DUET: a graph-based workflow for TCR-epitope prioritization and tumor-reactive T-cell identification
Briefings in Bioinformatics · 2026
DOI: 10.1093/bib/bbag519 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Yunsheng Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science & Mathematics, Faculty of Computer Science and Technology, Algoma University, 24 Queen St E, Brampton, ON L6V 1A3, Can…. Hauptthemen laut MEDLINE: Receptors, Antigen, T-Cell, Epitopes, T-Lymphocyte, Neoplasms, Computational Biology. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada (NSERC), Algoma University Research Fund.
Abstract (Originalsprache)
Accurate prioritization of T-cell receptor (TCR)-epitope interactions and identification of tumor-reactive T cells are important but difficult steps in immunotherapy-oriented bioinformatics workflows. Existing methods typically address these tasks separately and either model TCR-epitope pairs as independent observations or rely primarily on transcriptomic signatures. In this study, we present DUET (Dual Unified Evaluation of TCR-Epitopes and Tumor-reactive T cells), a graph-based computational workflow that unifies both applications within a single heterogeneous graph framework. The protocol represents TCRs, epitopes, and T cells as typed nodes connected by similarity and association edges, and combines pretrained sequence embeddings with edge-aware graph attention, Laplacian positional encoding, and bidirectional cross-domain attention. Applied to the IEDB and VDJdb benchmarks, DUET achieved AUROC/AUPR values of 0.937/0.922 and 0.992/0.990, respectively, outperforming five state-of-the-art algorithms under standard evaluation. On a single-cell RNA-seq tumor-reactivity benchmark, the workflow achieved an area under the receiver operating characteristic curve of 0.985 and an area under the precision-recall curve of 0.975, substantially exceeding transcriptomic signature-based baselines. Additional generalization analyses showed that DUET’s clearest graph-specific benefit occurred under epitope-disjoint TCR-epitope prediction. Ablation analysis showed that Laplacian positional encoding provided the largest performance gain, particularly in sparse graph settings. These results suggest that heterogeneous graph modeling can serve as a practical protocol for integrating receptor sequence, antigen context, and cellular phenotype in computational immunology.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Computer Science & Mathematics, Faculty of Computer Science and Technology, Algoma University, 24 Queen St E, Brampton, ON L6V 1A3, Canada.
- Marshall McLuhan Catholic Secondary School, 1107 Avenue Rd, Toronto, ON M5N 3B1, Canada.
- College of Computational, Mathematical and Physical Sciences, School of Computer Science, University of Guelph, 474 Gordon St, Guelph, ON N1G 1Y4, Canada.
Förderung
- Natural Sciences and Engineering Research Council of Canada (NSERC)
- Algoma University Research Fund
Zitieren
APA
Chen, Y., Giuliano, V., Dacillo, I., Lin, W., Yan, Y., & Luo, P. (2026). DUET: a graph-based workflow for TCR-epitope prioritization and tumor-reactive T-cell identification. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag519
Vancouver
Chen Y, Giuliano V, Dacillo I, Lin W, Yan Y, Luo P. DUET: a graph-based workflow for TCR-epitope prioritization and tumor-reactive T-cell identification. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag519
BibTeX
@article{Chen2026,
author = {Chen, Yunsheng and Giuliano, Vanessa and Dacillo, Ian and Lin, Wenjun and Yan, Yan and Luo, Ping},
title = {DUET: a graph-based workflow for TCR-epitope prioritization and tumor-reactive T-cell identification},
journal = {Briefings in Bioinformatics},
year = {2026},
doi = {10.1093/bib/bbag519}
}
EUVIMED