Classification of autoimmune diseases from Peripheral blood TCR repertoires by multimodal multi-instance learning

TL;DR

This paper introduces EAMil, a deep learning framework that accurately classifies autoimmune diseases from TCR sequencing data, overcoming sequence sparsity and low witness rates, with high accuracy and interpretability.

Contribution

The study presents a novel multimodal multi-instance learning model that integrates advanced feature extraction and attention mechanisms for autoimmune disease classification from TCR data.

Findings

Achieved AUCs of 98.95% for SLE and 97.76% for RA.

Successfully identified disease-associated TCR genes with over 90% concordance.

Demonstrated robustness in classifying multiple disease categories and stratifying disease severity.

Abstract

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.