Parameters and data files to support the ADAPT immune receptor design pipeline and paper

Datafiles to support the ADAPT design pipeline and paper.

Targeting peptide–MHC complexes with designed T cell receptors and antibodies

Amir Motmaen, Kevin M. Jude, Nan Wang, Anastasia Minervina, David Feldman, Mauriz A. Lichtenstein, Abishai Ebenezer, Colin Correnti, Paul G. Thomas, K. Christopher Garcia*, David Baker*, Philip Bradley*

(*- corresponding authors)

https://www.biorxiv.org/content/10.1101/2025.11.19.689381v1

Class I major histocompatibility complexes (MHCs), expressed on the surface of all nucleated cells, present peptides derived from intracellular proteins for surveillance by T cells. The precise recognition of foreign or mutated peptide–MHC (pMHC) complexes by T cell receptors (TCRs) is central to immune defense against pathogens and tumors. Although patient-derived TCRs specific for cancer-associated antigens have been used to engineer tumor-targeting therapies, their reactivity toward self- or near-self antigens may be constrained by negative selection in the thymus. Here, we introduce a structure-based deep learning framework, ADAPT (Antigen-receptor Design Against Peptide-MHC Targets), for the design of TCRs and antibodies that bind to pMHC targets of interest. We evaluate the ADAPT pipeline by designing and characterizing TCRs and antibodies against a diverse panel of pMHCs. Cryogenic electron microscopy structures of two designed antibodies bound to their respective pMHC targets demonstrate atomic-level accuracy at the recognition interface, supporting the robustness of our structure-based approach. Computationally designed TCRs and antibodies targeting pMHC complexes could enable a broad range of therapeutic applications, from cancer immunotherapy to autoimmune disease treatment, and insights gained from TCR–pMHC design should advance predictive understanding of TCR specificity with implications for basic immunology and clinical diagnostics.

Special thanks to Joe Watson and Nate Bennett for help with the fine-tuned RFab parameters (https://github.com/RosettaCommons/RFantibody), to the Alphafold2 developers for making their code and parameter sets freely available (https://github.com/google-deepmind/alphafold), to the creators of the SAbDab database (https://opig.stats.ox.ac.uk/webapps/sabdab-sabpred/sabdab) for sharing parsed antibody information, and to all the structural biologists whose work (https://www.rcsb.org/) makes structure-based approaches like this possible.

Please contact Phil Bradley with questions: pbradley at fredhutch dot org