A groundbreaking achievement in virology has been accomplished through a collaboration between researchers from the University of Sydney, Alibaba Cloud Intelligence’s Apsara Lab, and Sun Yat-Sen University. Their study, published in the renowned journal Cell, uncovers over 161,000 previously unknown RNA virus species–an unprecedented milestone in scientific history. This breakthrough was enabled by LucaProt, an innovative machine learning tool that has transformed the analysis of viral genomic data. Until now, vast quantities of genetic data from environmental samples–spanning soil, water, and plant and animal tissues–have remained largely unanalyzed. Millions of genetic sequence fragments, potentially viral, were scattered across extensive databases, rendering them inaccessible for efficient analysis with conventional methods. Manual processing of such enormous datasets would have demanded decades of work from numerous researchers. Unlike earlier tools, LucaProt employs advanced deep learning algorithms to identify distinctive patterns in genomic sequences. Rather than merely searching for matches with known viruses, it examines gene structures, predicts the functions of encoded proteins, and classifies novel viruses based on this intricate data, even when they lack close relatives in existing scientific records. LucaProt’s strength lies in its ability to consider multiple factors, such as genetic code characteristics, genome size, and the presence of specific genes, enabling precise differentiation of viruses across various families and genera.