Skip to main content
 
Notice: Users may be experiencing issues with displaying some pages on stanfordhealthcare.org. We are working closely with our technical teams to resolve the issue as quickly as possible. Thank you for your patience.
Stanford Health Care

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

Disease diagnostics using machine learning of B cell and T cell receptor sequences. Science (New York, N.Y.) Zaslavsky, M. E., Craig, E., Michuda, J. K., Sehgal, N., Ram-Mohan, N., Lee, J. Y., Nguyen, K. D., Hoh, R. A., Pham, T. D., Röltgen, K., Lam, B., Parsons, E. S., Macwana, S. R., DeJager, W., Drapeau, E. M., Roskin, K. M., Cunningham-Rundles, C., Moody, M. A., Haynes, B. F., Goldman, J. D., Heath, J. R., Chinthrajah, R. S., Nadeau, K. C., Pinsky, B. A., Blish, C. A., Hensley, S. E., Jensen, K., Meyer, E., Balboni, I., Utz, P. J., Merrill, J. T., Guthridge, J. M., James, J. A., Yang, S., Tibshirani, R., Kundaje, A., Boyd, S. D. 2025; 387 (6736): eadp2407

Abstract

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.

View details for DOI 10.1126/science.adp2407

View details for PubMedID 39977494