Machine learning analysis of the T cell receptor repertoire identifies sequence features that predict self-reactivity

Abstract

The T cell receptor (TCR) determines the specificity and affinity for both foreign and self-peptides presented by MHC. It is established that self-pMHC reactivity impacts T cell function, but it has been challenging to identify TCR sequence features that predict T cell fate. To discern patterns distinguishing TCRs from naive CD4+ T cells with low versus high self-pMHC reactivity, we used data from 42 mice to train a machine learning (ML) algorithm that predicts self-reactivity directly from TCR{beta} sequences. This approach revealed that n-nucleotide additions and acidic amino acids weaken self-reactivity. We tested our ML predictions of TCR{beta} sequence self-reactivity using retrogenic mice. Extrapolating our analyses to independent datasets, we found high predicted self-reactivity for regulatory CD4+ T cells and low predicted self-reactivity for T cells responding to chronic infection. Our analyses suggest a potential trade-off between repertoire diversity and self-reactivity intrinsic to the architecture of a TCR repertoire.