Disease diagnostics using machine learning of B cell and T cell receptor sequences

• 成果类型: Article
• 署名作者: Zaslavsky, Maxim E.; Craig, Erin; Michuda, Jackson K.; Sehgal, Nidhi; Ram-Mohan, Nikhil; Lee, Ji-Yeun; Nguyen, Khoa D.; Hoh, Ramona A.; Pham, Tho D.; Roltgen, Katharina; Lam, Brandon; Parsons, Ella S.; Macwana, Susan R.; DeJager, Wade; Drapeau, Elizabeth M.; Roskin, Krishna M.; Cunningham-Rundles, Charlotte; Moody, M. Anthony; Haynes, Barton F.; Goldman, Jason D.; Heath, James R.; Chinthrajah, R. Sharon; Nadeau, Kari C.; Pinsky, Benjamin A.; Blish, Catherine A.; Hensley, Scott E.; Jensen, Kent; Meyer, Everett; Balboni, Imelda; Utz, Paul J.; Merrill, Joan T.; Guthridge, Joel M.; James, Judith A.; Yang, Samuel; Tibshirani, Robert; Kundaje, Anshul; Boyd, Scott D.
• 署名单位: Stanford University; Stanford University; Stanford University; Stanford University; Stanford University; Stanford University; University of Basel; Swiss Tropical & Public Health Institute; University of Basel; Stanford University; Oklahoma Medical Research Foundation; University of Pennsylvania; University System of Ohio; University of Cincinnati; Cincinnati Children's Hospital Medical Center; University System of Ohio; University of Cincinnati; Cincinnati Children's Hospital Medical Center; Icahn School of Medicine at Mount Sinai; Duke University; Duke University; Duke University; Duke University; Swedish Medical Center; University of Washington; University of Washington Seattle; Institute for Systems Biology (ISB); University of Washington; University of Washington Seattle; Harvard University; Harvard T.H. Chan School of Public Health; Harvard University; Harvard University Medical Affiliates; Beth Israel Deaconess Medical Center; Stanford University; Stanford University; New York University; Stanford University
• 刊物名称: SCIENCE
• ISSN/ISSBN: 0036-10725
• DOI: 10.1126/science.adp2407
• 发表日期: 2025-02-21
• 页码: 844-+
• 关键词: systemic-lupus-erythematosus; repertoire; immunoglobulin; antibodies; influenza; autoantibodies; diversity; signatures; responses; selection

摘要

Clinical diagnosis typically incorporates physical examination, patient history, various laboratory tests, and imaging studies but makes limited use of the human immune system's own record of antigen exposures encoded by receptors on B cells and T cells. We analyzed immune receptor datasets from 593 individuals to develop MAchine Learning for Immunological Diagnosis, an interpretive framework to screen for multiple illnesses simultaneously or precisely test for one condition. This approach detects specific infections, autoimmune disorders, vaccine responses, and disease severity differences. Human-interpretable features of the model recapitulate known immune responses to severe acute respiratory syndrome coronavirus 2, influenza, and human immunodeficiency virus, highlight antigen-specific receptors, and reveal distinct characteristics of systemic lupus erythematosus and type-1 diabetes autoreactivity. This analysis framework has broad potential for scientific and clinical interpretation of immune responses.