 The article presents VirSorter, a tool designed to detect viral signal in different types of microbial sequence data, such as single-cell amplified genomes, sacks, and genomic fragments assembled from metagenomic sequencing. VirSorter uses probabilistic models and extensive virome data to maximize detection of novel viruses and performs better than existing tools in predicting viral sequences outside of a host genome. The tool can also be used to identify viral sequence and viral metagenomes by sorting away cellular DNA. VirSorter is made available through the I-Plant Cyber Infrastructure and should enable the discovery of new viruses in microbial datasets, furthering our understanding of uncultivated viral communities across diverse ecosystems. This article was authored by Simon Rue, François Nault, Bonnie L. Hurwitz, and others. We are article.tv. Links in the description below.