Contrastive learning of T cell receptor representations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916430608334848 |
|---|---|
| author | Nagano, Yuta Pyo, Andrew Milighetti, Martina Henderson, James Shawe-Taylor, John Chain, Benny Tiffeau-Mayer, Andreas |
| author_facet | Nagano, Yuta Pyo, Andrew Milighetti, Martina Henderson, James Shawe-Taylor, John Chain, Benny Tiffeau-Mayer, Andreas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_06397 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Contrastive learning of T cell receptor representations Nagano, Yuta Pyo, Andrew Milighetti, Martina Henderson, James Shawe-Taylor, John Chain, Benny Tiffeau-Mayer, Andreas Biomolecules Artificial Intelligence Machine Learning J.3; I.2.7 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. |
| title | Contrastive learning of T cell receptor representations |
| topic | Biomolecules Artificial Intelligence Machine Learning J.3; I.2.7 |
| url | https://arxiv.org/abs/2406.06397 |