Improved predictions of antigen presentation and TCR recognition with MixMHCpred2.2 and PRIME2.0 reveal potent SARS-CoV-2 CD8+ T-cell epitopes

Geometric deep learning improves generalizability of MHC-bound peptide predictions

The interaction between peptides and major histocompatibility complex (MHC) molecules is pivotal in autoimmunity, pathogen recognition and tumor immunity. Recent advances in cancer immunotherapies demand for more accurate computational prediction of MHC-bound peptides. We address the generalizability challenge of MHC-bound peptide predictions, revealing limitations in current sequence-based approaches. Our structure-based methods leveraging geometric deep learning (GDL) demonstrate promising improvement in generalizability across unseen MHC alleles. Further, we tackle data efficiency by introducing a self-supervised learning approach on structures (3D-SSL). Without being exposed to any binding affinity data, our 3D-SSL outperforms sequence-based methods trained on ~90 times more data points. Finally, we demonstrate the resilience of structure-based GDL methods to biases in binding data on an Hepatitis B virus vaccine immunopeptidomics case study. This proof-of-concept study highlights structure-based methods' potential to enhance generalizability and data efficiency, with possible implications for data-intensive fields like T-cell receptor specificity predictions.

Exploring immunogenic CD8 + T-cell epitopes for peptide-based vaccine development against evolving SARS-CoV-2 variants: An immunoinformatics approach

The COVID-19 pandemic originated in Wuhan in 2019 due to a novel SARS-COV-2 (Severe Acute Respiratory Syndrome Coronavirus 2) responsible for the massive number of deaths across the globe. So far, several vaccines have been developed using highly antigenic Spike protein and authorized for emergency use, reducing the severity of the infection. Nonetheless, the virus continues to evolve through multiple mutations, resulting in numerous variants with enhanced transmission that evade the vaccine-induced immune response. Given the persistently mutating nature of the SARS-COV-2 virus, peptide-based vaccines with highly conserved epitopes may offer lasting protection against evolving variants. This study presents an immunoinformatics-based identification of potentially immunogenic CD8 + T-cell epitopes (CTLs) of Spike (S), Membrane (M), Nucleocapsid (N) and Envelope (E) proteins of SARS-COV-2. By utilizing the immunoinformatic approach, 21 epitopes have successfully been evaluated, where 15, 3, 2, and 1 epitopes are respectively from Spike, Membrane, Envelope and Nucleocapsid proteins. Out of these, 20 are found to be identical with experimentally verified immunogenic epitopes, except for the novel NTQEVFAQV epitope from spike protein. These epitopes show a high degree of conservation in both former variants of concerns (VOCs), variants of interest (VOIs) and current variants under monitoring (VUMs), are non-toxic, non-homologous to humans and have a wide range of global population coverage. Furthermore, utilizing molecular docking analysis followed by molecular dynamics simulation, these epitopes have been verified as having stable interactions with their respective HLA molecules. The described framework and projected immunogenic epitopes could significantly impact the development of SARS-COV-2 vaccines based on peptides.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13337-024-00894-7.

CapHLA: a comprehensive tool to predict peptide presentation and binding to HLA class I and class II

Human leukocyte antigen class I (HLA-I) and class II (HLA-II) proteins play an essential role in epitope binding and presentation to initiate an immune response. Accurate prediction of peptide-HLA (pHLA) binding and presentation is critical for developing effective immunotherapies. However, current tools can predict antigens exclusively for pHLA-I or pHLA-II, but not both; have constraints on peptide length; and commonly show unsatisfactory predictive accuracy. Here, we developed a convolution and attention-based model, CapHLA, trained with eluted ligand and binding affinity mass spectrometry data, to predict peptide presentation probability (PB) and binding affinities (BA) for HLA-I and HLA-II. In comparison with 11 other methods, CapHLA consistently showed improved performance in predicting pHLA BA and PB, particularly in HLA-II and non-classical peptide length datasets. Using CapHLA PB and BA predictions in combination with antigen expression level (EP) from transcriptomic data, we developed a neoantigen quality model for predicting immunotherapy response. In analyses of clinical response among 276 cancer patients given immunotherapy and overall survival in 7228 cancer patients, our neoantigen quality model outperformed other genetics-based models in predicting response to checkpoint inhibitors and patient prognosis. This study provides a versatile neoantigen screening tool, illustrating the prognostic value of neoantigen quality.

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.

Identification of highly conserved surface-exposed peptides of spike protein for multiepitope vaccine design against emerging omicron variants: An immunoinformatic approach

The COVID-19 pandemic, originating in Wuhan in 2019, was caused by SARS-CoV-2, leading to significant global fatalities. Despite the development of vaccines, the virus mutates, creating variants that evade vaccine-induced immunity. To address SARS-CoV-2's evolving nature, a multiepitope vaccine was developed using immunoinformatics approach, specifically targeting the Omicron variant's spike protein. This vaccine includes six CD8 + and eleven CD4 + epitopes selected for their immunogenicity, non-toxicity, and significant conservation among former Variants of Concern (VOCs) and Variants of Interest (VOIs), such as Alpha, Beta, Gamma, Delta, Lambda, Mu, R1, and Zeta, as well as current Variants Under Monitoring (VUMs) like XBB.1.5, XBB.1.16, EG.5, BA.2.86, and JN.1. Notably, certain epitopes like ELLHAPATV and PYRVVVLSFELLHAP were fully conserved across all tested variants in the spike protein's receptor binding domain (RBD). Others, such as NATRFASVYAWNRKR, were fully conserved in all former VOCs and VOIs and 93.33 % in current VUMs, while ERDISTEIYQAGNKP was entirely conserved in current VUMs within the RBD region. The study went on to model, refine, and validate the vaccine prototype's tertiary structure. Docking experiments and molecular dynamic simulations revealed robust and stable interactions with Toll-like receptor 4. Cloning and codon optimization confirmed successful expression in E. coli. Subsequently, the immunological reaction of the multiepitope vaccine demonstrated that the three-time administration of the prototype significantly enhanced the antibody response while decreasing the number of antigens. The designed vaccine's epitopes showed significant combined global population coverage of 100 % with 89.75 % for CD8 + and 99.98 % for CD4 + epitopes and conservation across SARS-CoV-2 variants especially in current monitoring omicron subvariants, supporting its broader applicability and potential efficacy. Although, this promising vaccine candidate needs to undergo clinical trials to determine its effectiveness in neutralising SARS-CoV-2.

A modular protein language modelling approach to immunogenicity prediction

Neoantigen immunogenicity prediction is a highly challenging problem in the development of personalised medicines. Low reactivity rates in called neoantigens result in a difficult prediction scenario with limited training datasets. Here we describe ImmugenX, a modular protein language modelling approach to immunogenicity prediction for CD8+ reactive epitopes. ImmugenX comprises of a pMHC encoding module trained on three pMHC prediction tasks, an optional TCR encoding module and a set of context specific immunogenicity prediction head modules. Compared with state-of-the-art models for each task, ImmugenX's encoding module performs comparably or better on pMHC binding affinity, eluted ligand prediction and stability tasks. ImmugenX outperforms all compared models on pMHC immunogenicity prediction (Area under the receiver operating characteristic curve = 0.619, average precision: 0.514), with a 7% increase in average precision compared to the next best model. ImmugenX shows further improved performance on immunogenicity prediction with the integration of TCR context information. ImmugenX performance is further analysed for interpretability, which locates areas of weakness found across existing immunogenicity models and highlight possible biases in public datasets.

ImmuneApp for HLA-I epitope prediction and immunopeptidome analysis

Advances in mass spectrometry accelerates the characterization of HLA ligandome, necessitating the development of efficient methods for immunopeptidomics analysis and (neo)antigen prediction. We develop ImmuneApp, an interpretable deep learning framework trained on extensive HLA ligand datasets, which improves the prediction of HLA-I epitopes, prioritizes neoepitopes, and enhances immunopeptidomics deconvolution. ImmuneApp extracts informative embeddings and identifies key residues for pHLA binding. We also present a more accurate model-based deconvolution approach and systematically analyzed 216 multi-allelic immunopeptidomics samples, identifying 835,551 ligands restricted to over 100 HLA-I alleles. Our investigation reveals the effectiveness of the composite model, denoted as ImmuneApp-MA, which integrates mono- and multi-allelic data to enhance predictive performance. Leveraging ImmuneApp-MA as a pre-trained model, we built ImmuneApp-Neo, an immunogenicity predictor that outperforms existing methods for prioritizing immunogenic neoepitope. ImmuneApp demonstrates its utility across various immunopeptidomics datasets, which will promote the discovery of novel neoantigens and the development of new immunotherapies.

A comprehensive proteogenomic pipeline for neoantigen discovery to advance personalized cancer immunotherapy

The accurate identification and prioritization of antigenic peptides is crucial for the development of personalized cancer immunotherapies. Publicly available pipelines to predict clinical neoantigens do not allow direct integration of mass spectrometry immunopeptidomics data, which can uncover antigenic peptides derived from various canonical and noncanonical sources. To address this, we present an end-to-end clinical proteogenomic pipeline, called NeoDisc, that combines state-of-the-art publicly available and in-house software for immunopeptidomics, genomics and transcriptomics with in silico tools for the identification, prediction and prioritization of tumor-specific and immunogenic antigens from multiple sources, including neoantigens, viral antigens, high-confidence tumor-specific antigens and tumor-specific noncanonical antigens. We demonstrate the superiority of NeoDisc in accurately prioritizing immunogenic neoantigens over recent prioritization pipelines. We showcase the various features offered by NeoDisc that enable both rule-based and machine-learning approaches for personalized antigen discovery and neoantigen cancer vaccine design. Additionally, we demonstrate how NeoDisc's multiomics integration identifies defects in the cellular antigen presentation machinery, which influence the heterogeneous tumor antigenic landscape.

T Cell Peptide Prediction, Immune Response, and Host-Pathogen Relationship in Vaccinated and Recovered from Mild COVID-19 Subjects

COVID-19 remains a significant threat, particularly to vulnerable populations. The emergence of new variants necessitates the development of treatments and vaccines that induce both humoral and cellular immunity. This study aimed to identify potentially immunogenic SARS-CoV-2 peptides and to explore the intricate host-pathogen interactions involving peripheral immune responses, memory profiles, and various demographic, clinical, and lifestyle factors. Using in silico and experimental methods, we identified several CD8-restricted SARS-CoV-2 peptides that are either poorly studied or have previously unreported immunogenicity: fifteen from the Spike and three each from non-structural proteins Nsp1-2-3-16. A Spike peptide, LA-9, demonstrated a 57% response rate in ELISpot assays using PBMCs from 14 HLA-A*02:01 positive, vaccinated, and mild-COVID-19 recovered subjects, indicating its potential for diagnostics, research, and multi-epitope vaccine platforms. We also found that younger individuals, with fewer vaccine doses and longer intervals since infection, showed lower anti-Spike (ELISA) and anti-Wuhan neutralizing antibodies (pseudovirus assay), higher naïve T cells, and lower central memory, effector memory, and CD4hiCD8low T cells (flow cytometry) compared to older subjects. In our cohort, a higher prevalence of Vδ2-γδ and DN T cells, and fewer naïve CD8 T cells, seemed to correlate with strong cellular and lower anti-NP antibody responses and to associate with Omicron infection, absence of confusional state, and habitual sporting activity.

Strategies to Overcome Hurdles in Cancer Immunotherapy

Despite marked advancements in cancer immunotherapy over the past few decades, there remains an urgent need to develop more effective treatments in humans. This review explores strategies to overcome hurdles in cancer immunotherapy, leveraging innovative technologies including multi-specific antibodies, chimeric antigen receptor (CAR) T cells, myeloid cells, cancer-associated fibroblasts, artificial intelligence (AI)-predicted neoantigens, autologous vaccines, and mRNA vaccines. These approaches aim to address the diverse facets and interactions of tumors' immune evasion mechanisms. Specifically, multi-specific antibodies and CAR T cells enhance interactions with tumor cells, bolstering immune responses to facilitate tumor infiltration and destruction. Modulation of myeloid cells and cancer-associated fibroblasts targets the tumor's immunosuppressive microenvironment, enhancing immunotherapy efficacy. AI-predicted neoantigens swiftly and accurately identify antigen targets, which can facilitate the development of personalized anticancer vaccines. Additionally, autologous and mRNA vaccines activate individuals' immune systems, fostering sustained immune responses against cancer neoantigens as therapeutic vaccines. Collectively, these strategies are expected to enhance efficacy of cancer immunotherapy, opening new horizons in anticancer treatment.

RLpMIEC: High-Affinity Peptide Generation Targeting Major Histocompatibility Complex-I Guided and Interpreted by Interaction Spectrum-Navigated Reinforcement Learning

Major histocompatibility complex (MHC) plays a vital role in presenting epitopes (short peptides from pathogenic proteins) to T-cell receptors (TCRs) to trigger the subsequent immune responses. Vaccine design targeting MHC generally aims to find epitopes with a high binding affinity for MHC presentation. Nevertheless, to find novel epitopes usually requires high-throughput screening of bulk peptide database, which is time-consuming, labor-intensive, more unaffordable, and very expensive. Excitingly, the past several years have witnessed the great success of artificial intelligence (AI) in various fields, such as natural language processing (NLP, e.g., GPT-4), protein structure prediction and engineering (e.g., AlphaFold2), and so on. Therefore, herein, we propose a deep reinforcement-learning (RL)-based generative algorithm, RLpMIEC, to quantitatively design peptide targeting MHC-I systems. Specifically, RLpMIEC combines the energetic spectrum (namely, the molecular interaction energy component, MIEC) based on the peptide-MHC interaction and the sequence information to generate peptides with strong binding affinity and precise MIEC spectra to accelerate the discovery of candidate peptide vaccines. RLpMIEC performs well in all the generative capability evaluations and can generate peptides with strong binding affinities and precise MIECs and, moreover, with high interpretability, demonstrating its powerful capability in participation for accelerating peptide-based vaccine development.

Harnessing microbial antigens as cancer antigens: a promising avenue for cancer immunotherapy

Immunotherapy has revolutionized cancer treatment by leveraging the immune system's innate capabilities to combat malignancies. Despite the promise of tumor antigens in stimulating anti-tumor immune responses, their clinical utility is hampered by limitations in eliciting robust and durable immune reactions, exacerbated by tumor heterogeneity and immune evasion mechanisms. Recent insights into the immunogenic properties of host homologous microbial antigens have sparked interest in their potential for augmenting anti-tumor immunity while minimizing off-target effects. This review explores the therapeutic potential of microbial antigen peptides in tumor immunotherapy, beginning with an overview of tumor antigens and their challenges in clinical translation. We further explore the intricate relationship between microorganisms and tumor development, elucidating the concept of molecular mimicry and its implications for immune recognition of tumor-associated antigens. Finally, we discuss methodologies for identifying and characterizing microbial antigen peptides, highlighting their immunogenicity and prospects for therapeutic application.

Development and Clinical Applications of Therapeutic Cancer Vaccines with Individualized and Shared Neoantigens

Neoantigens, presented as peptides on the surfaces of cancer cells, have recently been proposed as optimal targets for immunotherapy in clinical practice. The promising outcomes of neoantigen-based cancer vaccines have inspired enthusiasm for their broader clinical applications. However, the individualized tumor-specific antigens (TSA) entail considerable costs and time due to the variable immunogenicity and response rates of these neoantigens-based vaccines, influenced by factors such as neoantigen response, vaccine types, and combination therapy. Given the crucial role of neoantigen efficacy, a number of bioinformatics algorithms and pipelines have been developed to improve the accuracy rate of prediction through considering a series of factors involving in HLA-peptide-TCR complex formation, including peptide presentation, HLA-peptide affinity, and TCR recognition. On the other hand, shared neoantigens, originating from driver mutations at hot mutation spots (e.g., KRASG12D), offer a promising and ideal target for the development of therapeutic cancer vaccines. A series of clinical practices have established the efficacy of these vaccines in patients with distinct HLA haplotypes. Moreover, increasing evidence demonstrated that a combination of tumor associated antigens (TAAs) and neoantigens can also improve the prognosis, thus expand the repertoire of shared neoantigens for cancer vaccines. In this review, we provide an overview of the complex process involved in identifying personalized neoantigens, their clinical applications, advances in vaccine technology, and explore the therapeutic potential of shared neoantigen strategies.

Vaccination Shapes Within-Host SARS-CoV-2 Diversity of Omicron BA.2.2 Breakthrough Infection

BACKGROUND

Low-frequency intrahost single-nucleotide variants of SARS-CoV-2 have been recognized as predictive indicators of selection. However, the impact of vaccination on the intrahost evolution of SARS-CoV-2 remains uncertain at present.

METHODS

We investigated the genetic variation of SARS-CoV-2 in individuals who were unvaccinated, partially vaccinated, or fully vaccinated during Shanghai's Omicron BA.2.2 wave. We substantiated the connection between particular amino acid substitutions and immune-mediated selection through a pseudovirus neutralization assay or by cross-verification with the human leukocyte antigen-associated T-cell epitopes.

RESULTS

In contrast to those with immunologic naivety or partial vaccination, participants who were fully vaccinated had intrahost variant spectra characterized by reduced diversity. Nevertheless, the distribution of mutations in the fully vaccinated group was enriched in the spike protein. The distribution of intrahost single-nucleotide variants in individuals who were immunocompetent did not demonstrate notable signs of positive selection, in contrast to the observed adaptation in 2 participants who were immunocompromised who had an extended period of viral shedding.

CONCLUSIONS

In SARS-CoV-2 infections, vaccine-induced immunity was associated with decreased diversity of within-host variant spectra, with milder inflammatory pathophysiology. The enrichment of mutations in the spike protein gene indicates selection pressure exerted by vaccination on the evolution of SARS-CoV-2.

Joint host-pathogen genomic analysis identifies hepatitis B virus mutations associated with human NTCP and HLA class I variation

Evolutionary changes in the hepatitis B virus (HBV) genome could reflect its adaptation to host-induced selective pressure. Leveraging paired human exome and ultra-deep HBV genome-sequencing data from 567 affected individuals with chronic hepatitis B, we comprehensively searched for the signatures of this evolutionary process by conducting "genome-to-genome" association tests between all human genetic variants and viral mutations. We identified significant associations between an East Asian-specific missense variant in the gene encoding the HBV entry receptor NTCP (rs2296651, NTCP S267F) and mutations within the receptor-binding region of HBV preS1. Through in silico modeling and in vitro preS1-NTCP binding assays, we observed that the associated HBV mutations are in proximity to the NTCP variant when bound and together partially increase binding affinity to NTCP S267F. Furthermore, we identified significant associations between HLA-A variation and viral mutations in HLA-A-restricted T cell epitopes. We used in silico binding prediction tools to evaluate the impact of the associated HBV mutations on HLA presentation and observed that mutations that result in weaker binding affinities to their cognate HLA alleles were enriched. Overall, our results suggest the emergence of HBV escape mutations that might alter the interaction between HBV PreS1 and its cellular receptor NTCP during viral entry into hepatocytes and confirm the role of HLA class I restriction in inducing HBV epitope variations.

Immunogenicity of Non-Mutated Ovarian Cancer-Specific Antigens

Epithelial ovarian cancer (EOC) has not significantly benefited from advances in immunotherapy, mainly because of the lack of well-defined actionable antigen targets. Using proteogenomic analyses of primary EOC tumors, we previously identified 91 aberrantly expressed tumor-specific antigens (TSAs) originating from unmutated genomic sequences. Most of these TSAs derive from non-exonic regions, and their expression results from cancer-specific epigenetic changes. The present study aimed to evaluate the immunogenicity of 48 TSAs selected according to two criteria: presentation by highly prevalent HLA allotypes and expression in a significant fraction of EOC tumors. Using targeted mass spectrometry analyses, we found that pulsing with synthetic TSA peptides leads to a high-level presentation on dendritic cells. TSA abundance correlated with the predicted binding affinity to the HLA allotype. We stimulated naïve CD8 T cells from healthy blood donors with TSA-pulsed dendritic cells and assessed their expansion with two assays: MHC-peptide tetramer staining and TCR Vβ CDR3 sequencing. We report that these TSAs can expand sizeable populations of CD8 T cells and, therefore, represent attractive targets for EOC immunotherapy.

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.

HLAIImaster: a deep learning method with adaptive domain knowledge predicts HLA II neoepitope immunogenic responses

While significant strides have been made in predicting neoepitopes that trigger autologous CD4+ T cell responses, accurately identifying the antigen presentation by human leukocyte antigen (HLA) class II molecules remains a challenge. This identification is critical for developing vaccines and cancer immunotherapies. Current prediction methods are limited, primarily due to a lack of high-quality training epitope datasets and algorithmic constraints. To predict the exogenous HLA class II-restricted peptides across most of the human population, we utilized the mass spectrometry data to profile >223 000 eluted ligands over HLA-DR, -DQ, and -DP alleles. Here, by integrating these data with peptide processing and gene expression, we introduce HLAIImaster, an attention-based deep learning framework with adaptive domain knowledge for predicting neoepitope immunogenicity. Leveraging diverse biological characteristics and our enhanced deep learning framework, HLAIImaster is significantly improved against existing tools in terms of positive predictive value across various neoantigen studies. Robust domain knowledge learning accurately identifies neoepitope immunogenicity, bridging the gap between neoantigen biology and the clinical setting and paving the way for future neoantigen-based therapies to provide greater clinical benefit. In summary, we present a comprehensive exploitation of the immunogenic neoepitope repertoire of cancers, facilitating the effective development of "just-in-time" personalized vaccines.

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.

NeoMUST: an accurate and efficient multi-task learning model for neoantigen presentation

Accurate identification of neoantigens is important for advancing cancer immunotherapies. This study introduces Neoantigen MUlti-taSk Tower (NeoMUST), a model employing multi-task learning to effectively capture task-specific information across related tasks. Our results show that NeoMUST rivals existing algorithms in predicting the presentation of neoantigens via MHC-I molecules, while demonstrating a significantly shorter training time for enhanced computational efficiency. The use of multi-task learning enables NeoMUST to leverage shared knowledge and task dependencies, leading to improved performance metrics and a significant reduction in the training time. NeoMUST, implemented in Python, is freely accessible at the GitHub repository. Our model will facilitate neoantigen prediction and empower the development of effective cancer immunotherapeutic approaches.

APE-Gen2.0: Expanding Rapid Class I Peptide-Major Histocompatibility Complex Modeling to Post-Translational Modifications and Noncanonical Peptide Geometries

The recognition of peptides bound to class I major histocompatibility complex (MHC-I) receptors by T-cell receptors (TCRs) is a determinant of triggering the adaptive immune response. While the exact molecular features that drive the TCR recognition are still unknown, studies have suggested that the geometry of the joint peptide-MHC (pMHC) structure plays an important role. As such, there is a definite need for methods and tools that accurately predict the structure of the peptide bound to the MHC-I receptor. In the past few years, many pMHC structural modeling tools have emerged that provide high-quality modeled structures in the general case. However, there are numerous instances of non-canonical cases in the immunopeptidome that the majority of pMHC modeling tools do not attend to, most notably, peptides that exhibit non-standard amino acids and post-translational modifications (PTMs) or peptides that assume non-canonical geometries in the MHC binding cleft. Such chemical and structural properties have been shown to be present in neoantigens; therefore, accurate structural modeling of these instances can be vital for cancer immunotherapy. To this end, we have developed APE-Gen2.0, a tool that improves upon its predecessor and other pMHC modeling tools, both in terms of modeling accuracy and the available modeling range of non-canonical peptide cases. Some of the improvements include (i) the ability to model peptides that have different types of PTMs such as phosphorylation, nitration, and citrullination; (ii) a new and improved anchor identification routine in order to identify and model peptides that exhibit a non-canonical anchor conformation; and (iii) a web server that provides a platform for easy and accessible pMHC modeling. We further show that structures predicted by APE-Gen2.0 can be used to assess the effects that PTMs have in binding affinity in a more accurate manner than just using solely the sequence of the peptide. APE-Gen2.0 is freely available at https://apegen.kavrakilab.org.

A large-scale study of peptide features defining immunogenicity of cancer neo-epitopes

Accurate prediction of immunogenicity for neo-epitopes arising from a cancer associated mutation is a crucial step in many bioinformatics pipelines that predict outcome of checkpoint blockade treatments or that aim to design personalised cancer immunotherapies and vaccines. In this study, we performed a comprehensive analysis of peptide features relevant for prediction of immunogenicity using the Cancer Epitope Database and Analysis Resource (CEDAR), a curated database of cancer epitopes with experimentally validated immunogenicity annotations from peer-reviewed publications. The developed model, ICERFIRE (ICore-based Ensemble Random Forest for neo-epitope Immunogenicity pREdiction), extracts the predicted ICORE from the full neo-epitope as input, i.e. the nested peptide with the highest predicted major histocompatibility complex (MHC) binding potential combined with its predicted likelihood of antigen presentation (%Rank). Key additional features integrated into the model include assessment of the BLOSUM mutation score of the neo-epitope, and antigen expression levels of the wild-type counterpart which is often reflecting a neo-epitope's abundance. We demonstrate improved and robust performance of ICERFIRE over existing immunogenicity and epitope prediction models, both in cross-validation and on external validation datasets.

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.

In Silico Tools for Predicting Novel Epitopes

Identifying antigens within a pathogen is a critical task to develop effective vaccines and diagnostic methods, as well as understanding the evolution and adaptation to host immune responses. Historically, antigenicity was studied with experiments that evaluate the immune response against selected fragments of pathogens. Using this approach, the scientific community has gathered abundant information regarding which pathogenic fragments are immunogenic. The systematic collection of this data has enabled unraveling many of the fundamental rules underlying the properties defining epitopes and immunogenicity, and has resulted in the creation of a large panel of immunologically relevant predictive (in silico) tools. The development and application of such tools have proven to accelerate the identification of novel epitopes within biomedical applications reducing experimental costs. This chapter introduces some basic concepts about MHC presentation, T cell and B cell epitopes, the experimental efforts to determine those, and focuses on state-of-the-art methods for epitope prediction, highlighting their strengths and limitations, and catering instructions for their rational use.

Unsupervised and supervised AI on molecular dynamics simulations reveals complex characteristics of HLA-A2-peptide immunogenicity

Immunologic recognition of peptide antigens bound to class I major histocompatibility complex (MHC) molecules is essential to both novel immunotherapeutic development and human health at large. Current methods for predicting antigen peptide immunogenicity rely primarily on simple sequence representations, which allow for some understanding of immunogenic features but provide inadequate consideration of the full scale of molecular mechanisms tied to peptide recognition. We here characterize contributions that unsupervised and supervised artificial intelligence (AI) methods can make toward understanding and predicting MHC(HLA-A2)-peptide complex immunogenicity when applied to large ensembles of molecular dynamics simulations. We first show that an unsupervised AI method allows us to identify subtle features that drive immunogenicity differences between a cancer neoantigen and its wild-type peptide counterpart. Next, we demonstrate that a supervised AI method for class I MHC(HLA-A2)-peptide complex classification significantly outperforms a sequence model on small datasets corrected for trivial sequence correlations. Furthermore, we show that both unsupervised and supervised approaches reveal determinants of immunogenicity based on time-dependent molecular fluctuations and anchor position dynamics outside the MHC binding groove. We discuss implications of these structural and dynamic immunogenicity correlates for the induction of T cell responses and therapeutic T cell receptor design.

Accurate TCR-pMHC interaction prediction using a BERT-based transfer learning method

Accurate prediction of TCR-pMHC binding is important for the development of cancer immunotherapies, especially TCR-based agents. Existing algorithms often experience diminished performance when dealing with unseen epitopes, primarily due to the complexity in TCR-pMHC recognition patterns and the scarcity of available data for training. We have developed a novel deep learning model, 'TCR Antigen Binding Recognition' based on BERT, named as TABR-BERT. Leveraging BERT's potent representation learning capabilities, TABR-BERT effectively captures essential information regarding TCR-pMHC interactions from TCR sequences, antigen epitope sequences and epitope-MHC binding. By transferring this knowledge to predict TCR-pMHC recognition, TABR-BERT demonstrated better results in benchmark tests than existing methods, particularly for unseen epitopes.

Structural basis for T cell recognition of cancer neoantigens and implications for predicting neoepitope immunogenicity

Adoptive cell therapy (ACT) with tumor-specific T cells has been shown to mediate durable cancer regression. Tumor-specific T cells are also the basis of other therapies, notably cancer vaccines. The main target of tumor-specific T cells are neoantigens resulting from mutations in self-antigens over the course of malignant transformation. The detection of neoantigens presents a major challenge to T cells because of their high structural similarity to self-antigens, and the need to avoid autoimmunity. How different a neoantigen must be from its wild-type parent for it to induce a T cell response is poorly understood. Here we review recent structural and biophysical studies of T cell receptor (TCR) recognition of shared cancer neoantigens derived from oncogenes, including p53R175H, KRASG12D, KRASG12V, HHATp8F, and PIK3CAH1047L. These studies have revealed that, in some cases, the oncogenic mutation improves antigen presentation by strengthening peptide-MHC binding. In other cases, the mutation is detected by direct interactions with TCR, or by energetically driven or other indirect strategies not requiring direct TCR contacts with the mutation. We also review antibodies designed to recognize peptide-MHC on cell surfaces (TCR-mimic antibodies) as an alternative to TCRs for targeting cancer neoantigens. Finally, we review recent computational advances in this area, including efforts to predict neoepitope immunogenicity and how these efforts may be advanced by structural information on peptide-MHC binding and peptide-MHC recognition by TCRs.

Trade-offs inside the black box of neoantigen prediction

Success of precision neoantigen-based immunotherapies hinges on the selection of immunogenic neoantigens, yet currently neither large-scale datasets nor streamlined methods are available to achieve this goal. Müller et al. present a large experimental dataset resource along with machine learning-based models to classify immunogenic neoantigens.

Machine learning methods and harmonized datasets improve immunogenic neoantigen prediction

The accurate selection of neoantigens that bind to class I human leukocyte antigen (HLA) and are recognized by autologous T cells is a crucial step in many cancer immunotherapy pipelines. We reprocessed whole-exome sequencing and RNA sequencing (RNA-seq) data from 120 cancer patients from two external large-scale neoantigen immunogenicity screening assays combined with an in-house dataset of 11 patients and identified 46,017 somatic single-nucleotide variant mutations and 1,781,445 neo-peptides, of which 212 mutations and 178 neo-peptides were immunogenic. Beyond features commonly used for neoantigen prioritization, factors such as the location of neo-peptides within protein HLA presentation hotspots, binding promiscuity, and the role of the mutated gene in oncogenicity were predictive for immunogenicity. The classifiers accurately predicted neoantigen immunogenicity across datasets and improved their ranking by up to 30%. Besides insights into machine learning methods for neoantigen ranking, we have provided homogenized datasets valuable for developing and benchmarking companion algorithms for neoantigen-based immunotherapies.

Deep neural networks predict class I major histocompatibility complex epitope presentation and transfer learn neoepitope immunogenicity

Identifying neoepitopes that elicit an adaptive immune response is a major bottleneck to developing personalized cancer vaccines. Experimental validation of candidate neoepitopes is extremely resource intensive and the vast majority of candidates are non-immunogenic, creating a needle-in-a-haystack problem. Here we address this challenge, presenting computational methods for predicting class I major histocompatibility complex (MHC-I) epitopes and identifying immunogenic neoepitopes with improved precision. The BigMHC method comprises an ensemble of seven pan-allelic deep neural networks trained on peptide-MHC eluted ligand data from mass spectrometry assays and transfer learned on data from assays of antigen-specific immune response. Compared with four state-of-the-art classifiers, BigMHC significantly improves the prediction of epitope presentation on a test set of 45,409 MHC ligands among 900,592 random negatives (area under the receiver operating characteristic = 0.9733; area under the precision-recall curve = 0.8779). After transfer learning on immunogenicity data, BigMHC yields significantly higher precision than seven state-of-the-art models in identifying immunogenic neoepitopes, making BigMHC effective in clinical settings.

Cancer vaccines based on whole-tumor lysate or neoepitopes with validated HLA binding outperform those with predicted HLA-binding affinity

Antigen selection and prioritization represent crucial determinants of vaccines' efficacy. Here, we compare two personalized dendritic cell-based vaccination strategies using whole-tumor lysate or neoantigens. Data in mouse and in cancer patients demonstrate that peptide vaccines using neoantigens predicted on the sole basis of in silico peptide-major histocompatibility complex (MHC) binding affinity underperform relative to whole-tumor-lysate vaccines. In contrast, effective in vitro peptide-MHC binding affinity and peptide immunogenicity significantly improve the prioritization of tumor-rejecting neoepitopes and result in more efficacious vaccines.