Story perspectives

MIT's VaxSeer AI Predicts Flu Strains, Outperforming WHO

8/29/2025

33 7

Summary

Story summary

MIT researchers created VaxSeer, an AI system that predicts dominant flu strains for better vaccine selection.
VaxSeer surpassed WHO predictions for A/H3N2 in 9 of 10 seasons and A/H1N1 in 6 of 10 seasons.
The system employs deep learning on viral sequences to model flu evolution and vaccine efficacy.
Future iterations may incorporate more proteins and factors for broader predictive modeling.
The project is funded by the U.S. Defense Threat Reduction Agency and the MIT Jameel Clinic.

1 of 1

Story summary

MIT researchers created VaxSeer, an AI system that predicts dominant flu strains for better vaccine selection.
VaxSeer surpassed WHO predictions for A/H3N2 in 9 of 10 seasons and A/H1N1 in 6 of 10 seasons.
The system employs deep learning on viral sequences to model flu evolution and vaccine efficacy.
Future iterations may incorporate more proteins and factors for broader predictive modeling.
The project is funded by the U.S. Defense Threat Reduction Agency and the MIT Jameel Clinic.