Contrastive learning of T cell receptor representations

TL;DR

This paper introduces SCEPTR, a contrastive learning-based TCR language model that improves TCR specificity prediction by combining autocontrastive learning with masked-language modeling, achieving state-of-the-art results.

Contribution

The paper presents a novel pre-training strategy for TCR language models that enhances data efficiency and predictive performance.

Findings

SCEPTR outperforms existing protein language models in TCR specificity prediction.

Contrastive learning combined with masked-language modeling improves model performance.

Sequence alignment-based methods still outperform some pre-trained models without contrastive learning.

Abstract

Computational prediction of the interaction of T cell receptors (TCRs) and their ligands is a grand challenge in immunology. Despite advances in high-throughput assays, specificity-labelled TCR data remains sparse. In other domains, the pre-training of language models on unlabelled data has been successfully used to address data bottlenecks. However, it is unclear how to best pre-train protein language models for TCR specificity prediction. Here we introduce a TCR language model called SCEPTR (Simple Contrastive Embedding of the Primary sequence of T cell Receptors), capable of data-efficient transfer learning. Through our model, we introduce a novel pre-training strategy combining autocontrastive learning and masked-language modelling, which enables SCEPTR to achieve its state-of-the-art performance. In contrast, existing protein language models and a variant of SCEPTR pre-trained without autocontrastive learning are outperformed by sequence alignment-based methods. We anticipate that contrastive learning will be a useful paradigm to decode the rules of TCR specificity.