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

作者：Maxim Zaslavsky, Erin Craig, Jackson Michuda, Nidhi Sehgal, Nikhil Ram-Mohan, Ji-Yeun Lee, Khoa D. Nguyen, Ramona A. Hoh, Tho D. Pham, Katharina Röltgen, Brandon Lam, Ella Parsons, Susan Macwana, Wade DeJager, Elizabeth M. Drapeau, Krishna M. Roskin, Charlotte Cunningham‐Rundles, M. Anthony Moody, Barton F. Haynes, Jason D. Goldman, James R. Heath, R. Sharon Chinthrajah, Kari C. Nadeau, Benjamin A. Pinsky, Catherine A. Blish, Scott E. Hensley, Kent P. Jensen, Everett Meyer, Imelda Balboni, Paul J. Utz, Joan T. Merrill, Joel M. Guthridge, Judith A. James, Samuel Yang, Robert Tibshirani, Anshul Kundaje, Scott D. Boyd · 发表于：Science · 年份：2025 · DOI：10.1126/science.adp2407 · 被引用次数：90 · 研究领域：vaccines and immunoinformatics approaches、SARS-CoV-2 and COVID-19 Research、Immunotherapy and Immune Responses

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.