De novo identification of CD4+ T cell epitopes.

CD4+ T cells recognize peptide antigens presented on class II major histocompatibility complex (MHC-II) molecules to carry out their function. The remarkable diversity of T cell receptor sequences and lack of antigen discovery approaches for MHC-II make profiling the specificities of CD4+ T cells challenging. We have expanded our platform of signaling and antigen-presenting bifunctional receptors to encode MHC-II molecules presenting covalently linked peptides (SABR-IIs) for CD4+ T cell antigen discovery. SABR-IIs can present epitopes to CD4+ T cells and induce signaling upon their recognition, allowing a readable output. Furthermore, the SABR-II design is modular in signaling and deployment to T cells and B cells. Here, we demonstrate that SABR-IIs libraries presenting endogenous and non-contiguous epitopes can be used for antigen discovery in the context of type 1 diabetes. SABR-II libraries provide a rapid, flexible, scalable and versatile approach for de novo identification of CD4+ T cell ligands from single-cell RNA sequencing data using experimental and computational approaches.

Sliding Window INteraction Grammar (SWING): a generalized interaction language model for peptide and protein interactions.

The explosion of sequence data has allowed the rapid growth of protein language models (pLMs). pLMs have now been employed in many frameworks including variant-effect and peptide-specificity prediction. Traditionally, for protein-protein or peptide-protein interactions (PPIs), corresponding sequences are either co-embedded followed by post-hoc integration or the sequences are concatenated prior to embedding. Interestingly, no method utilizes a language representation of the interaction itself. We developed an interaction LM (iLM), which uses a novel language to represent interactions between protein/peptide sequences. Sliding Window Interaction Grammar (SWING) leverages differences in amino acid properties to generate an interaction vocabulary. This vocabulary is the input into a LM followed by a supervised prediction step where the LM's representations are used as features. SWING was first applied to predicting peptide:MHC (pMHC) interactions. SWING was not only successful at generating Class I and Class II models that have comparable prediction to state-of-the-art approaches, but the unique Mixed Class model was also successful at jointly predicting both classes. Further, the SWING model trained only on Class I alleles was predictive for Class II, a complex prediction task not attempted by any existing approach. For de novo data, using only Class I or Class II data, SWING also accurately predicted Class II pMHC interactions in murine models of SLE (MRL/lpr model) and T1D (NOD model), that were validated experimentally. To further evaluate SWING's generalizability, we tested its ability to predict the disruption of specific protein-protein interactions by missense mutations. Although modern methods like AlphaMissense and ESM1b can predict interfaces and variant effects/pathogenicity per mutation, they are unable to predict interaction-specific disruptions. SWING was successful at accurately predicting the impact of both Mendelian mutations and population variants on PPIs. This is the first generalizable approach that can accurately predict interaction-specific disruptions by missense mutations with only sequence information. Overall, SWING is a first-in-class generalizable zero-shot iLM that learns the language of PPIs.