meTCRs - Learning a metric for T-cell receptors

Felix Drost, Lennard Schiefelbein, Benjamin Schubert

Keywords: Deep Metric Learning, T cell receptor, Specificity prediction

TL;DR: We developed the deep metric learning based distance meTCRs for embedding T cell receptors for clustering, visualisation, and querying against TCR-epitope databases.

Abstract: T cell receptors (TCRs) bind to pathogen- or self-derived epitopes to elicit a T cell response as part of the adaptive immune system. Determining the specificity of TCRs provides context for immunological studies and can be used to identify candidates for novel immunotherapies. To avoid costly experiments, large-scale TCR-epitope databases are queried for similar sequences via various distance functions. Here, we developed the deep-learning based distance meTCRs. Contrary to most previous approaches, the method avoids computational expansive pairwise string operations by comparing TCRs in a numeric embedding. In contrast to models which are trained specificity-agnostic, we directly utilize epitope information by applying deep metric learning to guide the training. Summarizing, we present meTCRs as a scalable alternative to embed TCR repertoires for clustering, visualization, and querying against the ever-increasing amount TCR-epitope pairs in publicly available databases.