The prediction of epitope recognition by T-cell receptors (TCRs) has seen many advancements in recent years, with several methods now available that can predict recognition for a specific set of epitopes. However, the generic case of evaluating all possible TCR-epitope pairs remains challenging, mainly due to the high diversity of the interacting sequences and the limited amount of currently available training data. In this work, we provide an overview of the current state of this unsolved problem. First, we examine appropriate validation strategies to accurately assess the generalization performance of generic TCR-epitope recognition models when applied to both seen and unseen epitopes. In addition, we present a novel feature representation approach, which we call ImRex (interaction map recognition). This approach is based on the pairwise combination of physicochemical properties of the individual amino acids in the CDR3 and epitope sequences, which provides a convolutional neural network with the combined representation of both sequences. Lastly, we highlight various challenges that are specific to TCR-epitope data and that can adversely affect model performance. These include the issue of selecting negative data, the imbalanced epitope distribution of curated TCR-epitope datasets and the potential exchangeability of TCR alpha and beta chains. Our results indicate that while extrapolation to unseen epitopes remains a difficult challenge, ImRex makes this feasible for a subset of epitopes that are not too dissimilar from the training data. We show that appropriate feature engineering methods and rigorous benchmark standards are required to create and validate TCR-epitope predictive models.

High-throughput T cell receptor (TCR) sequencing allows the characterization of an individual's TCR repertoire and directly queries their immune state. However, it remains a non-trivial task to couple these sequenced TCRs to their antigenic targets. In this paper, we present a novel strategy to annotate full TCR sequence repertoires with their epitope specificities. The strategy is based on a machine learning algorithm to learn the TCR patterns common to the recognition of a specific epitope. These results are then combined with a statistical analysis to evaluate the occurrence of specific epitope-reactive TCR sequences per epitope in repertoire data. In this manner, we can directly study the capacity of full TCR repertoires to target specific epitopes of the relevant vaccines or pathogens. We demonstrate the usability of this approach on three independent datasets related to vaccine monitoring and infectious disease diagnostics by independently identifying the epitopes that are targeted by the TCR repertoire. The developed method is freely available as a web tool for academic use at tcrex.biodatamining.be.

The T-cell receptor is responsible for recognizing potentially harmful epitopes presented on cell surfaces. The binding rules that govern this recognition between receptor and epitope is currently an unsolved problem, yet one of great interest. Several methods have been proposed recently to perform supervised classification of T-cell receptor sequences, but this requires known examples of T-cell sequences for a given epitope. Here we study the viability of various methods to perform unsupervised clustering of distinct T-cell receptor sequences and how these clusters relate to their target epitope. The goal is to provide an overview of the performance of various distance metrics on two large independent T-cell receptor sequence data sets. Our results confirm the presence of structural distinct T-cell groups that target identical epitopes. In addition, we put forward several recommendations to perform T-cell receptor sequence clustering.

The non-responders already showed an activated state of the immune system before vaccination. Furthermore, after vaccination, they exhibited a delayed and partial immune response in comparison to the responders. Our data may indicate that the baseline and untriggered immune system can influence the response upon hepatitis B vaccination.

Current T cell epitope prediction tools are a valuable resource in designing targeted immunogenicity experiments. They typically focus on, and are able to, accurately predict peptide binding and presentation by major histocompatibility complex (MHC) molecules on the surface of antigen-presenting cells. However, recognition of the peptide-MHC complex by a T cell receptor (TCR) is often not included in these tools. We developed a classification approach based on random forest classifiers to predict recognition of a peptide by a T cell receptor and discover patterns that contribute to recognition. We considered two approaches to solve this problem: (1) distinguishing between two sets of TCRs that each bind to a known peptide and (2) retrieving TCRs that bind to a given peptide from a large pool of TCRs. Evaluation of the models on two HIV-1, B*08-restricted epitopes reveals good performance and hints towards structural CDR3 features that can determine peptide immunogenicity. These results are of particular importance as they show that prediction of T cell epitope and T cell epitope recognition based on sequence data is a feasible approach. In addition, the validity of our models not only serves as a proof of concept for the prediction of immunogenic T cell epitopes but also paves the way for more general and high-performing models.

Pathogens of past and current infections have been identified directly by means of PCR or indirectly by measuring a specific immune response (e.g., antibody titration). Using a novel approach, Emerson and colleagues showed that the cytomegalovirus serostatus can also be accurately determined by using a T cell receptor repertoire data mining approach. In this study, we have sequenced the CD4 memory T cell receptor repertoire of a Belgian cohort with known cytomegalovirus serostatus. A random forest classifier was trained on the CMV specific T cell receptor repertoire signature and used to classify individuals in the Belgian cohort. This study shows that the novel approach can be reliably replicated with an equivalent performance as that reported by Emerson and colleagues. Additionally, it provides evidence that the T cell receptor repertoire signature is to a large extent present in the CD4 memory repertoire.

Abstract:28 Current T-cell epitope prediction tools are a valuable resource in designing targeted immunogenicity 29 experiments. They typically focus on, and are able to, accurately predict peptide binding and presentation by 30 major histocompatibility complex (MHC) molecules on the surface of antigen-presenting cells. However, 31 recognition of the peptide-MHC complex by a T-cell receptor is often not included in these tools. We developed 32 a classification approach based on random forest classifiers to predict recognition of a peptide by a T-cell and 33 discover patterns that contribute to recognition. We considered two approaches to solve this problem: (1) 34 distinguishing between two sets of T-cell receptors that each bind to a known peptide and (2) retrieving T-cell 35 receptors that bind to a given peptide from a large pool of T-cell receptors. Evaluation of the models on two 36 HIV-1, B*08-restricted epitopes reveals good performance and hints towards structural CDR3 features that can 37 determine peptide immunogenicity. These results are of particularly importance as they show that prediction of 38 T-cell epitope and T-cell epitope recognition based on sequence data is a feasible approach. In addition, the 39 validity of our models not only serves as a proof of concept for the prediction of immunogenic T-cell epitopes 40 but also paves the way for more general and high performing models.

Multiple myeloma (MM) is a hematological malignancy characterized by plasma cells’ uncontrolled growth. The major barrier in treating MM is the occurrence of primary and acquired therapy resistance to anticancer drugs. Often, this therapy resistance is associated with constitutive hyperactivation of tyrosine kinase signaling. Novel covalent kinase inhibitors, such as the clinically approved BTK inhibitor ibrutinib (IBR) and the preclinical phytochemical withaferin A (WA), have, therefore, gained pharmaceutical interest. Remarkably, WA is more effective than IBR in killing BTK-overexpressing glucocorticoid (GC)-resistant MM1R cells. To further characterize the kinase inhibitor profiles of WA and IBR in GC-resistant MM cells, we applied phosphopeptidome- and transcriptome-specific tyrosine kinome profiling. In contrast to IBR, WA was found to reverse BTK overexpression in GC-resistant MM1R cells. Furthermore, WA-induced cell death involves covalent cysteine targeting of Hinge-6 domain type tyrosine kinases of the kinase cysteinome classification, including inhibition of the hyperactivated BTK. Covalent interaction between WA and BTK could further be confirmed by biotin-based affinity purification and confocal microscopy. Similarly, molecular modeling suggests WA preferably targets conserved cysteines in the Hinge-6 region of the kinase cysteinome classification, favoring inhibition of multiple B-cell receptors (BCR) family kinases. Altogether, we show that WA’s promiscuous inhibition of multiple BTK family tyrosine kinases represents a highly effective strategy to overcome GC-therapy resistance in MM.