Reproduce “Contrastive learning of T cell receptor representations” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yuta Nagano, Andrew Pyo, Martina Milighetti, James Henderson, John Shawe-Taylor, Benny Chain, Andreas Tiffeau-Mayer
SCEPTR learns T cell receptor representations for few-shot prediction of peptide–MHC specificity. Alongside masked-language modeling, it uses contrastive learning to bring two corrupted views of the same receptor closer. On six well-sampled pMHCs, it matched or exceeded TCRdist; at 200 references, it scored higher on five of six, without decisive statistical evidence, so transfer to unseen ligands remains unestablished.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.