March 12, 2024
Flu vaccines could be getting a booster of their own with the help of machine learning. MAIVeSS — the Machine-learning Assistant Influenza VaccinE Strain Selection framework — functions to reduce the time it takes to choose flu strains used in annual vaccines from months to mere days.
Designed and built by University of Missouri researcher Cheng Gao in collaboration with Mississippi State University, MAIVeSS is a computational model that combines algorithms to select optimal flu candidate vaccine viruses when supplied a specific strain of the flu.
This technology can help scientists predict which flu strains will be most dominant in a given year — an aspect key in developing successful flu vaccines each season — and what vaccine virus candidates will yield high enough for manufacture. If the wrong variants are chosen, a vaccine will be ineffective against dominant strains causing illness and won’t efficiently yield enough for vaccine production.
“That’s our goal; we really want to help people speed up the procedure and make effective products,” said Cheng Gao, lead author and doctoral student the in the lab of Henry Wan, a Bond Life Sciences Center researcher and director of the NextGen Center for Influenza and Emerging Infectious Diseases.
This new algorithm improves on a tried-and-true vaccine creation method. However, because the process to identify virus strain candidates for yearly flu vaccines has been lengthy and complicated, this method represents a significant advance in vaccine development and strengthens the efficacy of future flu vaccines.
The study “MAIVeSS: Streamlined selection of antigenically matched, high-yield viruses for seasonal influenza vaccine production” was published in the journal Nature Communications.
Read more from Bond Life Sciences Center
