Trained solely on pre-pandemic sequences, DERIVE anticipates variant emergence and immune escape weeks before clinical recognition across divergent viral families, demonstrating that generalizable pandemic threat assessment requires no real-time functional surveillance data.
DERIVE, a flow-based generative framework that learns disentangled multimodal representations of viral evolutionary history by integrating sequence homology with physicochemical and structural features, accurately predicts high-risk mutations and antigenic evolution using only pre-pandemic data for SARS-CoV-2 and generalizes robustly across structurally diverse viral families including influenza, HIV, rabies lyssavirus, and chikungunya virus with strong concordance to functional measurements.
Antigenic evolution drives immune escape and complicates early assessment of emerging pathogens, especially when genomic surveillance is sparse and functional measurements lag behind real-world spread. Early prediction and generalization to unknown viruses require faithful and information-rich representations of viral evolution, a need that is not fully addressed by existing protein language model–based approaches. Here we introduce DERIVE, a flow-based generative framework that learns a disentangled latent representation of multimodal evolutionary history by integrating sequence homology with physicochemical and structural features. Using only pre-pandemic SARS-CoV-2 sequences, DERIVE prioritizes high-risk mutations, reconstructs strain-level evolutionary trajectories, forecasts immune escape and prevalence trends, and produces mutation-level effect maps. The learned representation transfers robustly across viral families, with strong concordance to functional data for influenza virus, HIV, rabies lyssavirus and chikungunya virus. Together, these results position DERIVE as a generalizable and interpretable framework for anticipating antigenic evolution and supporting early, actionable assessment of future “Disease X” threats.