, San Francisco, CA 94158, United States.

ORCID-Profile: Li Zhang

Förderung

  • NCI NIH HHS
  • NIH HHS
  • National Cancer Institute
  • National Institutes of Health

Zitieren

APA

Le, P., Ung, L., Yang, H., Huang, A., He, T., Bruno, P., Oh, D. Y., Keenan, B. P., & Zhang, L. (2025). PepTCR-Net: prediction of multi-class antigen peptides by T-cell receptor sequences with deep learning. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf351

Vancouver

Le P, Ung L, Yang H, Huang A, He T, Bruno P, et al. PepTCR-Net: prediction of multi-class antigen peptides by T-cell receptor sequences with deep learning. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf351

BibTeX
@article{Le2025,
  author = {Le, Phi and Ung, Leah and Yang, Hai and Huang, Anwen and He, Tao and Bruno, Peter and Oh, David Y and Keenan, Bridget P and Zhang, Li},
  title = {PepTCR-Net: prediction of multi-class antigen peptides by T-cell receptor sequences with deep learning},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf351}
}
Kostenlos starten →