Li X, Xiao K, Zhou C, Jia X, Zhao D, Xu J, Zeng X,. VirPLM: Antigenic prediction of influenza A/H3N2 viruses with a fine-tuned protein language model. Bioinformatics. 2026 Sep 18:btag692
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).
Supplementary information: Supplementary information is available at Bioinformatics online.
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).
Supplementary information: Supplementary information is available at Bioinformatics online.
See Also:
Latest articles in those days:
- Weekly US Influenza Surveillance Report: Key Updates for Week 45, ending November 14, 2026 11 hours ago
- Anatomical Compartmentalization in Chickens Drives Divergent H9N2 Influenza Evolution Toward Human Receptor Binding and Immune Escape 1 days ago
- Epidemiologic Variability and Clinical Severity Across 11 Influenza Seasons in Children 2 days ago
- Molecular Epidemiology of Clade 2.3.4.4b H5N1 High-Pathogenicity Avian Influenza in South Africa, 2025-2026 2 days ago
- Structural basis of avian-to-human receptor-binding adaptation in H9Ny influenza A virus hemagglutinin 2 days ago
[Go Top] [Close Window]


