Predicting recognition between T cell receptors and epitopes with TCRGP

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.

epiTCR-KDA: knowledge distillation model on dihedral angles for TCR-peptide prediction

Motivation

The prediction of the T-cell receptor (TCR) and antigen bindings is crucial for advancements in immunotherapy. However, most current TCR-peptide interaction predictors struggle to perform well on unseen data. This limitation may stem from the conventional use of TCR and/or peptide sequences as input, which may not adequately capture their structural characteristics. Therefore, incorporating the structural information of TCRs and peptides into the prediction model is necessary to improve its generalizability.

Results

We developed epiTCR-KDA (KDA stands for Knowledge Distillation model on Dihedral Angles), a new predictor of TCR-peptide binding that utilizes the dihedral angles between the residues of the peptide and the TCR as a structural descriptor. This structural information was integrated into a knowledge distillation model to enhance its generalizability. epiTCR-KDA demonstrated competitive prediction performance, with an area under the curve (AUC) of 1.00 for seen data and AUC of 0.91 for unseen data. On public datasets, epiTCR-KDA consistently outperformed other predictors, maintaining a median AUC of 0.93. Further analysis of epiTCR-KDA revealed that the cosine similarity of the dihedral angle vectors between the unseen testing data and training data is crucial for its stable performance. In conclusion, our epiTCR-KDA model represents a significant step forward in developing a highly effective pipeline for antigen-based immunotherapy.

Availability and implementation

epiTCR-KDA is available on GitHub (https://github.com/ddiem-ri-4D/epiTCR-KDA).

tcrBLOSUM: an amino acid substitution matrix for sensitive alignment of distant epitope-specific TCRs

Deciphering the specificity of T-cell receptor (TCR) repertoires is crucial for monitoring adaptive immune responses and developing targeted immunotherapies and vaccines. To elucidate the specificity of previously unseen TCRs, many methods employ the BLOSUM62 matrix to find TCRs with similar amino acid (AA) sequences. However, while BLOSUM62 reflects the AA substitutions within conserved regions of proteins with similar functions, the remarkable diversity of TCRs means that both TCRs with similar and dissimilar sequences can bind the same epitope. Therefore, reliance on BLOSUM62 may bias detection towards epitope-specific TCRs with similar biochemical properties, overlooking those with more diverse AA compositions. In this study, we introduce tcrBLOSUMa and tcrBLOSUMb, specialized AA substitution matrices for CDR3 alpha and CDR3 beta TCR chains, respectively. The matrices reflect AA frequencies and variations occurring within TCRs that bind the same epitope, revealing that both CDR3 alpha and CDR3 beta display tolerance to a wide range of AA substitutions and differ noticeably from the standard BLOSUM62. By accurately aligning distant TCRs employing tcrBLOSUMb, we were able to improve clustering performance and capture a large number of epitope-specific TCRs with diverse AA compositions and physicochemical profiles overlooked by BLOSUM62. Utilizing both the general BLOSUM62 and specialized tcrBLOSUM matrices in existing computational tools will broaden the range of TCRs that can be associated with their cognate epitopes, thereby enhancing TCR repertoire analysis.

Meta learning for mutant HLA class I epitope immunogenicity prediction to accelerate cancer clinical immunotherapy

Accurate prediction of binding between human leukocyte antigen (HLA) class I molecules and antigenic peptide segments is a challenging task and a key bottleneck in personalized immunotherapy for cancer. Although existing prediction tools have demonstrated significant results using established datasets, most can only predict the binding affinity of antigenic peptides to HLA and do not enable the immunogenic interpretation of new antigenic epitopes. This limitation results from the training data for the computational models relying heavily on a large amount of peptide-HLA (pHLA) eluting ligand data, in which most of the candidate epitopes lack immunogenicity. Here, we propose an adaptive immunogenicity prediction model, named MHLAPre, which is trained on the large-scale MS-derived HLA I eluted ligandome (mostly presented by epitopes) that are immunogenic. Allele-specific and pan-allelic prediction models are also provided for endogenous peptide presentation. Using a meta-learning strategy, MHLAPre rapidly assessed HLA class I peptide affinities across the whole pHLA pairs and accurately identified tumor-associated endogenous antigens. During the process of adaptive immune response of T-cells, pHLA-specific binding in the antigen presentation is only a pre-task for CD8+ T-cell recognition. The key factor in activating the immune response is the interaction between pHLA complexes and T-cell receptors (TCRs). Therefore, we performed transfer learning on the pHLA model using the pHLA-TCR dataset. In pHLA binding task, MHLAPre demonstrated significant improvement in identifying neoepitope immunogenicity compared with five state-of-the-art models, proving its effectiveness and robustness. After transfer learning of the pHLA-TCR data, MHLAPre also exhibited relatively superior performance in revealing the mechanism of immunotherapy. MHLAPre is a powerful tool to identify neoepitopes that can interact with TCR and induce immune responses. We believe that the proposed method will greatly contribute to clinical immunotherapy, such as anti-tumor immunity, tumor-specific T-cell engineering, and personalized tumor vaccine.

Predicting T cell receptor functionality against mutant epitopes

Cancer cells and pathogens can evade T cell receptors (TCRs) via mutations in immunogenic epitopes. TCR cross-reactivity (i.e., recognition of multiple epitopes with sequence similarities) can counteract such escape but may cause severe side effects in cell-based immunotherapies through targeting self-antigens. To predict the effect of epitope point mutations on T cell functionality, we here present the random forest-based model Predicting T Cell Epitope-Specific Activation against Mutant Versions (P-TEAM). P-TEAM was trained and tested on three datasets with TCR responses to single-amino-acid mutations of the model epitope SIINFEKL, the tumor neo-epitope VPSVWRSSL, and the human cytomegalovirus antigen NLVPMVATV, totaling 9,690 unique TCR-epitope interactions. P-TEAM was able to accurately classify T cell reactivities and quantitatively predict T cell functionalities for unobserved single-point mutations and unseen TCRs. Overall, P-TEAM provides an effective computational tool to study T cell responses against mutated epitopes.

Make or break: The influence of expected challenges and rewards on the motivation and experience associated with cognitive effort exertion

Challenging goals can induce harder work but also greater stress, in turn potentially undermining goal achievement. We sought to examine how mental effort and subjective experiences thereof interact as a function of challenge level and the size of the incentives at stake. Participants performed a task that rewarded individual units of effort investment (correctly performed Stroop trials) but only if they met a threshold number of correct trials within a fixed time interval (challenge level). We varied this challenge level (Study 1, N = 40), and the rewards at stake (Study 2, N = 79), and measured variability in task performance and self-reported affect across task intervals. Greater challenge and higher rewards facilitated greater effort investment but also induced greater stress, while higher rewards (and lower challenge) simultaneously induced greater positive affect. Within intervals, we observed an initial speed up then slowdown in performance, which could reflect dynamic reconfiguration of control. Collectively, these findings further our understanding of the influence of task demands and incentives on mental effort exertion and wellbeing.

Computational Methods for Predicting Key Interactions in T Cell-Mediated Adaptive Immunity

The adaptive immune system recognizes pathogen- and cancer-specific features and is endowed with memory, enabling it to respond quickly and efficiently to repeated encounters with the same antigens. T cells play a central role in the adaptive immune system by directly targeting intracellular pathogens and helping to activate B cells to secrete antibodies. Several fundamental protein interactions-including those between major histocompatibility complex (MHC) proteins and antigen-derived peptides as well as between T cell receptors and peptide-MHC complexes-underlie the ability of T cells to recognize antigens with great precision. Computational approaches to predict these interactions are increasingly being used for medically relevant applications, including vaccine design and prediction of patient response to cancer immunotherapies. We provide computational researchers with an accessible introduction to the adaptive immune system, review computational approaches to predict the key protein interactions underlying T cell-mediated adaptive immunity, and highlight remaining challenges.

TULIP: A transformer-based unsupervised language model for interacting peptides and T cell receptors that generalizes to unseen epitopes

The accurate prediction of binding between T cell receptors (TCR) and their cognate epitopes is key to understanding the adaptive immune response and developing immunotherapies. Current methods face two significant limitations: the shortage of comprehensive high-quality data and the bias introduced by the selection of the negative training data commonly used in the supervised learning approaches. We propose a method, Transformer-based Unsupervised Language model for Interacting Peptides and T cell receptors (TULIP), that addresses both limitations by leveraging incomplete data and unsupervised learning and using the transformer architecture of language models. Our model is flexible and integrates all possible data sources, regardless of their quality or completeness. We demonstrate the existence of a bias introduced by the sampling procedure used in previous supervised approaches, emphasizing the need for an unsupervised approach. TULIP recognizes the specific TCRs binding an epitope, performing well on unseen epitopes. Our model outperforms state-of-the-art models and offers a promising direction for the development of more accurate TCR epitope recognition models.

Somatic mutations associate with clonal expansion of CD8+ T cells

Somatic mutations in T cells can cause cancer but also have implications for immunological diseases and cell therapies. The mutation spectrum in nonmalignant T cells is unclear. Here, we examined somatic mutations in CD4+ and CD8+ T cells from 90 patients with hematological and immunological disorders and used T cell receptor (TCR) and single-cell sequencing to link mutations with T cell expansions and phenotypes. CD8+ cells had a higher mutation burden than CD4+ cells. Notably, the biggest variant allele frequency (VAF) of non-synonymous variants was higher than synonymous variants in CD8+ T cells, indicating non-random occurrence. The non-synonymous VAF in CD8+ T cells strongly correlated with the TCR frequency, but not age. We identified mutations in pathways essential for T cell function and often affected lymphoid neoplasia. Single-cell sequencing revealed cytotoxic TEMRA phenotypes of mutated T cells. Our findings suggest that somatic mutations contribute to CD8+ T cell expansions without malignant transformation.

HeteroTCR: A heterogeneous graph neural network-based method for predicting peptide-TCR interaction

Identifying interactions between T-cell receptors (TCRs) and immunogenic peptides holds profound implications across diverse research domains and clinical scenarios. Unsupervised clustering models (UCMs) cannot predict peptide-TCR binding directly, while supervised predictive models (SPMs) often face challenges in identifying antigens previously unencountered by the immune system or possessing limited TCR binding repertoires. Therefore, we propose HeteroTCR, an SPM based on Heterogeneous Graph Neural Network (GNN), to accurately predict peptide-TCR binding probabilities. HeteroTCR captures within-type (TCR-TCR or peptide-peptide) similarity information and between-type (peptide-TCR) interaction insights for predictions on unseen peptides and TCRs, surpassing limitations of existing SPMs. Our evaluation shows HeteroTCR outperforms state-of-the-art models on independent datasets. Ablation studies and visual interpretation underscore the Heterogeneous GNN module's critical role in enhancing HeteroTCR's performance by capturing pivotal binding process features. We further demonstrate the robustness and reliability of HeteroTCR through validation using single-cell datasets, aligning with the expectation that pMHC-TCR complexes with higher predicted binding probabilities correspond to increased binding fractions.

Transformers meets neoantigen detection: a systematic literature review

Cancer immunology offers a new alternative to traditional cancer treatments, such as radiotherapy and chemotherapy. One notable alternative is the development of personalized vaccines based on cancer neoantigens. Moreover, Transformers are considered a revolutionary development in artificial intelligence with a significant impact on natural language processing (NLP) tasks and have been utilized in proteomics studies in recent years. In this context, we conducted a systematic literature review to investigate how Transformers are applied in each stage of the neoantigen detection process. Additionally, we mapped current pipelines and examined the results of clinical trials involving cancer vaccines.

Artificial intelligence and neoantigens: paving the path for precision cancer immunotherapy

Cancer immunotherapy has witnessed rapid advancement in recent years, with a particular focus on neoantigens as promising targets for personalized treatments. The convergence of immunogenomics, bioinformatics, and artificial intelligence (AI) has propelled the development of innovative neoantigen discovery tools and pipelines. These tools have revolutionized our ability to identify tumor-specific antigens, providing the foundation for precision cancer immunotherapy. AI-driven algorithms can process extensive amounts of data, identify patterns, and make predictions that were once challenging to achieve. However, the integration of AI comes with its own set of challenges, leaving space for further research. With particular focus on the computational approaches, in this article we have explored the current landscape of neoantigen prediction, the fundamental concepts behind, the challenges and their potential solutions providing a comprehensive overview of this rapidly evolving field.

GTE: a graph learning framework for prediction of T-cell receptors and epitopes binding specificity

The interaction between T-cell receptors (TCRs) and peptides (epitopes) presented by major histocompatibility complex molecules (MHC) is fundamental to the immune response. Accurate prediction of TCR-epitope interactions is crucial for advancing the understanding of various diseases and their prevention and treatment. Existing methods primarily rely on sequence-based approaches, overlooking the inherent topology structure of TCR-epitope interaction networks. In this study, we present $GTE$, a novel heterogeneous Graph neural network model based on inductive learning to capture the topological structure between TCRs and Epitopes. Furthermore, we address the challenge of constructing negative samples within the graph by proposing a dynamic edge update strategy, enhancing model learning with the nonbinding TCR-epitope pairs. Additionally, to overcome data imbalance, we adapt the Deep AUC Maximization strategy to the graph domain. Extensive experiments are conducted on four public datasets to demonstrate the superiority of exploring underlying topological structures in predicting TCR-epitope interactions, illustrating the benefits of delving into complex molecular networks. The implementation code and data are available at https://github.com/uta-smile/GTE.

VitTCR: A deep learning method for peptide recognition prediction

This study introduces VitTCR, a predictive model based on the vision transformer (ViT) architecture, aimed at identifying interactions between T cell receptors (TCRs) and peptides, crucial for developing cancer immunotherapies and vaccines. VitTCR converts TCR-peptide interactions into numerical AtchleyMaps using Atchley factors for prediction, achieving AUROC (0.6485) and AUPR (0.6295) values. Benchmark analysis indicates VitTCR's performance is comparable to other models, with further comparative studies suggested to understand its effectiveness in varied contexts. Additionally, integrating a positional bias weight matrix (PBWM), derived from amino acid contact probabilities in structurally resolved pMHC-TCR complexes, slightly improves VitTCR's accuracy. The model's predictions show weak yet statistically significant correlations with immunological factors like T cell clonal expansion and activation percentages, underscoring the biological relevance of VitTCR's predictive capabilities. VitTCR emerges as a valuable computational tool for predicting TCR-peptide interactions, offering insights for immunotherapy and vaccine development.

The physiological interactome of TCR-like antibody therapeutics in human tissues

Selective binding of TCR-like antibodies that target a single tumour-specific peptide antigen presented by human leukocyte antigens (HLA) is the absolute prerequisite for their therapeutic suitability and patient safety. To date, selectivity assessment has been limited to peptide library screening and predictive modeling. We developed an experimental platform to de novo identify interactomes of TCR-like antibodies directly in human tissues using mass spectrometry. As proof of concept, we confirm the target epitope of a MAGE-A4-specific TCR-like antibody. We further determine cross-reactive peptide sequences for ESK1, a TCR-like antibody with known off-target activity, in human liver tissue. We confirm off-target-induced T cell activation and ESK1-mediated liver spheroid killing. Off-target sequences feature an amino acid motif that allows a structural groove-coordination mimicking that of the target peptide, therefore allowing the interaction with the engager molecule. We conclude that our strategy offers an accurate, scalable route for evaluating the non-clinical safety profile of TCR-like antibody therapeutics prior to first-in-human clinical application.

Deep learning predictions of TCR-epitope interactions reveal epitope-specific chains in dual alpha T cells

T cells have the ability to eliminate infected and cancer cells and play an essential role in cancer immunotherapy. T cell activation is elicited by the binding of the T cell receptor (TCR) to epitopes displayed on MHC molecules, and the TCR specificity is determined by the sequence of its α and β chains. Here, we collect and curate a dataset of 17,715 αβTCRs interacting with dozens of class I and class II epitopes. We use this curated data to develop MixTCRpred, an epitope-specific TCR-epitope interaction predictor. MixTCRpred accurately predicts TCRs recognizing several viral and cancer epitopes. MixTCRpred further provides a useful quality control tool for multiplexed single-cell TCR sequencing assays of epitope-specific T cells and pinpoints a substantial fraction of putative contaminants in public databases. Analysis of epitope-specific dual α T cells demonstrates that MixTCRpred can identify α chains mediating epitope recognition. Applying MixTCRpred to TCR repertoires from COVID-19 patients reveals enrichment of clonotypes predicted to bind an immunodominant SARS-CoV-2 epitope. Overall, MixTCRpred provides a robust tool to predict TCRs interacting with specific epitopes and interpret TCR-sequencing data from both bulk and epitope-specific T cells.

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/.

APTAnet: an atom-level peptide-TCR interaction affinity prediction model

The prediction of affinity between TCRs and peptides is crucial for the further development of TIL (Tumor-Infiltrating Lymphocytes) immunotherapy. Inspired by the broader research of drug-protein interaction (DPI), we propose an atom-level peptide-TCR interaction (PTI) affinity prediction model APTAnet using natural language processing methods. APTAnet model achieved an average ROC-AUC and PR-AUC of 0.893 and 0.877, respectively, in ten-fold cross-validation on 25,675 pairs of PTI data. Furthermore, experimental results on an independent test set from the McPAS database showed that APTAnet outperformed the current mainstream models. Finally, through the validation on 11 cases of real tumor patient data, we found that the APTAnet model can effectively identify tumor peptides and screen tumor-specific TCRs.

Development and use of machine learning algorithms in vaccine target selection

Computer-aided discovery of vaccine targets has become a cornerstone of rational vaccine design. In this article, I discuss how Machine Learning (ML) can inform and guide key computational steps in rational vaccine design concerned with the identification of B and T cell epitopes and correlates of protection. I provide examples of ML models, as well as types of data and predictions for which they are built. I argue that interpretable ML has the potential to improve the identification of immunogens also as a tool for scientific discovery, by helping elucidate the molecular processes underlying vaccine-induced immune responses. I outline the limitations and challenges in terms of data availability and method development that need to be addressed to bridge the gap between advances in ML predictions and their translational application to vaccine design.

Single-cell analysis of immune recognition in chronic myeloid leukemia patients following tyrosine kinase inhibitor discontinuation

Immunological control of residual leukemia cells is thought to occur in patients with chronic myeloid leukemia (CML) that maintain treatment-free remission (TFR) following tyrosine kinase inhibitor (TKI) discontinuation. To study this, we analyzed 55 single-cell RNA and T cell receptor (TCR) sequenced samples (scRNA+TCRαβ-seq) from patients with CML (n = 13, N = 25), other cancers (n = 28), and healthy (n = 7). The high number and active phenotype of natural killer (NK) cells in CML separated them from healthy and other cancers. Most NK cells in CML belonged to the active CD56dim cluster with high expression of GZMA/B, PRF1, CCL3/4, and IFNG, with interactions with leukemic cells via inhibitory LGALS9-TIM3 and PVR-TIGIT interactions. Accordingly, upregulation of LGALS9 was observed in CML target cells and TIM3 in NK cells when co-cultured together. Additionally, we created a classifier to identify TCRs targeting leukemia-associated antigen PR1 and quantified anti-PR1 T cells in 90 CML and 786 healthy TCRβ-sequenced samples. Anti-PR1 T cells were more prevalent in CML, enriched in bone marrow samples, and enriched in the mature, cytotoxic CD8 + TEMRA cluster, especially in a patient maintaining TFR. Our results highlight the role of NK cells and anti-PR1 T cells in anti-leukemic immune responses in CML.

pan-MHC and cross-Species Prediction of T Cell Receptor-Antigen Binding

Profiling the binding of T cell receptors (TCRs) of T cells to antigenic peptides presented by MHC proteins is one of the most important unsolved problems in modern immunology. Experimental methods to probe TCR-antigen interactions are slow, labor-intensive, costly, and yield moderate throughput. To address this problem, we developed pMTnet-omni, an Artificial Intelligence (AI) system based on hybrid protein sequence and structure information, to predict the pairing of TCRs of αβ T cells with peptide-MHC complexes (pMHCs). pMTnet-omni is capable of handling peptides presented by both class I and II pMHCs, and capable of handling both human and mouse TCR-pMHC pairs, through information sharing enabled this hybrid design. pMTnet-omni achieves a high overall Area Under the Curve of Receiver Operator Characteristics (AUROC) of 0.888, which surpasses competing tools by a large margin. We showed that pMTnet-omni can distinguish binding affinity of TCRs with similar sequences. Across a range of datasets from various biological contexts, pMTnet-omni characterized the longitudinal evolution and spatial heterogeneity of TCR-pMHC interactions and their functional impact. We successfully developed a biomarker based on pMTnet-omni for predicting immune-related adverse events of immune checkpoint inhibitor (ICI) treatment in a cohort of 57 ICI-treated patients. pMTnet-omni represents a major advance towards developing a clinically usable AI system for TCR-pMHC pairing prediction that can aid the design and implementation of TCR-based immunotherapeutics.

GGNpTCR: A Generative Graph Structure Neural Network for Predicting Immunogenic Peptides for T-cell Immune Response

Identifying the interactions between T-cell receptor (TCRs) and human antigens is a crucial step in developing new vaccines, diagnostics, and immunotherapy. Current methods primarily focus on learning binding patterns from known TCR binding repertoires by using sequence information alone without considering the binding specificity of new antigens or exogenous peptides that have not appeared in the training set. Furthermore, the spatial structure of antigens plays a critical role in immune studies and immunotherapy, which should be addressed properly in the identification of interacting TCR-antigen pairs. In this study, we introduced a novel deep learning framework based on generative graph structures, GGNpTCR, for predicting interactions between TCR and peptides from sequence information. Results of real data analysis indicate that our model achieved excellent prediction for new antigens unseen in the training data set, making significant improvements compared to existing methods. We also applied the model to a large COVID-19 data set with no antigens in the training data set, and the improvement was also significant. Furthermore, through incorporation of additional supervised mechanisms, GGNpTCR demonstrated the ability to precisely forecast the locations of peptide-TCR interactions within 3D configurations. This enhancement substantially improved the model's interpretability. In summary, based on the performance on multiple data sets, GGNpTCR has made significant progress in terms of performance, universality, and interpretability.

EPIC-TRACE: predicting TCR binding to unseen epitopes using attention and contextualized embeddings

MOTIVATION

T cells play an essential role in adaptive immune system to fight pathogens and cancer but may also give rise to autoimmune diseases. The recognition of a peptide-MHC (pMHC) complex by a T cell receptor (TCR) is required to elicit an immune response. Many machine learning models have been developed to predict the binding, but generalizing predictions to pMHCs outside the training data remains challenging.

RESULTS

We have developed a new machine learning model that utilizes information about the TCR from both α and β chains, epitope sequence, and MHC. Our method uses ProtBERT embeddings for the amino acid sequences of both chains and the epitope, as well as convolution and multi-head attention architectures. We show the importance of each input feature as well as the benefit of including epitopes with only a few TCRs to the training data. We evaluate our model on existing databases and show that it compares favorably against other state-of-the-art models.

AVAILABILITY AND IMPLEMENTATION

https://github.com/DaniTheOrange/EPIC-TRACE.

Determining epitope specificity of T-cell receptors with transformers

SUMMARY

T-cell receptors (TCRs) on T cells recognize and bind to epitopes presented by the major histocompatibility complex in case of an infection or cancer. However, the high diversity of TCRs, as well as their unique and complex binding mechanisms underlying epitope recognition, make it difficult to predict the binding between TCRs and epitopes. Here, we present the utility of transformers, a deep learning strategy that incorporates an attention mechanism that learns the informative features, and show that these models pre-trained on a large set of protein sequences outperform current strategies. We compared three pre-trained auto-encoder transformer models (ProtBERT, ProtAlbert, and ProtElectra) and one pre-trained auto-regressive transformer model (ProtXLNet) to predict the binding specificity of TCRs to 25 epitopes from the VDJdb database (human and murine). Two additional modifications were performed to incorporate gene usage of the TCRs in the four transformer models. Of all 12 transformer implementations (four models with three different modifications), a modified version of the ProtXLNet model could predict TCR-epitope pairs with the highest accuracy (weighted F1 score 0.55 simultaneously considering all 25 epitopes). The modification included additional features representing the gene names for the TCRs. We also showed that the basic implementation of transformers outperformed the previously available methods, i.e. TCRGP, TCRdist, and DeepTCR, developed for the same biological problem, especially for the hard-to-classify labels. We show that the proficiency of transformers in attention learning can be made operational in a complex biological setting like TCR binding prediction. Further ingenuity in utilizing the full potential of transformers, either through attention head visualization or introducing additional features, can extend T-cell research avenues.

AVAILABILITY AND IMPLEMENTATION

Data and code are available on https://github.com/InduKhatri/tcrformer.

Training of epitope-TCR prediction models with healthy donor-derived cancer-specific T cells

Discovery of epitope-specific T-cell receptors (TCRs) for cancer therapies is a time consuming and expensive procedure that usually requires a large amount of patient cells. To maximize information from and minimize the need of precious samples in cancer research, prediction models have been developed to identify in silico epitope-specific TCRs. In this chapter, we provide a step-by-step protocol to train a prediction model using the user-friendly TCRex webtool for the nearly universal tumor-associated antigen Wilms' tumor 1 (WT1)-specific TCR repertoire. WT1 is a self-antigen overexpressed in numerous solid and hematological malignancies with a high clinical relevance. Training of computational models starts from a list of known epitope-specific TCRs which is often not available for new cancer epitopes. Therefore, we describe a workflow to assemble a training data set consisting of TCR sequences obtained from WT137-45-reactive CD8 T cell clones expanded and sorted from healthy donor peripheral blood mononuclear cells.

Quantitative approaches for decoding the specificity of the human T cell repertoire

T cell receptor (TCR)-peptide-major histocompatibility complex (pMHC) interactions play a vital role in initiating immune responses against pathogens, and the specificity of TCRpMHC interactions is crucial for developing optimized therapeutic strategies. The advent of high-throughput immunological and structural evaluation of TCR and pMHC has provided an abundance of data for computational approaches that aim to predict favorable TCR-pMHC interactions. Current models are constructed using information on protein sequence, structures, or a combination of both, and utilize a variety of statistical learning-based approaches for identifying the rules governing specificity. This review examines the current theoretical, computational, and deep learning approaches for identifying TCR-pMHC recognition pairs, placing emphasis on each method's mathematical approach, predictive performance, and limitations.

Can we predict T cell specificity with digital biology and machine learning?

Recent advances in machine learning and experimental biology have offered breakthrough solutions to problems such as protein structure prediction that were long thought to be intractable. However, despite the pivotal role of the T cell receptor (TCR) in orchestrating cellular immunity in health and disease, computational reconstruction of a reliable map from a TCR to its cognate antigens remains a holy grail of systems immunology. Current data sets are limited to a negligible fraction of the universe of possible TCR-ligand pairs, and performance of state-of-the-art predictive models wanes when applied beyond these known binders. In this Perspective article, we make the case for renewed and coordinated interdisciplinary effort to tackle the problem of predicting TCR-antigen specificity. We set out the general requirements of predictive models of antigen binding, highlight critical challenges and discuss how recent advances in digital biology such as single-cell technology and machine learning may provide possible solutions. Finally, we describe how predicting TCR specificity might contribute to our understanding of the broader puzzle of antigen immunogenicity.

BERTrand-peptide:TCR binding prediction using Bidirectional Encoder Representations from Transformers augmented with random TCR pairing

MOTIVATION

The advent of T-cell receptor (TCR) sequencing experiments allowed for a significant increase in the amount of peptide:TCR binding data available and a number of machine-learning models appeared in recent years. High-quality prediction models for a fixed epitope sequence are feasible, provided enough known binding TCR sequences are available. However, their performance drops significantly for previously unseen peptides.

RESULTS

We prepare the dataset of known peptide:TCR binders and augment it with negative decoys created using healthy donors' T-cell repertoires. We employ deep learning methods commonly applied in Natural Language Processing to train part a peptide:TCR binding model with a degree of cross-peptide generalization (0.69 AUROC). We demonstrate that BERTrand outperforms the published methods when evaluated on peptide sequences not used during model training.

AVAILABILITY AND IMPLEMENTATION

The datasets and the code for model training are available at https://github.com/SFGLab/bertrand.

Immunologic Characterization and T cell Receptor Repertoires of Expanded Tumor-infiltrating Lymphocytes in Patients with Renal Cell Carcinoma

The successful use of expanded tumor-infiltrating lymphocytes (TIL) in adoptive TIL therapies has been reported, but the effects of the TIL expansion, immunophenotype, function, and T cell receptor (TCR) repertoire of the infused products relative to the tumor microenvironment (TME) are not well understood. In this study, we analyzed the tumor samples (n = 58) from treatment-naïve patients with renal cell carcinoma (RCC), "pre-rapidly expanded" TILs (pre-REP TIL, n = 15) and "rapidly expanded" TILs (REP TIL, n = 25) according to a clinical-grade TIL production protocol, with single-cell RNA (scRNA)+TCRαβ-seq (TCRαβ sequencing), TCRβ-sequencing (TCRβ-seq), and flow cytometry. REP TILs encompassed a greater abundance of CD4⁺ than CD8⁺ T cells, with increased LAG-3 and low PD-1 expressions in both CD4⁺ and CD8⁺ T cell compartments compared with the pre-REP TIL and tumor T cells. The REP protocol preferentially expanded small clones of the CD4⁺ phenotype (CD4, IL7R, KLRB1) in the TME, indicating that the largest exhausted T cell clones in the tumor do not expand during the expansion protocol. In addition, by generating a catalog of RCC-associated TCR motifs from >1,000 scRNA+TCRαβ-seq and TCRβ-seq RCC, healthy and other cancer sample cohorts, we quantified the RCC-associated TCRs from the expansion protocol. Unlike the low-remaining amount of anti-viral TCRs throughout the expansion, the quantity of the RCC-associated TCRs was high in the tumors and pre-REP TILs but decreased in the REP TILs. Our results provide an in-depth understanding of the origin, phenotype, and TCR specificity of RCC TIL products, paving the way for a more rationalized production of TILs.

Significance

TILs are a heterogenous group of immune cells that recognize and attack the tumor, thus are utilized in various clinical trials. In our study, we explored the TILs in patients with kidney cancer by expanding the TILs using a clinical-grade protocol, as well as observed their characteristics and ability to recognize the tumor using in-depth experimental and computational tools.

A current and future perspective on T cell receptor repertoire profiling

T cell receptors (TCR) play a vital role in the immune system's ability to recognize and respond to foreign antigens, relying on the highly polymorphic rearrangement of TCR genes. The recognition of autologous peptides by adaptive immunity may lead to the development and progression of autoimmune diseases. Understanding the specific TCR involved in this process can provide insights into the autoimmune process. RNA-seq (RNA sequencing) is a valuable tool for studying TCR repertoires by providing a comprehensive and quantitative analysis of the RNA transcripts. With the development of RNA technology, transcriptomic data must provide valuable information to model and predict TCR and antigen interaction and, more importantly, identify or predict neoantigens. This review provides an overview of the application and development of bulk RNA-seq and single-cell (SC) RNA-seq to examine the TCR repertoires. Furthermore, discussed here are bioinformatic tools that can be applied to study the structural biology of peptide/TCR/MHC (major histocompatibility complex) and predict antigenic epitopes using advanced artificial intelligence tools.

epiTCR: a highly sensitive predictor for TCR-peptide binding

MOTIVATION

Predicting the binding between T-cell receptor (TCR) and peptide presented by human leucocyte antigen molecule is a highly challenging task and a key bottleneck in the development of immunotherapy. Existing prediction tools, despite exhibiting good performance on the datasets they were built with, suffer from low true positive rates when used to predict epitopes capable of eliciting T-cell responses in patients. Therefore, an improved tool for TCR-peptide prediction built upon a large dataset combining existing publicly available data is still needed.

RESULTS

We collected data from five public databases (IEDB, TBAdb, VDJdb, McPAS-TCR, and 10X) to form a dataset of >3 million TCR-peptide pairs, 3.27% of which were binding interactions. We proposed epiTCR, a Random Forest-based method dedicated to predicting the TCR-peptide interactions. epiTCR used simple input of TCR CDR3β sequences and antigen sequences, which are encoded by flattened BLOSUM62. epiTCR performed with area under the curve (0.98) and higher sensitivity (0.94) than other existing tools (NetTCR, Imrex, ATM-TCR, and pMTnet), while maintaining comparable prediction specificity (0.9). We identified seven epitopes that contributed to 98.67% of false positives predicted by epiTCR and exerted similar effects on other tools. We also demonstrated a considerable influence of peptide sequences on prediction, highlighting the need for more diverse peptides in a more balanced dataset. In conclusion, epiTCR is among the most well-performing tools, thanks to the use of combined data from public sources and its use will contribute to the quest in identifying neoantigens for precision cancer immunotherapy.

AVAILABILITY AND IMPLEMENTATION

epiTCR is available on GitHub (https://github.com/ddiem-ri-4D/epiTCR).

Single-cell characterization of anti-LAG-3 and anti-PD-1 combination treatment in patients with melanoma

BackgroundRelatlimab plus nivolumab (anti-lymphocyte-activation gene 3 plus anti-programmed death 1 [anti-LAG-3+anti-PD-1]) has been approved by the FDA as a first-line therapy for stage III/IV melanoma, but its detailed effect on the immune system is unknown.MethodsWe evaluated blood samples from 40 immunotherapy-naive or prior immunotherapy-refractory patients with metastatic melanoma treated with anti-LAG-3+anti-PD-1 in a phase I trial using single-cell RNA and T cell receptor sequencing (scRNA+TCRαβ-Seq) combined with other multiomics profiling.ResultsThe highest LAG3 expression was noted in NK cells, Tregs, and CD8+ T cells, and these cell populations underwent the most significant changes during the treatment. Adaptive NK cells were enriched in responders and underwent profound transcriptomic changes during the therapy, resulting in an active phenotype. LAG3+ Tregs expanded, but based on the transcriptome profile, became metabolically silent during the treatment. Last, higher baseline TCR clonality was observed in responding patients, and their expanding CD8+ T cell clones gained a more cytotoxic and NK-like phenotype.ConclusionAnti-LAG-3+anti-PD-1 therapy has profound effects on NK cells and Tregs in addition to CD8+ T cells.Trial registrationClinicalTrials.gov (NCT01968109)FundingCancer Foundation Finland, Sigrid Juselius Foundation, Signe and Ane Gyllenberg Foundation, Relander Foundation, State funding for university-level health research in Finland, a Helsinki Institute of Life Sciences Fellow grant, Academy of Finland (grant numbers 314442, 311081, 335432, and 335436), and an investigator-initiated research grant from BMS.

T-Cell Receptor Repertoire Sequencing in the Era of Cancer Immunotherapy

T cells are integral components of the adaptive immune system, and their responses are mediated by unique T-cell receptors (TCR) that recognize specific antigens from a variety of biological contexts. As a result, analyzing the T-cell repertoire offers a better understanding of immune responses and of diseases like cancer. Next-generation sequencing technologies have greatly enabled the high-throughput analysis of the TCR repertoire. On the basis of our extensive experience in the field from the past decade, we provide an overview of TCR sequencing, from the initial library preparation steps to sequencing and analysis methods and finally to functional validation techniques. With regards to data analysis, we detail important TCR repertoire metrics and present several computational tools for predicting antigen specificity. Finally, we highlight important applications of TCR sequencing and repertoire analysis to understanding tumor biology and developing cancer immunotherapies.

Counting is almost all you need

The immune memory repertoire encodes the history of present and past infections and immunological attributes of the individual. As such, multiple methods were proposed to use T-cell receptor (TCR) repertoires to detect disease history. We here show that the counting method outperforms two leading algorithms. We then show that the counting can be further improved using a novel attention model to weigh the different TCRs. The attention model is based on the projection of TCRs using a Variational AutoEncoder (VAE). Both counting and attention algorithms predict better than current leading algorithms whether the host had CMV and its HLA alleles. As an intermediate solution between the complex attention model and the very simple counting model, we propose a new Graph Convolutional Network approach that obtains the accuracy of the attention model and the simplicity of the counting model. The code for the models used in the paper is provided at: https://github.com/louzounlab/CountingIsAlmostAllYouNeed.

Clustering and Annotation of T Cell Receptor Repertoires

Immunological protection against a wide variety of pathogens is largely mediated by the diverse and dynamic T cell receptor (TCR) repertoire, a crucial component of the adaptive immune system. An encounter with infectious agents stimulates specific T cells to initiate a direct immune response to combat intruders. Hence, the TCR repertoire may conceal crucial information regarding current and past infections and might assist in the development and monitoring of vaccines. To unlock its knowledge, we describe a computational workflow involving both supervised and unsupervised machine learning techniques to analyze and annotate full TCR repertoire data. The method is explained using data from a published yellow fever virus (YFV) vaccination study in healthy individuals. The TCR repertoire of one individual is studied before and 2 weeks after vaccination, using an efficient clustering method and identification of YFV-specific TCRs.

simAIRR: simulation of adaptive immune repertoires with realistic receptor sequence sharing for benchmarking of immune state prediction methods

BACKGROUND

Machine learning (ML) has gained significant attention for classifying immune states in adaptive immune receptor repertoires (AIRRs) to support the advancement of immunodiagnostics and therapeutics. Simulated data are crucial for the rigorous benchmarking of AIRR-ML methods. Existing approaches to generating synthetic benchmarking datasets result in the generation of naive repertoires missing the key feature of many shared receptor sequences (selected for common antigens) found in antigen-experienced repertoires.

RESULTS

We demonstrate that a common approach to generating simulated AIRR benchmark datasets can introduce biases, which may be exploited for undesired shortcut learning by certain ML methods. To mitigate undesirable access to true signals in simulated AIRR datasets, we devised a simulation strategy (simAIRR) that constructs antigen-experienced-like repertoires with a realistic overlap of receptor sequences. simAIRR can be used for constructing AIRR-level benchmarks based on a range of assumptions (or experimental data sources) for what constitutes receptor-level immune signals. This includes the possibility of making or not making any prior assumptions regarding the similarity or commonality of immune state-associated sequences that will be used as true signals. We demonstrate the real-world realism of our proposed simulation approach by showing that basic ML strategies perform similarly on simAIRR-generated and real-world experimental AIRR datasets.

CONCLUSIONS

This study sheds light on the potential shortcut learning opportunities for ML methods that can arise with the state-of-the-art way of simulating AIRR datasets. simAIRR is available as a Python package: https://github.com/KanduriC/simAIRR.

TCRconv: predicting recognition between T cell receptors and epitopes using contextualized motifs

MOTIVATION

T cells use T cell receptors (TCRs) to recognize small parts of antigens, called epitopes, presented by major histocompatibility complexes. Once an epitope is recognized, an immune response is initiated and T cell activation and proliferation by clonal expansion begin. Clonal populations of T cells with identical TCRs can remain in the body for years, thus forming immunological memory and potentially mappable immunological signatures, which could have implications in clinical applications including infectious diseases, autoimmunity and tumor immunology.

RESULTS

We introduce TCRconv, a deep learning model for predicting recognition between TCRs and epitopes. TCRconv uses a deep protein language model and convolutions to extract contextualized motifs and provides state-of-the-art TCR-epitope prediction accuracy. Using TCR repertoires from COVID-19 patients, we demonstrate that TCRconv can provide insight into T cell dynamics and phenotypes during the disease.

AVAILABILITY AND IMPLEMENTATION

TCRconv is available at https://github.com/emmijokinen/tcrconv.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Attention-aware contrastive learning for predicting T cell receptor-antigen binding specificity

MOTIVATION

It has been proven that only a small fraction of the neoantigens presented by major histocompatibility complex (MHC) class I molecules on the cell surface can elicit T cells. This restriction can be attributed to the binding specificity of T cell receptor (TCR) and peptide-MHC complex (pMHC). Computational prediction of T cells binding to neoantigens is a challenging and unresolved task.

RESULTS

In this paper, we proposed an attention-aware contrastive learning model, ATMTCR, to infer the TCR-pMHC binding specificity. For each TCR sequence, we used a transformer encoder to transform it to latent representation, and then masked a percentage of amino acids guided by attention weights to generate its contrastive view. Compared to fully-supervised baseline model, we verified that contrastive learning-based pretraining on large-scale TCR sequences significantly improved the prediction performance of downstream tasks. Interestingly, masking a percentage of amino acids with low attention weights yielded best performance compared to other masking strategies. Comparison experiments on two independent datasets demonstrated our method achieved better performance than other existing algorithms. Moreover, we identified important amino acids and their positional preference through attention weights, which indicated the potential interpretability of our proposed model.

On TCR binding predictors failing to generalize to unseen peptides

Several recent studies investigate TCR-peptide/-pMHC binding prediction using machine learning or deep learning approaches. Many of these methods achieve impressive results on test sets, which include peptide sequences that are also included in the training set. In this work, we investigate how state-of-the-art deep learning models for TCR-peptide/-pMHC binding prediction generalize to unseen peptides. We create a dataset including positive samples from IEDB, VDJdb, McPAS-TCR, and the MIRA set, as well as negative samples from both randomization and 10X Genomics assays. We name this collection of samples TChard. We propose the hard split, a simple heuristic for training/test split, which ensures that test samples exclusively present peptides that do not belong to the training set. We investigate the effect of different training/test splitting techniques on the models’ test performance, as well as the effect of training and testing the models using mismatched negative samples generated randomly, in addition to the negative samples derived from assays. Our results show that modern deep learning methods fail to generalize to unseen peptides. We provide an explanation why this happens and verify our hypothesis on the TChard dataset. We then conclude that robust prediction of TCR recognition is still far for being solved.

Evolution and modulation of antigen-specific T cell responses in melanoma patients

Analyzing antigen-specific T cell responses at scale has been challenging. Here, we analyze three types of T cell receptor (TCR) repertoire data (antigen-specific TCRs, TCR-repertoire, and single-cell RNA + TCRαβ-sequencing data) from 515 patients with primary or metastatic melanoma and compare it to 783 healthy controls. Although melanoma-associated antigen (MAA) -specific TCRs are restricted to individuals, they share sequence similarities that allow us to build classifiers for predicting anti-MAA T cells. The frequency of anti-MAA T cells distinguishes melanoma patients from healthy and predicts metastatic recurrence from primary melanoma. Anti-MAA T cells have stem-like properties and frequent interactions with regulatory T cells and tumor cells via Galectin9-TIM3 and PVR-TIGIT -axes, respectively. In the responding patients, the number of expanded anti-MAA clones are higher after the anti-PD1(+anti-CTLA4) therapy and the exhaustion phenotype is rescued. Our systems immunology approach paves the way for understanding antigen-specific responses in human disorders.

Previous studies have characterized the diversity and dynamics of the T cell receptor (TCR) repertoire in patients with solid cancer. Here, by analyzing TCR repertoire data from multiple datasets, the authors report that melanoma-associated antigen-specific TCRs can be used to separate metastatic melanoma patients from healthy controls and to follow anti-tumor responses in patients treated with immunotherapy.

Gene Signatures of T-Cell Activation Can Serve as Predictors of Functionality for SARS-CoV-2-Specific T-Cell Receptors

The importance of T cells in controlling SARS-CoV-2 infections has been demonstrated widely, but insights into the quality of these responses are still limited due to technical challenges. Indeed, understanding the functionality of the T-cell receptor (TCR) repertoire of a polyclonal antigen-specific population still requires the tedious work of T-cell cloning or TCR re-expression and subsequent characterization. In this work, we show that it is possible to discriminate highly functional and bystander TCRs based on gene signatures of T-cell activation induced by recent peptide stimulation. SARS-CoV-2-specific TCRs previously identified by cytokine release after peptide restimulation and subsequent single-cell RNA sequencing were re-expressed via CRISPR-Cas9-mediated gene editing into a Jurkat-based reporter cell line system suitable for high-throughput screening. We could observe differences in SARS-CoV-2 epitope recognition as well as a wide range of functional avidities. By correlating these in vitro TCR engineered functional data with the transcriptomic profiles of the corresponding TCR-expressing parental T cells, we could validate that gene signatures of recent T-cell activation accurately identify and predict truly SARS-CoV-2-specific TCRs. In summary, this work paves the way for alternative approaches useful for the functional analysis of global antigen-specific TCR repertoires with largely improved throughput.

IFN-α with dasatinib broadens the immune repertoire in patients with chronic-phase chronic myeloid leukemia

In chronic myeloid leukemia (CML), combination therapies with tyrosine kinase inhibitors (TKIs) aim to improve the achievement of deep molecular remission that would allow therapy discontinuation. IFN-α is one promising candidate, as it has long-lasting effects on both malignant and immune cells. In connection with a multicenter clinical trial combining dasatinib with IFN-α in 40 patients with chronic-phase CML (NordCML007, NCT01725204), we performed immune monitoring with single-cell RNA and T cell receptor (TCR) sequencing (n = 4, 12 samples), bulk TCRβ sequencing (n = 13, 26 samples), flow cytometry (n = 40, 106 samples), cytokine analyses (n = 17, 80 samples), and ex vivo functional studies (n = 39, 80 samples). Dasatinib drove the immune repertoire toward terminally differentiated NK and CD8⁺ T cells with dampened functional capabilities. Patients with dasatinib-associated pleural effusions had increased numbers of CD8⁺ recently activated effector memory T (Temra) cells. In vitro, dasatinib prevented CD3-induced cell death by blocking TCR signaling. The addition of IFN-α reversed the terminally differentiated phenotypes and increased the number of costimulatory intercellular interactions and the number of unique putative epitope-specific TCR clusters. In vitro IFN-α had costimulatory effects on TCR signaling. Our work supports the combination of IFN-α with TKI therapy, as IFN-α broadens the immune repertoire and restores immunological function.

ATM-TCR: TCR-Epitope Binding Affinity Prediction Using a Multi-Head Self-Attention Model

TCR-epitope pair binding is the key component for T cell regulation. The ability to predict whether a given pair binds is fundamental to understanding the underlying biology of the binding mechanism as well as developing T-cell mediated immunotherapy approaches. The advent of large-scale public databases containing TCR-epitope binding pairs enabled the recent development of computational prediction methods for TCR-epitope binding. However, the number of epitopes reported along with binding TCRs is far too small, resulting in poor out-of-sample performance for unseen epitopes. In order to address this issue, we present our model ATM-TCR which uses a multi-head self-attention mechanism to capture biological contextual information and improve generalization performance. Additionally, we present a novel application of the attention map from our model to improve out-of-sample performance by demonstrating on recent SARS-CoV-2 data.

DECODE: a computational pipeline to discover T cell receptor binding rules

Motivation

Understanding the mechanisms underlying T cell receptor (TCR) binding is of fundamental importance to understanding adaptive immune responses. A better understanding of the biochemical rules governing TCR binding can be used, e.g. to guide the design of more powerful and safer T cell-based therapies. Advances in repertoire sequencing technologies have made available millions of TCR sequences. Data abundance has, in turn, fueled the development of many computational models to predict the binding properties of TCRs from their sequences. Unfortunately, while many of these works have made great strides toward predicting TCR specificity using machine learning, the black-box nature of these models has resulted in a limited understanding of the rules that govern the binding of a TCR and an epitope.

Results

We present an easy-to-use and customizable computational pipeline, DECODE, to extract the binding rules from any black-box model designed to predict the TCR-epitope binding. DECODE offers a range of analytical and visualization tools to guide the user in the extraction of such rules. We demonstrate our pipeline on a recently published TCR-binding prediction model, TITAN, and show how to use the provided metrics to assess the quality of the computed rules. In conclusion, DECODE can lead to a better understanding of the sequence motifs that underlie TCR binding. Our pipeline can facilitate the investigation of current immunotherapeutic challenges, such as cross-reactive events due to off-target TCR binding.

Availability and implementation

Code is available publicly at https://github.com/phineasng/DECODE.

Supplementary information

Supplementary data are available at Bioinformatics online.

Naive and memory T cells TCR-HLA-binding prediction

T cells recognize antigens through the interaction of their T cell receptor (TCR) with a peptide-major histocompatibility complex (pMHC) molecule. Following thymic-positive selection, TCRs in peripheral naive T cells are expected to bind MHC alleles of the host. Peripheral clonal selection is expected to further increase the frequency of antigen-specific TCRs that bind to the host MHC alleles. To check for a systematic preference for MHC-binding T cells in TCR repertoires, we developed Natural Language Processing-based methods to predict TCR-MHC binding independently of the peptide presented for Class I MHC alleles. We trained a classifier on published TCR-pMHC binding pairs and obtained a high area under curve (AUC) of over 0.90 on the test set. However, when applied to TCR repertoires, the accuracy of the classifier dropped. We thus developed a two-stage prediction model, based on large-scale naive and memory TCR repertoires, denoted TCR HLA-binding predictor (CLAIRE). Since each host carries multiple human leukocyte antigen (HLA) alleles, we first computed whether a TCR on a CD8 T cell binds an MHC from any of the host Class-I HLA alleles. We then performed an iteration, where we predict the binding with the most probable allele from the first round. We show that this classifier is more precise for memory than for naïve cells. Moreover, it can be transferred between datasets. Finally, we developed a CD4-CD8 T cell classifier to apply CLAIRE to unsorted bulk sequencing datasets and showed a high AUC of 0.96 and 0.90 on large datasets. CLAIRE is available through a GitHub at: https://github.com/louzounlab/CLAIRE, and as a server at: https://claire.math.biu.ac.il/Home.

CAD v1.0: Cancer Antigens Database Platform for Cancer Antigen Algorithm Development and Information Exploration

Cancer vaccines have gradually attracted attention for their tremendous preclinical and clinical performance. With the development of next-generation sequencing technologies and related algorithms, pipelines based on sequencing and machine learning methods have become mainstream in cancer antigen prediction; of particular focus are neoantigens, mutation peptides that only exist in tumor cells that lack central tolerance and have fewer side effects. The rapid prediction and filtering of neoantigen peptides are crucial to the development of neoantigen-based cancer vaccines. However, due to the lack of verified neoantigen datasets and insufficient research on the properties of neoantigens, neoantigen prediction algorithms still need to be improved. Here, we recruited verified cancer antigen peptides and collected as much relevant peptide information as possible. Then, we discussed the role of each dataset for algorithm improvement in cancer antigen research, especially neoantigen prediction. A platform, Cancer Antigens Database (CAD, http://cad.bio-it.cn/), was designed to facilitate users to perform a complete exploration of cancer antigens online.

Single-cell characterization of leukemic and non-leukemic immune repertoires in CD8+ T-cell large granular lymphocytic leukemia

T cell large granular lymphocytic leukemia (T-LGLL) is a rare lymphoproliferative disorder of mature, clonally expanded T cells, where somatic-activating STAT3 mutations are common. Although T-LGLL has been described as a chronic T cell response to an antigen, the function of the non-leukemic immune system in this response is largely uncharacterized. Here, by utilizing single-cell RNA and T cell receptor profiling (scRNA+TCRαβ-seq), we show that irrespective of STAT3 mutation status, T-LGLL clonotypes are more cytotoxic and exhausted than healthy reactive clonotypes. In addition, T-LGLL clonotypes show more active cell communication than reactive clones with non-leukemic immune cells via costimulatory cell-cell interactions, monocyte-secreted proinflammatory cytokines, and T-LGLL-clone-secreted IFNγ. Besides the leukemic repertoire, the non-leukemic T cell repertoire in T-LGLL is also more mature, cytotoxic, and clonally restricted than in other cancers and autoimmune disorders. Finally, 72% of the leukemic T-LGLL clonotypes share T cell receptor similarities with their non-leukemic repertoire, linking the leukemic and non-leukemic repertoires together via possible common target antigens. Our results provide a rationale to prioritize therapies that target the entire immune repertoire and not only the T-LGLL clonotype.