Nature Microbiology, Published online: 27 May 2026; doi:10.1038/s41564-026-02377-5 By integrating DMS profiles, evolutionary trajectories and epidemiological data, a deep-learning framework enables the spatiotemporal prediction of emerging dominant SARS-CoV-2 variants.
A deep mutational scanning-informed protein language model predicts SARS-CoV-2 evolution dynamics with spatiotemporal resolution
Yunlong Cao