Predicting the evolutionary and functional landscapes of viruses with a unified nucleotide-protein language model: LucaVirus.

Predicting viral evolution and function remains a central challenge in biology, hindered by high sequence divergence and limited knowledge compared to cellular organisms. Here, we introduce LucaVirus, a multi-modal foundation model for viruses, trained on 25.4 billion nucleotide and amino acid tokens covering a vast majority of catalogued viral diversity. LucaVirus learns biologically meaningful representations that reflect relationships between sequences, protein/gene homology, and evolutionary divergence. Using these embeddings, we developed downstream models that address key virology tasks: identifying hidden viruses in genomic 'dark matter', annotating enzymatic activities of uncharacterized proteins, predicting viral evolvability, and identifying antibody candidates for emerging viruses. LucaVirus demonstrates competitive performance in three tasks and matches leading models in the fourth with one-third the parameters. Together, these findings demonstrate the utility of a unified foundation model in analyzing viral sequence data and establish LucaVirus as an efficient and versatile platform for AI-driven virology, from virus discovery to functional and therapeutic predictions.