Contrastive learning of T cell receptor representations

arXiv:2406.06397v1 Announce Type: cross
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 …

abstract advances arxiv bottlenecks challenge computational cs.ai cs.lg data domains immunology language language models ligands prediction pre-training q-bio.bm specificity training type