LucaVirus, a unified 1-billion-parameter foundation model trained on 25.4 billion nucleotide and amino acid tokens from nearly all known viruses, achieves state-of-the-art performance in discovering hidden viruses from genomic dark matter, annotating uncharacterized viral proteins, predicting viral fitness landscapes, and identifying therapeutic antibodies, while requiring substantially fewer computational resources than larger generalist models through its virus-specific multi-modal architecture that spontaneously learns fundamental biological syntax and evolutionary relationships.

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 nearly all known viruses. LucaVirus learns biologically meaningful representations capturing 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 achieves state-of-the-art results in three tasks and matches leading models in the fourth with one-third the parameters. Together, these findings demonstrate the power of a unified foundation model to comprehensively decode the viral world and establish LucaVirus as an efficient and versatile platform for AI-driven virology, from virus discovery to functional and therapeutic predictions.