EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Foundation Protein Language Models for Influenza A Virus T-Cell Epitope Prediction: A Transformer-Based Viroinformatics Framework

Syed Nisar Hussain Bukhari, Kingsley A Ogudo iD

Viruses · 18.03.2026 · 18 (3) · 380

DOI: 10.3390/v18030380 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Viruses, online erschienen am 18.03.2026. Verfasst von Syed Nisar Hussain Bukhari und 1 weiteren Autor:innen. Beteiligte Einrichtung: National Institute of Electronics and Information Technology (NIELIT) J&K, Srinagar 191132, India. Hauptthemen laut MEDLINE: Epitopes, T-Lymphocyte, Influenza A virus, Computational Biology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Johannesburg.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Influenza A virus remains a major cause of respiratory disease worldwide and poses a persistent challenge to vaccine development due to its rapid genetic evolution and antigenic variability. T-cell-based immunity has therefore gained increasing importance, as it can provide broader and more durable protection by targeting conserved viral regions. Accurate identification of T-cell epitopes (TCEs) is a fundamental requirement for epitope-based vaccine design and immunological research. Although numerous computational methods have been proposed, many existing approaches rely on handcrafted physicochemical features, which offer limited ability to capture contextual sequence dependencies. In this study, a transformer-based viroinformatics framework is proposed for the binary prediction of TCEs from Influenza A virus peptide sequences. The framework employs a pretrained Evolutionary Scale Modeling-2 (ESM-2) protein language model (PLM) to generate rich, contextualized embeddings directly from raw amino acid sequences, eliminating the need for manual feature engineering. These embeddings are processed using a lightweight attention-based transformer classifier to learn epitope-specific sequence patterns. The model achieves strong and stable predictive performance, attaining an accuracy of approximately 97% and an AUC close to 0.99 under stratified cross-validation. Ablation analysis further confirms that protein language model representations and self-attention contribute substantially to performance gains over classical machine learning baselines. To enhance practical reliability, Monte Carlo dropout is incorporated during inference to provide uncertainty-aware predictions, enabling differentiation between high-confidence and ambiguous peptide candidates. In addition, attention-based interpretability is used to identify residue-level contributions to model decisions, offering biologically meaningful insights into epitope recognition. Overall, this study demonstrates that PLMs combined with Transformer architectures provide an effective, interpretable, and a promising computational framework for Influenza A TCE discovery and vaccine research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Epitopes, T-LymphocyteInfluenza A virusComputational BiologyImmunoinformaticsHumansLarge Language ModelsPrediction AlgorithmsAmino Acid SequenceInfluenza, HumanPredictive Learning Models

Stichwörter der Autor:innen

Influenza A virusT-Cell epitopeattention mechanismsprotein language modelstransformer networksuncertainty estimation

Substanzen

Epitopes, T-Lymphocyte

Autor:innen und Institutionen

  • National Institute of Electronics and Information Technology (NIELIT) J&K, Srinagar 191132, India.
  • Department of Electrical & Electronic Engineering Technology, University of Johannesburg, Johannesburg 2094, South Africa.

ORCID-Profile: Kingsley A Ogudo

Förderung

  • University of Johannesburg

Zitieren

APA

Bukhari, S. N. H., & Ogudo, K. A. (2026). Foundation Protein Language Models for Influenza A Virus T-Cell Epitope Prediction: A Transformer-Based Viroinformatics Framework. Viruses, 18(3), 380. https://doi.org/10.3390/v18030380

Vancouver

Bukhari SNH, Ogudo KA. Foundation Protein Language Models for Influenza A Virus T-Cell Epitope Prediction: A Transformer-Based Viroinformatics Framework. Viruses. 2026;18(3):380. doi:10.3390/v18030380

BibTeX
@article{Bukhari2026,
  author = {Bukhari, Syed Nisar Hussain and Ogudo, Kingsley A},
  title = {Foundation Protein Language Models for Influenza A Virus T-Cell Epitope Prediction: A Transformer-Based Viroinformatics Framework},
  journal = {Viruses},
  year = {2026},
  volume = {18},
  number = {3},
  pages = {380},
  doi = {10.3390/v18030380}
}
Kostenlos starten →