Classification of autoimmune diseases from Peripheral blood TCR repertoires by multimodal multi-instance learning
This addresses the limited clinical application of TCR repertoires for autoimmune disease diagnosis, though it appears incremental as an improved method for a known bottleneck.
The researchers tackled the problem of diagnosing autoimmune diseases from sparse T cell receptor sequencing data by developing EAMil, a multimodal multi-instance learning framework that achieved state-of-the-art performance with AUCs of 98.95% for systemic lupus erythematosus and 97.76% for rheumatoid arthritis.
T cell receptor (TCR) repertoires encode critical immunological signatures for autoimmune diseases, yet their clinical application remains limited by sequence sparsity and low witness rates. We developed EAMil, a multi-instance deep learning framework that leverages TCR sequencing data to diagnose systemic lupus erythematosus (SLE) and rheumatoid arthritis (RA) with exceptional accuracy. By integrating PrimeSeq feature extraction with ESMonehot encoding and enhanced gate attention mechanisms, our model achieved state-of-the-art performance with AUCs of 98.95% for SLE and 97.76% for RA. EAMil successfully identified disease-associated genes with over 90% concordance with established differential analyses and effectively distinguished disease-specific TCR genes. The model demonstrated robustness in classifying multiple disease categories, utilizing the SLEDAI score to stratify SLE patients by disease severity as well as to diagnose the site of damage in SLE patients, and effectively controlling for confounding factors such as age and gender. This interpretable framework for immune receptor analysis provides new insights for autoimmune disease detection and classification with broad potential clinical applications across immune-mediated conditions.