TCRLens: structure-aware equivariant graph learning for TCR-pMHC-I recognition and immunogenic epitope discovery
Bioinformatics Advances · 07.01.2026 · 6 (1)
DOI: 10.1093/bioadv/vbag066 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics Advances, online erschienen am 24.02.2026. Verfasst von Paopit Siriarchawatana und 3 weiteren Autor:innen. Beteiligte Einrichtung: Microbial Systems and Computational Biology Research Team, Thailand Bioresource Research Center (TBRC), Pathum Thani, 12120, Thailand. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Development Agency.
Abstract (Originalsprache)
Motivation Accurate prediction of T-cell receptor (TCR) recognition of peptide-MHC class I (pMHC-I) complexes is a key challenge due to structural diversity and data sparsity. We introduce TCRLens, a structure-aware deep learning framework that models residue-level interactions across five critical interface zones using multi-scale graph representations and an equivariant graph neural network (EGNN). To mitigate data sparsity and severe class imbalance arising from limited negative samples, TCRLens incorporates a variational autoencoder-generative adversarial network (VAE-GAN) to generate structurally plausible weak-affinity interaction samples. We evaluated TCRlens across three prediction tasks including peptide-MHC binding, peptide-TCR recognition, and full-complex TCR-pMHC-I interaction and observed consistently strong performance. Results Using curated dataset of human TCR-pMHC-I structural complexes from ATLAS and TCR3d, TCRLens outperforms state-of-the-art sequence-based, motif-based, and structure-aware methods, including NetMHCpan 4.2, CapsNet-MHC, RPEMHC, NetTCR-2.0, TITAN, PanPep, pMTnet, ERGO II, and STAG. Furthermore, TCRLens demonstrates robust cross-species generalization, achieving high predictive performance in swine and chicken MHC-I systems. These findings highlight the value of geometry-aware representation learning and generative data augmentation for capturing immunological specificity. TCRLens provides a unified and extensible platform for TCR-pMHC-I interaction modeling, with potential applications in epitope discovery and structure-guided vaccine design across both human and veterinary immunology. Availability and implementation The code used in this study is publicly available at https://github.com/paopitsiri/TCRLens.
Autor:innen und Institutionen
- Microbial Systems and Computational Biology Research Team, Thailand Bioresource Research Center (TBRC), Pathum Thani, 12120, Thailand.
- National Center for Genetic Engineering and Biotechnology (BIOTEC), Pathum Thani, 12120, Thailand.
- Virology and Vaccine Technology Research Team, Veterinary Health Innovation and Management Research Group, Pathum Thani, 12120, Thailand.
ORCID-Profile: Paopit Siriarchawatana
Förderung
- National Science and Technology Development Agency
Zitieren
APA
Siriarchawatana, P., Ingsriswang, S., Kaewborisuth, C., & Jongkaewwattana, A. (2026). TCRLens: structure-aware equivariant graph learning for TCR-pMHC-I recognition and immunogenic epitope discovery. Bioinformatics Advances, 6(1). https://doi.org/10.1093/bioadv/vbag066
Vancouver
Siriarchawatana P, Ingsriswang S, Kaewborisuth C, Jongkaewwattana A. TCRLens: structure-aware equivariant graph learning for TCR-pMHC-I recognition and immunogenic epitope discovery. Bioinformatics Advances. 2026;6(1). doi:10.1093/bioadv/vbag066
BibTeX
@article{Siriarchawatana2026,
author = {Siriarchawatana, Paopit and Ingsriswang, Supawadee and Kaewborisuth, Challika and Jongkaewwattana, Anan},
title = {TCRLens: structure-aware equivariant graph learning for TCR-pMHC-I recognition and immunogenic epitope discovery},
journal = {Bioinformatics Advances},
year = {2026},
volume = {6},
number = {1},
doi = {10.1093/bioadv/vbag066}
}
EUVIMED