Altered somatic hypermutation patterns in covid-19 patients predicts disease severity

Much of the battle between the human body and SARS-CoV-2 relies on lymphocytes and their antigen receptors. Identifying and characterizing successful receptors is of utmost clinical importance. We report here the application of a machine learning approach utilizing B Cell Receptor (BCR) and T cell Receptor (TCR) repertoire sequencing data taken from severe and mild SARS-CoV-2 infected individuals and uninfected controls. In contrast to previous studies, our approach was successful in stratifying non-infected from infected individuals, as well as disease level of severity. The features that drive this classification can be used to build and adapt therapeutic strategies to covid-19, and constitute a proof of concept for future epidemiological challenges.