TCR-ESM: Employing protein language embeddings to predict TCR-peptide-MHC binding

Cognate target identification for T-cell receptors (TCRs) is a significant barrier in T-cell therapy development, which may be overcome by accurately predicting TCR interaction with peptide-bound major histocompatibility complex (pMHC). In this study, we have employed peptide embeddings learned from a large protein language model- Evolutionary Scale Modeling (ESM), to predict TCR-pMHC binding. The TCR-ESM model presented outperforms existing predictors. The complementarity-determining region 3 (CDR3) of the hypervariable TCR is located at the center of the paratope and plays a crucial role in peptide recognition. TCR-ESM trained on paired TCR data with both CDR3α and CDR3β chain information performs significantly better than those trained on data with only CDR3β, suggesting that both TCR chains contribute to specificity, the relative importance however depends on the specific peptide-MHC targeted. The study illuminates the importance of MHC information in TCR-peptide binding which remained inconclusive so far and was thought dependent on the dataset characteristics. TCR-ESM outperforms existing approaches on external datasets, suggesting generalizability. Overall, the potential of deep learning for predicting TCR-pMHC interactions and improving the understanding of factors driving TCR specificity are highlighted. The prediction model is available at http://tcresm.dhanjal-lab.iiitd.edu.in/ as an online tool.

Enhancing TCR specificity predictions by combined pan- and peptide-specific training, loss-scaling, and sequence similarity integration

Predicting the interaction between Major Histocompatibility Complex (MHC) class I-presented peptides and T-cell receptors (TCR) holds significant implications for vaccine development, cancer treatment, and autoimmune disease therapies. However, limited paired-chain TCR data, skewed towards well-studied epitopes, hampers the development of pan-specific machine-learning (ML) models. Leveraging a larger peptide-TCR dataset, we explore various alterations to the ML architectures and training strategies to address data imbalance. This leads to an overall improved performance, particularly for peptides with scant TCR data. However, challenges persist for unseen peptides, especially those distant from training examples. We demonstrate that such ML models can be used to detect potential outliers, which when removed from training, leads to augmented performance. Integrating pan-specific and peptide-specific models alongside with similarity-based predictions, further improves the overall performance, especially when a low false positive rate is desirable. In the context of the IMMREP22 benchmark, this modeling framework attained state-of-the-art performance. Moreover, combining these strategies results in acceptable predictive accuracy for peptides characterized with as little as 15 positive TCRs. This observation places great promise on rapidly expanding the peptide covering of the current models for predicting TCR specificity. The NetTCR 2.2 model incorporating these advances is available on GitHub (https://github.com/mnielLab/NetTCR-2.2) and as a web server at https://services.healthtech.dtu.dk/services/NetTCR-2.2/.

NetTCR-2.1: Lessons and guidance on how to develop models for TCR specificity predictions

T cell receptors (TCR) define the specificity of T cells and are responsible for their interaction with peptide antigen targets presented in complex with major histocompatibility complex (MHC) molecules. Understanding the rules underlying this interaction hence forms the foundation for our understanding of basic adaptive immunology. Over the last decade, efforts have been dedicated to developing assays for high throughput identification of peptide-specific TCRs. Based on such data, several computational methods have been proposed for predicting the TCR-pMHC interaction. The general conclusion from these studies is that the prediction of TCR interactions with MHC-peptide complexes remains highly challenging. Several reasons form the basis for this including scarcity and quality of data, and ill-defined modeling objectives imposed by the high redundancy of the available data. In this work, we propose a framework for dealing with this redundancy, allowing us to address essential questions related to the modeling of TCR specificity including the use of peptide- versus pan-specific models, how to best define negative data, and the performance impact of integrating of CDR1 and 2 loops. Further, we illustrate how and why it is strongly recommended to include simple similarity-based modeling approaches when validating an improved predictive power of machine learning models, and that such validation should include a performance evaluation as a function of "distance" to the training data, to quantify the potential for generalization of the proposed model. The conclusion of the work is that, given current data, TCR specificity is best modeled using peptide-specific approaches, integrating information from all 6 CDR loops, and with negative data constructed from a combination of true and mislabeled negatives. Comparing such machine learning models to similarity-based approaches demonstrated an increased performance gain of the former as the "distance" to the training data was increased; thus demonstrating an improved generalization ability of the machine learning-based approaches. We believe these results demonstrate that the outlined modeling framework and proposed evaluation strategy form a solid basis for investigating the modeling of TCR specificities and that adhering to such a framework will allow for faster progress within the field. The final devolved model, NetTCR-2.1, is available at https://services.healthtech.dtu.dk/service.php?NetTCR-2.1.

Separating the wheat from the chaff: Making sense of Treg heterogeneity for better adoptive cellular therapy

Regulatory T (Treg) cells are essential for immunological tolerance and can be used to suppress unwanted or excessive immune responses through adoptive cellular therapy. It is increasingly clear that many subsets of Treg cells exist, which have different functions and reside in different locations. Treg cell therapies may benefit from tailoring the selected subset to the tissue that must be protected as well as to characteristics of the immune response that must be suppressed, but little attention is given to this topic in current therapies. Here, we will discuss how three major axes of heterogeneity can be discerned among the Treg cell population, which determine function and lineage fidelity. A first axis relates to the developmental route, as Treg cells can be generated from immature T cells in the thymus or from already mature Tconv cells in the immunological periphery. Heterogeneity furthermore stems from activation history (naïve or effector) and location (lymphoid or peripheral tissues). Each of these axes bestows specific properties on Treg cells, which are further refined by additional processes leading to yet further variation. A critical aspect impacting on Treg cell heterogeneity is TCR specificity, which determines when and where Treg cells are generated as well as where they exhibit their effector functions. We will discuss the implications of this heterogeneity and the role of the TCR for the design of next generation adoptive cellular therapy with Treg cells.

Indoctrinating T cells to attack pathogens through homeschooling

Adaptive immunity is predicated on the ability of the T cell repertoire to have pre-existing specificity for the universe of potential pathogens. Recent findings suggest that T cell receptor (TCR)-self-major histocompatibility protein (pMHC) interactions limit autoimmune responses while enhancing T cell response to foreign antigens. We review these findings here, placing them in context of the current understanding of how TCR-self-pMHC interactions regulate T cell activation thresholds, and suggest that TCR-self-pMHC interactions increase the efficiency of the T cell repertoire by giving a competitive advantage to peptide cross-reactive T cells. We propose that self-reactivity and peptide cross-reactivity are controlled by particular CDR3 sequence motifs, which would allow thymic selection to contribute to solving the feat of broad pathogen specificity by exporting T cells that are pre-screened by positive and negative selection for the ability to be 'moderately' peptide cross-reactive.