EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

VirPLM: antigenic prediction of influenza A/H3N2 viruses with a fine-tuned protein language model

Xingyi Li iD, Kexin Xiao, Chunyan Zhou, Xiangting Jia, Dongmin Zhao, Jialuo Xu, Xianying Zeng, Jianzhong Shi, Xuequn Shang, Junnan Zhu, Huihui Kong

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag692 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Xingyi Li und 10 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Northwestern Polytechnical University, Xi'an 710129, China. Hauptthemen laut MEDLINE: Influenza A Virus, H3N2 Subtype, Antigens, Viral, Hemagglutinin Glycoproteins, Influenza Virus, Computational Biology. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agricultural Science and Technology Innovation Program, National Natural Science Foundation of China, Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Human influenza A/H3N2 viruses undergo rapid antigenic evolution primarily driven by the hemagglutinin subunit 1 (HA1). Within HA1, amino acid substitutions under immune pressure cause antigenic drift, necessitating frequent updates to vaccine strains. While hemagglutination inhibition (HI) assays remain the gold standard for assessing antigenic relationships, their labor-intensive and low-throughput nature limits scalability. Fortunately, the rapid accumulation of HA1 sequences enables sequence-based antigenic prediction, yet effectively extracting informative representations from these viral sequences remains challenging. Results In this study, we present VirPLM, a two-stage framework that adapts the ESM-2 protein language model to H3N2 HA1 sequences for antigenic prediction. VirPLM significantly outperforms representative methods and maintains robust performance under both cross-validation and retrospective time-split evaluations. Moreover, VirPLM identifies highly critical sites enriched in known regions related to antigenic evolution. In the season-specific coverage analysis, VirPLM-prioritized strains achieve higher estimated coverage rates than the corresponding historical strains recommended by the World Health Organization in most evaluated seasons, suggesting that VirPLM can provide complementary sequence-based evidence for candidate strain prioritization. Availability and Implementation The source code is available at https://github.com/xingyili/VirPLM, and the version used in this study is archived in Zenodo (DOI: 10.5281/zenodo.21650323).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Influenza A Virus, H3N2 SubtypeAntigens, ViralHemagglutinin Glycoproteins, Influenza VirusComputational BiologySoftwareHumansEvolution, Molecular

Substanzen

Antigens, ViralHemagglutinin Glycoproteins, Influenza Virus

Autor:innen und Institutionen

  • School of Computer Science, Northwestern Polytechnical University, Xi'an 710129, China.
  • State Key Laboratory of Animal Disease Control and Prevention, Harbin Veterinary Research Institute, Chinese Academy of Agricultural Sciences, Harbin 150001, China.
  • State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.

ORCID-Profile: Xingyi Li

Förderung

  • Agricultural Science and Technology Innovation Program
  • National Natural Science Foundation of China
  • Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China

Zitieren

APA

Li, X., Xiao, K., Zhou, C., Jia, X., Zhao, D., Xu, J., Zeng, X., Shi, J., Shang, X., Zhu, J., & Kong, H. (2026). VirPLM: antigenic prediction of influenza A/H3N2 viruses with a fine-tuned protein language model. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag692

Vancouver

Li X, Xiao K, Zhou C, Jia X, Zhao D, Xu J, et al. VirPLM: antigenic prediction of influenza A/H3N2 viruses with a fine-tuned protein language model. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag692

BibTeX
@article{Li2026,
  author = {Li, Xingyi and Xiao, Kexin and Zhou, Chunyan and Jia, Xiangting and Zhao, Dongmin and Xu, Jialuo and Zeng, Xianying and Shi, Jianzhong and Shang, Xuequn and Zhu, Junnan and Kong, Huihui},
  title = {VirPLM: antigenic prediction of influenza A/H3N2 viruses with a fine-tuned protein language model},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag692}
}
Kostenlos starten →