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

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 <i>coronavirus</i> 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.

Authors

Institutions

Publication Details

Journal
Science
Published
2025-02-20
DOI
https://doi.org/10.1126/science.adp2407
Citations
55
Primary Topic
vaccines and immunoinformatics approaches
Type
article
Field-Weighted Citation Impact
44.33
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

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

M. Anthony Moody, R. Sharon Chinthrajah, Paul J. Utz, Brandon Lam et al.
55 citations
Science
vaccines and immunoinformatics approaches
44.33
article

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

M. Anthony Moody, R. Sharon Chinthrajah, Paul J. Utz, Brandon Lam, Samuel Yang, Charlotte Cunningham‐Rundles, Jason D. Goldman, Nikhil Ram-Mohan, Robert John Tibshirani, Kari Christine Nadeau, Krishna M. Roskin, Scott E. Hensley, Joel M. Guthridge, James R. Heath, Imelda Balboni, Tho D. Pham, Katharina Röltgen, Susan Macwana, Elizabeth M. Drapeau, Ji-Yeun Lee, Jackson Michuda, Barton F. Haynes, Joan T. Merrill, Erin Craig, Neha Sehgal, Ramona A. Hoh, Maxim Zaslavsky, Kent P. Jensen, Benjamin A. Pinsky, Scott D. Boyd, Ella Parsons, Catherine A. Blish, Everett Meyer, Anshul Kundaje, Judith A. James, Khoa D. Nguyen, Wade DeJager
article en
55 citations

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 <i>coronavirus</i> 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.

ScienceVol. 387(6736)
Cincinnati Children's Hospital Medical Center (US), Beth Israel Deaconess Medical Center (US), Harvard University (US), Swiss Tropical and Public Health Institute (CH), Duke University (US), University of Basel (CH), University of Washington (US), Lupus Foundation of America (US), Oklahoma Medical Research Foundation (US), Institute for Systems Biology (US), Swedish Medical Center (US), Stanford Blood Center (US), New York University (US), University of Pennsylvania (US), University of Cincinnati Medical Center (US), Stanford University (US), Icahn School of Medicine at Mount Sinai (US)
Openalex Percentile: Top 0%
vaccines and immunoinformatics approaches
44.33
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.