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.

人体与严重急性呼吸综合征冠状病毒2（SARS-CoV-2）的免疫对抗，很大程度上依赖于淋巴细胞及其抗原受体。精准识别并表征具有抗病毒活性的受体，具有至关重要的临床意义。本研究报道了一种机器学习方法的应用：该方法利用了从重症、轻症SARS-CoV-2感染者以及未感染对照人群中获取的B细胞受体（B Cell Receptor, BCR）和T细胞受体（T Cell Receptor, TCR）受体组测序数据。与既往研究不同，本方法可有效区分未感染人群与感染者，还能对疾病严重程度进行分层。驱动该分类任务的特征可用于构建并优化新型冠状病毒肺炎（COVID-19）的治疗策略，同时为应对未来的流行病学挑战提供了概念验证。