Design and characterization of broadly protective influenza A(H3N2) vaccine candidates using protein language models
- 1VUMC
Abstract
Seasonal influenza A viruses cause significant global morbidity each year. Although vaccination remains the primary preventive strategy, effectiveness is often reduced by antigenic drift. This challenge is particularly pronounced for influenza A(H3N2), which has required eight vaccine updates over the past decade. Here, we present a computational framework to engineer broadly reactive influenza A(H3N2) vaccines, using protein language models to generate novel hemagglutinin (HA) sequences and a machine learning model to predict antigenic distance from circulating strains. In a proof-of-concept study, seven HA candidates designed using sequence data from 2013-2018 were evaluated in mice against contemporary and subsequently circulating viruses. Two candidates elicited protective levels of reactive antibodies, robust H3-specific antibody-secreting cell responses, and cross-neutralization against contemporary clades and drifted 2019-2020 strains. These findings demonstrate that an integrated generation-selection strategy can enhance vaccine coverage across current and future A(H3N2) seasons and may be applicable to other influenza subtypes.
Related
- Epistasis and pleiotropy constrain the evolution of cross-reactive breadth in a broadly neutralizing influenza antibody
- Computationally Optimized H1 and H3 Hemagglutinin Messenger RNA Vaccines Confer Broad Protective Immunity Against Modern Influenza Viruses
- Large Language Models as Simulated Candidates in Objective Structured Clinical Examinations: A Rubric-Mapping Proof-of-Concept Study
- Genetic Characterization of Avian Influenza H14 Viruses in Guangdong, China: Evidence of Intercontinental Transmission and Reassortment in the East Asian–Australasian Flyway
- Epidemiological characterization of avian influenza virus circulation in pigeons and quail across different production systems in Chattogram, Bangladesh
BibTeX
@misc{howard2026design,
title = {{Design and characterization of broadly protective influenza A(H3N2) vaccine candidates using protein language models}},
author = {V. R. Howard and J. D. Allen and M. H. Thomas and G. A. Sautto and T. M. Ross and I. S. Georgiev},
howpublished = {bioRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.26.747087},
url = {https://www.biorxiv.org/content/10.64898/2026.08.26.747087v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Design and characterization of broadly protective influenza A(H3N2) vaccine candidates using protein language models
AU - V. R. Howard
AU - J. D. Allen
AU - M. H. Thomas
AU - G. A. Sautto
AU - T. M. Ross
AU - I. S. Georgiev
PY - 2026
DA - 2026/08/26
PB - bioRxiv
DO - 10.64898/2026.08.26.747087
UR - https://www.biorxiv.org/content/10.64898/2026.08.26.747087v1
AB - Seasonal influenza A viruses cause significant global morbidity each year. Although vaccination remains the primary preventive strategy, effectiveness is often reduced by antigenic drift. This challenge is particularly pronounced for influenza A(H3N2), which has required eight vaccine updates over the past decade. Here, we present a computational framework to engineer broadly reactive influenza A(H3N2) vaccines, using protein language models to generate novel hemagglutinin (HA) sequences and a machine learning model to predict antigenic distance from circulating strains. In a proof-of-concept study, seven HA candidates designed using sequence data from 2013-2018 were evaluated in mice against contemporary and subsequently circulating viruses. Two candidates elicited protective levels of reactive antibodies, robust H3-specific antibody-secreting cell responses, and cross-neutralization against contemporary clades and drifted 2019-2020 strains. These findings demonstrate that an integrated generation-selection strategy can enhance vaccine coverage across current and future A(H3N2) seasons and may be applicable to other influenza subtypes.
ER -