Unsupervised HLA Peptidome Deconvolution Improves Ligand Prediction Accuracy and Predicts Cooperative Effects in Peptide-HLA Interactions

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.

3D genome contributes to MHC-II neoantigen prediction

Reliable and ultra-fast DNA and RNA sequencing have been achieved with the emergence of high-throughput sequencing technology. When combining the results of DNA and RNA sequencing for tumor cells of cancer patients, neoantigens that potentially stimulate the immune response of either CD4+ or CD8+ T cells can be identified. However, due to the abundance of somatic mutations and the high polymorphic nature of human leukocyte antigen (HLA) it is challenging to accurately predict the neoantigens. Moreover, comparing to HLA-I presented peptides, the HLA-II presented peptides are more variable in length, making the prediction of HLA-II loaded neoantigens even harder. A number of computational approaches have been proposed to address this issue but none of them considers the DNA origin of the neoantigens from the perspective of 3D genome. Here we investigate the DNA origins of the immune-positive and non-negative HLA-II neoantigens in the context of 3D genome and discovered that the chromatin 3D architecture plays an important role in more effective HLA-II neoantigen prediction. We believe that the 3D genome information will help to increase the precision of HLA-II neoantigen discovery and eventually benefit precision and personalized medicine in cancer immunotherapy.

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.

The HLA-II immunopeptidome of SARS-CoV-2

Targeted synthetic vaccines have the potential to transform our response to viral outbreaks, yet the design of these vaccines requires a comprehensive knowledge of viral immunogens. Here, we report severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) peptides that are naturally processed and loaded onto human leukocyte antigen-II (HLA-II) complexes in infected cells. We identify over 500 unique viral peptides from canonical proteins as well as from overlapping internal open reading frames. Most HLA-II peptides colocalize with known CD4+ T cell epitopes in coronavirus disease 2019 patients, including 2 reported immunodominant regions in the SARS-CoV-2 membrane protein. Overall, our analyses show that HLA-I and HLA-II pathways target distinct viral proteins, with the structural proteins accounting for most of the HLA-II peptidome and nonstructural and noncanonical proteins accounting for the majority of the HLA-I peptidome. These findings highlight the need for a vaccine design that incorporates multiple viral elements harboring CD4+ and CD8+ T cell epitopes to maximize vaccine effectiveness.

MHCpLogics: an interactive machine learning-based tool for unsupervised data visualization and cluster analysis of immunopeptidomes

The major histocompatibility complex (MHC) encodes a range of immune response genes, including the human leukocyte antigens (HLAs) in humans. These molecules bind peptide antigens and present them on the cell surface for T cell recognition. The repertoires of peptides presented by HLA molecules are termed immunopeptidomes. The highly polymorphic nature of the genres that encode the HLA molecules confers allotype-specific differences in the sequences of bound ligands. Allotype-specific ligand preferences are often defined by peptide-binding motifs. Individuals express up to six classical class I HLA allotypes, which likely present peptides displaying different binding motifs. Such complex datasets make the deconvolution of immunopeptidomic data into allotype-specific contributions and further dissection of binding-specificities challenging. Herein, we developed MHCpLogics as an interactive machine learning-based tool for mining peptide-binding sequence motifs and visualization of immunopeptidome data across complex datasets. We showcase the functionalities of MHCpLogics by analyzing both in-house and published mono- and multi-allelic immunopeptidomics data. The visualization modalities of MHCpLogics allow users to inspect clustered sequences down to individual peptide components and to examine broader sequence patterns within multiple immunopeptidome datasets. MHCpLogics can deconvolute large immunopeptidome datasets enabling the interrogation of clusters for the segregation of allotype-specific peptide sequence motifs, identification of sub-peptidome motifs, and the exportation of clustered peptide sequence lists. The tool facilitates rapid inspection of immunopeptidomes as a resource for the immunology and vaccine communities. MHCpLogics is a standalone application available via an executable installation at: https://github.com/PurcellLab/MHCpLogics.

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.

A robust deep learning workflow to predict CD8 + T-cell epitopes

BACKGROUND

T-cells play a crucial role in the adaptive immune system by triggering responses against cancer cells and pathogens, while maintaining tolerance against self-antigens, which has sparked interest in the development of various T-cell-focused immunotherapies. However, the identification of antigens recognised by T-cells is low-throughput and laborious. To overcome some of these limitations, computational methods for predicting CD8 + T-cell epitopes have emerged. Despite recent developments, most immunogenicity algorithms struggle to learn features of peptide immunogenicity from small datasets, suffer from HLA bias and are unable to reliably predict pathology-specific CD8 + T-cell epitopes.

METHODS

We developed TRAP (T-cell recognition potential of HLA-I presented peptides), a robust deep learning workflow for predicting CD8 + T-cell epitopes from MHC-I presented pathogenic and self-peptides. TRAP uses transfer learning, deep learning architecture and MHC binding information to make context-specific predictions of CD8 + T-cell epitopes. TRAP also detects low-confidence predictions for peptides that differ significantly from those in the training datasets to abstain from making incorrect predictions. To estimate the immunogenicity of pathogenic peptides with low-confidence predictions, we further developed a novel metric, RSAT (relative similarity to autoantigens and tumour-associated antigens), as a complementary to 'dissimilarity to self' from cancer studies.

RESULTS

TRAP was used to identify epitopes from glioblastoma patients as well as SARS-CoV-2 peptides, and it outperformed other algorithms in both cancer and pathogenic settings. TRAP was especially effective at extracting immunogenicity-associated properties from restricted data of emerging pathogens and translating them onto related species, as well as minimising the loss of likely epitopes in imbalanced datasets. We also demonstrated that the novel metric termed RSAT was able to estimate immunogenic of pathogenic peptides of various lengths and species. TRAP implementation is available at: https://github.com/ChloeHJ/TRAP .

CONCLUSIONS

This study presents a novel computational workflow for accurately predicting CD8 + T-cell epitopes to foster a better understanding of antigen-specific T-cell response and the development of effective clinical therapeutics.

Prioritizing candidate peptides for cancer vaccines through predicting peptide presentation by HLA-I proteins

Cancer (treatment) vaccines that are made of neoantigens, or peptides unique to tumor cells due to somatic mutations, have emerged as a promising method to reinvigorate the immune response against cancer. A key step to prioritizing neoantigens for cancer vaccines is computationally predicting which neoantigens are presented on the cell surface by a human leukocyte antigen (HLA). We propose to address this challenge by training a neural network using mass spectrometry (MS) data composed of peptides presented by at least one of several HLAs of a subject. We embed the neural network within a mixture model and train the neural network by maximizing the likelihood of the mixture model. After evaluating our method using data sets where the peptide presentation status was known, we applied it to analyze somatic mutations of 60 melanoma patients and identified a group of neoantigens more immunogenic in tumor cells than in normal cells. Moreover, neoantigen burden estimated by our method was significantly associated with a measurement of the immune system activity, suggesting these neoantigens could induce an immune response.

Improved prediction of MHC-peptide binding using protein language models

Major histocompatibility complex Class I (MHC-I) molecules bind to peptides derived from intracellular antigens and present them on the surface of cells, allowing the immune system (T cells) to detect them. Elucidating the process of this presentation is essential for regulation and potential manipulation of the cellular immune system. Predicting whether a given peptide binds to an MHC molecule is an important step in the above process and has motivated the introduction of many computational approaches to address this problem. NetMHCPan, a pan-specific model for predicting binding of peptides to any MHC molecule, is one of the most widely used methods which focuses on solving this binary classification problem using shallow neural networks. The recent successful results of Deep Learning (DL) methods, especially Natural Language Processing (NLP-based) pretrained models in various applications, including protein structure determination, motivated us to explore their use in this problem. Specifically, we consider the application of deep learning models pretrained on large datasets of protein sequences to predict MHC Class I-peptide binding. Using the standard performance metrics in this area, and the same training and test sets, we show that our models outperform NetMHCpan4.1, currently considered as the-state-of-the-art.

The HLA-II immunopeptidome of SARS-CoV-2

Targeted synthetic vaccines have the potential to transform our response to viral outbreaks; yet the design of these vaccines requires a comprehensive knowledge of viral immunogens, including T-cell epitopes. Having previously mapped the SARS-CoV-2 HLA-I landscape, here we report viral peptides that are naturally processed and loaded onto HLA-II complexes in infected cells. We identified over 500 unique viral peptides from canonical proteins, as well as from overlapping internal open reading frames (ORFs), revealing, for the first time, the contribution of internal ORFs to the HLA-II peptide repertoire. Most HLA-II peptides co-localized with the known CD4+ T cell epitopes in COVID-19 patients. We also observed that two reported immunodominant regions in the SARS-CoV-2 membrane protein are formed at the level of HLA-II presentation. Overall, our analyses show that HLA-I and HLA-II pathways target distinct viral proteins, with the structural proteins accounting for most of the HLA-II peptidome and non-structural and non-canonical proteins accounting for the majority of the HLA-I peptidome. These findings highlight the need for a vaccine design that incorporates multiple viral elements harboring CD4+ and CD8+ T cell epitopes to maximize the vaccine effectiveness.

The biogenesis of the immunopeptidome

The immunopeptidome is the repertoire of peptides bound and presented by the MHC class I, class II, and non-classical molecules. The peptides are produced by the degradation of most cellular proteins, and in some cases, peptides are produced from extracellular proteins taken up by the cells. This review attempts to first describe some of its known and well-accepted concepts, and next, raise some questions about a few of the established dogmas in this field: The production of novel peptides by splicing is questioned, suggesting here that spliced peptides are extremely rare, if existent at all. The degree of the contribution to the immunopeptidome by degradation of cellular protein by the proteasome is doubted, therefore this review attempts to explain why it is likely that this contribution to the immunopeptidome is possibly overstated. The contribution of defective ribosome products (DRiPs) and non-canonical peptides to the immunopeptidome is noted and methods are suggested to quantify them. In addition, the common misconception that the MHC class II peptidome is mostly derived from extracellular proteins is noted, and corrected. It is stressed that the confirmation of sequence assignments of non-canonical and spliced peptides should rely on targeted mass spectrometry using spiking-in of heavy isotope-labeled peptides. Finally, the new methodologies and modern instrumentation currently available for high throughput kinetics and quantitative immunopeptidomics are described. These advanced methods open up new possibilities for utilizing the big data generated and taking a fresh look at the established dogmas and reevaluating them critically.

The peptide woods are lovely, dark and deep: Hunting for novel cancer antigens

Harnessing the patient's immune system to control a tumor is a proven avenue for cancer therapy. T cell therapies as well as therapeutic vaccines, which target specific antigens of interest, are being explored as treatments in conjunction with immune checkpoint blockade. For these therapies, selecting the best suited antigens is crucial. Most of the focus has thus far been on neoantigens that arise from tumor-specific somatic mutations. Although there is clear evidence that T-cell responses against mutated neoantigens are protective, the large majority of these mutations are not immunogenic. In addition, most somatic mutations are unique to each individual patient and their targeting requires the development of individualized approaches. Therefore, novel antigen types are needed to broaden the scope of such treatments. We review high throughput approaches for discovering novel tumor antigens and some of the key challenges associated with their detection, and discuss considerations when selecting tumor antigens to target in the clinic.

The immunopeptidome landscape associated with T cell infiltration, inflammation and immune editing in lung cancer

One key barrier to improving efficacy of personalized cancer immunotherapies that are dependent on the tumor antigenic landscape remains patient stratification. Although patients with CD3⁺CD8⁺ T cell-inflamed tumors typically show better response to immune checkpoint inhibitors, it is still unknown whether the immunopeptidome repertoire presented in highly inflamed and noninflamed tumors is substantially different. We surveyed 61 tumor regions and adjacent nonmalignant lung tissues from 8 patients with lung cancer and performed deep antigen discovery combining immunopeptidomics, genomics, bulk and spatial transcriptomics, and explored the heterogeneous expression and presentation of tumor (neo)antigens. In the present study, we associated diverse immune cell populations with the immunopeptidome and found a relatively higher frequency of predicted neoantigens located within HLA-I presentation hotspots in CD3⁺CD8⁺ T cell-excluded tumors. We associated such neoantigens with immune recognition, supporting their involvement in immune editing. This could have implications for the choice of combination therapies tailored to the patient's mutanome and immune microenvironment.

Workflow enabling deepscale immunopeptidome, proteome, ubiquitylome, phosphoproteome, and acetylome analyses of sample-limited tissues

Serial multi-omic analysis of proteome, phosphoproteome, and acetylome provides insights into changes in protein expression, cell signaling, cross-talk and epigenetic pathways involved in disease pathology and treatment. However, ubiquitylome and HLA peptidome data collection used to understand protein degradation and antigen presentation have not together been serialized, and instead require separate samples for parallel processing using distinct protocols. Here we present MONTE, a highly sensitive multi-omic native tissue enrichment workflow, that enables serial, deep-scale analysis of HLA-I and HLA-II immunopeptidome, ubiquitylome, proteome, phosphoproteome, and acetylome from the same tissue sample. We demonstrate that the depth of coverage and quantitative precision of each 'ome is not compromised by serialization, and the addition of HLA immunopeptidomics enables the identification of peptides derived from cancer/testis antigens and patient specific neoantigens. We evaluate the technical feasibility of the MONTE workflow using a small cohort of patient lung adenocarcinoma tumors.

Artificial intelligence in cancer immunotherapy: Applications in neoantigen recognition, antibody design and immunotherapy response prediction

Cancer immunotherapy is a method of controlling and eliminating tumors by reactivating the body's cancer-immunity cycle and restoring its antitumor immune response. The increased availability of data, combined with advancements in high-performance computing and innovative artificial intelligence (AI) technology, has resulted in a rise in the use of AI in oncology research. State-of-the-art AI models for functional classification and prediction in immunotherapy research are increasingly used to support laboratory-based experiments. This review offers a glimpse of the current AI applications in immunotherapy, including neoantigen recognition, antibody design, and prediction of immunotherapy response. Advancing in this direction will result in more robust predictive models for developing better targets, drugs, and treatments, and these advancements will eventually make their way into the clinical setting, pushing AI forward in the field of precision oncology.

The impact of immunopeptidomics: From basic research to clinical implementation

The immunopeptidome is the set of peptides presented by the major histocompatibility complex (MHC) molecules, in humans also known as the human leukocyte antigen (HLA), on the surface of cells that mediate T-cell immunosurveillance. The immunopeptidome is a sampling of the cellular proteome and hence it contains information about the health state of cells. The peptide repertoire is influenced by intra- and extra-cellular perturbations - such as in the case of drug exposure, infection, or oncogenic transformation. Immunopeptidomics is the bioanalytical method by which the presented peptides are extracted from biological samples and analyzed by high-performance liquid chromatography coupled to tandem mass spectrometry (MS), resulting in a deep qualitative and quantitative snapshot of the immunopeptidome. In this review, we discuss published immunopeptidomics studies from recent years, grouped into three main domains: i) basic, ii) pre-clinical and iii) clinical research and applications. We review selected fundamental immunopeptidomics studies on the antigen processing and presentation machinery, on HLA restriction and studies that advanced our understanding of various diseases, and how exploration of the antigenic landscape allowed immune targeting at the pre-clinical stage, paving the way to pioneering exploratory clinical trials where immunopeptidomics is directly implemented in the conception of innovative treatments for cancer patients.

Contemplating immunopeptidomes to better predict them

The identification of T-cell epitopes is key for a complete molecular understanding of immune recognition mechanisms in infectious diseases, autoimmunity and cancer. T-cell epitopes further provide targets for personalized vaccines and T-cell therapy, with several therapeutic applications in cancer immunotherapy and elsewhere. T-cell epitopes consist of short peptides displayed on Major Histocompatibility Complex (MHC) molecules. The recent advances in mass spectrometry (MS) based technologies to profile the ensemble of peptides displayed on MHC molecules - the so-called immunopeptidome - had a major impact on our understanding of antigen presentation and MHC ligands. On the one hand, these techniques enabled researchers to directly identify hundreds of thousands of peptides presented on MHC molecules, including some that elicited T-cell recognition. On the other hand, the data collected in these experiments revealed fundamental properties of antigen presentation pathways and significantly improved our ability to predict naturally presented MHC ligands and T-cell epitopes across the wide spectrum of MHC alleles found in human and other organisms. Here we review recent computational developments to analyze experimentally determined immunopeptidomes and harness these data to improve our understanding of antigen presentation and MHC binding specificities, as well as our ability to predict MHC ligands. We further discuss the strengths and limitations of the latest approaches to move beyond predictions of antigen presentation and tackle the challenges of predicting TCR recognition and immunogenicity.

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

The recognition of pathogen or cancer-specific epitopes by CD8⁺ T cells is crucial for the clearance of infections and the response to cancer immunotherapy. This process requires epitopes to be presented on class I human leukocyte antigen (HLA-I) molecules and recognized by the T-cell receptor (TCR). Machine learning models capturing these two aspects of immune recognition are key to improve epitope predictions. Here, we assembled a high-quality dataset of naturally presented HLA-I ligands and experimentally verified neo-epitopes. We then integrated these data in a refined computational framework to predict antigen presentation (MixMHCpred2.2) and TCR recognition (PRIME2.0). The depth of our training data and the algorithmic developments resulted in improved predictions of HLA-I ligands and neo-epitopes. Prospectively applying our tools to SARS-CoV-2 proteins revealed several epitopes. TCR sequencing identified a monoclonal response in effector/memory CD8⁺ T cells against one of these epitopes and cross-reactivity with the homologous peptides from other coronaviruses.

The MHC Motif Atlas: a database of MHC binding specificities and ligands

The highly polymorphic Major Histocompatibility Complex (MHC) genes are responsible for the binding and cell surface presentation of pathogen or cancer specific T-cell epitopes. This process is fundamental for eliciting T-cell recognition of infected or malignant cells. Epitopes displayed on MHC molecules further provide therapeutic targets for personalized cancer vaccines or adoptive T-cell therapy. To help visualizing, analyzing and comparing the different binding specificities of MHC molecules, we developed the MHC Motif Atlas (http://mhcmotifatlas.org/). This database contains information about thousands of class I and class II MHC molecules, including binding motifs, peptide length distributions, motifs of phosphorylated ligands, multiple specificities or links to X-ray crystallography structures. The database further enables users to download curated datasets of MHC ligands. By combining intuitive visualization of the main binding properties of MHC molecules together with access to more than a million ligands, the MHC Motif Atlas provides a central resource to analyze and interpret the binding specificities of MHC molecules.

Immunopeptidomics-based design of mRNA vaccine formulations against Listeria monocytogenes

Listeria monocytogenes is a foodborne intracellular bacterial pathogen leading to human listeriosis. Despite a high mortality rate and increasing antibiotic resistance no clinically approved vaccine against Listeria is available. Attenuated Listeria strains offer protection and are tested as antitumor vaccine vectors, but would benefit from a better knowledge on immunodominant vector antigens. To identify novel antigens, we screen for Listeria peptides presented on the surface of infected human cell lines by mass spectrometry-based immunopeptidomics. In between more than 15,000 human self-peptides, we detect 68 Listeria immunopeptides from 42 different bacterial proteins, including several known antigens. Peptides presented on different cell lines are often derived from the same bacterial surface proteins, classifying these antigens as potential vaccine candidates. Encoding these highly presented antigens in lipid nanoparticle mRNA vaccine formulations results in specific CD8+ T-cell responses and induces protection in vaccination challenge experiments in mice. Our results can serve as a starting point for the development of a clinical mRNA vaccine against Listeria and aid to improve attenuated Listeria vaccines and vectors, demonstrating the power of immunopeptidomics for next-generation bacterial vaccine development.

Charge-based interactions through peptide position 4 drive diversity of antigen presentation by human leukocyte antigen class I molecules

Human leukocyte antigen class I (HLA-I) molecules bind and present peptides at the cell surface to facilitate the induction of appropriate CD8+ T cell-mediated immune responses to pathogen- and self-derived proteins. The HLA-I peptide-binding cleft contains dominant anchor sites in the B and F pockets that interact primarily with amino acids at peptide position 2 and the C-terminus, respectively. Nonpocket peptide-HLA interactions also contribute to peptide binding and stability, but these secondary interactions are thought to be unique to individual HLA allotypes or to specific peptide antigens. Here, we show that two positively charged residues located near the top of peptide-binding cleft facilitate interactions with negatively charged residues at position 4 of presented peptides, which occur at elevated frequencies across most HLA-I allotypes. Loss of these interactions was shown to impair HLA-I/peptide binding and complex stability, as demonstrated by both in vitro and in silico experiments. Furthermore, mutation of these Arginine-65 (R65) and/or Lysine-66 (K66) residues in HLA-A*02:01 and A*24:02 significantly reduced HLA-I cell surface expression while also reducing the diversity of the presented peptide repertoire by up to 5-fold. The impact of the R65 mutation demonstrates that nonpocket HLA-I/peptide interactions can constitute anchor motifs that exert an unexpectedly broad influence on HLA-I-mediated antigen presentation. These findings provide fundamental insights into peptide antigen binding that could broadly inform epitope discovery in the context of viral vaccine development and cancer immunotherapy.

A streamlined platform for analyzing tera-scale DDA and DIA mass spectrometry data enables highly sensitive immunopeptidomics

Integrating data-dependent acquisition (DDA) and data-independent acquisition (DIA) approaches can enable highly sensitive mass spectrometry, especially for imunnopeptidomics applications. Here we report a streamlined platform for both DDA and DIA data analysis. The platform integrates deep learning-based solutions of spectral library search, database search, and de novo sequencing under a unified framework, which not only boosts the sensitivity but also accurately controls the specificity of peptide identification. Our platform identifies 5-30% more peptide precursors than other state-of-the-art systems on multiple benchmark datasets. When evaluated on immunopeptidomics datasets, we identify 1.7-4.1 and 1.4-2.2 times more peptides from DDA and DIA data, respectively, than previously reported results. We also discover six T-cell epitopes from SARS-CoV-2 immunopeptidome that might represent potential targets for COVID-19 vaccine development. The platform supports data formats from all major instruments and is implemented with the distributed high-performance computing technology, allowing analysis of tera-scale datasets of thousands of samples for clinical applications.

T Cell Epitope Discovery in the Context of Distinct and Unique Indigenous HLA Profiles

CD8+ T cells are a pivotal part of the immune response to viruses, playing a key role in disease outcome and providing long-lasting immunity to conserved pathogen epitopes. Understanding CD8+ T cell immunity in humans is complex due to CD8+ T cell restriction by highly polymorphic Human Leukocyte Antigen (HLA) proteins, requiring T cell epitopes to be defined for different HLA allotypes across different ethnicities. Here we evaluate strategies that have been developed to facilitate epitope identification and study immunogenic T cell responses. We describe an immunopeptidomics approach to sequence HLA-bound peptides presented on virus-infected cells by liquid chromatography with tandem mass spectrometry (LC-MS/MS). Using antigen presenting cell lines that stably express the HLA alleles characteristic of Indigenous Australians, this approach has been successfully used to comprehensively identify influenza-specific CD8+ T cell epitopes restricted by HLA allotypes predominant in Indigenous Australians, including HLA-A*24:02 and HLA-A*11:01. This is an essential step in ensuring high vaccine coverage and efficacy in Indigenous populations globally, known to be at high risk from influenza disease and other respiratory infections.

Evaluating performance of existing computational models in predicting CD8+ T cell pathogenic epitopes and cancer neoantigens

T cell recognition of a cognate peptide-major histocompatibility complex (pMHC) presented on the surface of infected or malignant cells is of the utmost importance for mediating robust and long-term immune responses. Accurate predictions of cognate pMHC targets for T cell receptors would greatly facilitate identification of vaccine targets for both pathogenic diseases and personalized cancer immunotherapies. Predicting immunogenic peptides therefore has been at the center of intensive research for the past decades but has proven challenging. Although numerous models have been proposed, performance of these models has not been systematically evaluated and their success rate in predicting epitopes in the context of human pathology has not been measured and compared. In this study, we evaluated the performance of several publicly available models, in identifying immunogenic CD8+ T cell targets in the context of pathogens and cancers. We found that for predicting immunogenic peptides from an emerging virus such as severe acute respiratory syndrome coronavirus 2, none of the models perform substantially better than random or offer considerable improvement beyond HLA ligand prediction. We also observed suboptimal performance for predicting cancer neoantigens. Through investigation of potential factors associated with ill performance of models, we highlight several data- and model-associated issues. In particular, we observed that cross-HLA variation in the distribution of immunogenic and non-immunogenic peptides in the training data of the models seems to substantially confound the predictions. We additionally compared key parameters associated with immunogenicity between pathogenic peptides and cancer neoantigens and observed evidence for differences in the thresholds of binding affinity and stability, which suggested the need to modulate different features in identifying immunogenic pathogen versus cancer peptides. Overall, we demonstrate that accurate and reliable predictions of immunogenic CD8+ T cell targets remain unsolved; thus, we hope our work will guide users and model developers regarding potential pitfalls and unsettled questions in existing immunogenicity predictors.

Unsupervised Mining of HLA-I Peptidomes Reveals New Binding Motifs and Potential False Positives in the Community Database

Modern vaccine designs and studies of human leukocyte antigen (HLA)-mediated immune responses rely heavily on the knowledge of HLA allele-specific binding motifs and computational prediction of HLA-peptide binding affinity. Breakthroughs in HLA peptidomics have considerably expanded the databases of natural HLA ligands and enabled detailed characterizations of HLA-peptide binding specificity. However, cautions must be made when analyzing HLA peptidomics data because identified peptides may be contaminants in mass spectrometry or may weakly bind to the HLA molecules. Here, a hybrid de novo peptide sequencing approach was applied to large-scale mono-allelic HLA peptidomics datasets to uncover new ligands and refine current knowledge of HLA binding motifs. Up to 12-40% of the peptidomics data were low-binding affinity peptides with an arginine or a lysine at the C-terminus and likely to be tryptic peptide contaminants. Thousands of these peptides have been reported in a community database as legitimate ligands and might be erroneously used for training prediction models. Furthermore, unsupervised clustering of identified ligands revealed additional binding motifs for several HLA class I alleles and effectively isolated outliers that were experimentally confirmed to be false positives. Overall, our findings expanded the knowledge of HLA binding specificity and advocated for more rigorous interpretation of HLA peptidomics data that will ensure the high validity of community HLA ligandome databases.

The interdependence of machine learning and LC-MS approaches for an unbiased understanding of the cellular immunopeptidome

INTRODUCTION

The comprehensive collection of peptides presented by Major Histocompatibility Complex (MHC) molecules on the cell surface is collectively known as the immunopeptidome. The analysis and interpretation of such data sets holds great promise for furthering our understanding of basic immunology and adaptive immune activation and regulation, and for direct rational discovery of T cell antigens and the design of T-cell based therapeutics and vaccines. These applications are however challenged by the complex nature of immunopeptidome data.

AREAS COVERED

Here, we describe the benefits and shortcomings of applying liquid chromatography-tandem mass spectrometry (MS) to obtain large scale immunopeptidome data sets and illustrate how the accurate analysis and optimal interpretation of such data is reliant on the availability of refined and highly optimized machine learning approaches.

EXPERT OPINION

Further we demonstrate how the accuracy of immunoinformatics prediction methods within the field of MHC antigen presentation has benefited greatly from the availability of MS-immunopeptidomics data, and exemplify how optimal antigen discovery is best performed in a synergistic combination of MS experiments and such in silico models trained on large scale immunopeptidomics data.

Accurate MHC Motif Deconvolution of Immunopeptidomics Data Reveals a Significant Contribution of DRB3, 4 and 5 to the Total DR Immunopeptidome

Mass spectrometry (MS) based immunopeptidomics is used in several biomedical applications including neo-epitope discovery in oncology, next-generation vaccine development and protein-drug immunogenicity assessment. Immunopeptidome data are highly complex given the expression of multiple HLA alleles on the cell membrane and presence of co-immunoprecipitated contaminants. The absence of tools that deal with these challenges effectively and guide the analysis and interpretation of this complex type of data is currently a major bottleneck for the large-scale application of this technique. To resolve this, we here present the MHCMotifDecon that benefits from state-of-the-art HLA class-I and class-II predictions to accurately deconvolute immunopeptidome datasets and assign individual ligands to the most likely HLA molecule, allowing to identify and characterize HLA binding motifs while discarding co-purified contaminants. We have benchmarked the tool against other state-of-the-art methods and illustrated its application on experimental datasets for HLA-DR demonstrating a previously underappreciated role for HLA-DRB3/4/5 molecules in defining HLA class II immune repertoires. With its ease of use, MHCMotifDecon can efficiently guide interpretation of immunopeptidome datasets, serving the discovery of novel T cell targets. MHCMotifDecon is available at https://services.healthtech.dtu.dk/service.php?MHCMotifDecon-1.0.

Bedside formulation of a personalized multi-neoantigen vaccine against mammary carcinoma

Background

Harnessing the immune system to purposely recognize and destroy tumors represents a significant breakthrough in clinical oncology. Non-synonymous mutations (neoantigenic peptides) were identified as powerful cancer targets. This knowledge can be exploited for further improvements of active immunotherapies, including cancer vaccines, as T cells specific for neoantigens are not attenuated by immune tolerance mechanism and do not harm healthy tissues. The current study aimed at developing an optimized multitarget vaccine using short or long neoantigenic peptides utilizing virus-like particles (VLPs) as an efficient vaccine platform.

Methods

Mutations of murine mammary carcinoma cells were identified by integrating mass spectrometry-based immunopeptidomics and whole exome sequencing. Neoantigenic peptides were synthesized and covalently linked to virus-like nanoparticles using a Cu-free click chemistry method for easy preparation of vaccines against mouse mammary carcinoma.

Results

As compared with short peptides, vaccination with long peptides was superior in the generation of neoantigen-specific CD4⁺ and CD8⁺ T cells, which readily produced interferon gamma (IFN-γ) and tumor-necrosis factor α (TNF-α). The resulting anti-tumor effect was associated with favorable immune re-polarization in the tumor microenvironment through reduction of myeloid-derived suppressor cells. Vaccination with long neoantigenic peptides also decreased post-surgical tumor recurrence and metastases, and prolonged mouse survival, despite the tumor’s low mutational burden.

Conclusion

Integrating mass spectrometry-based immunopeptidomics and whole exome sequencing is an efficient approach for identifying neoantigenic peptides. Our multitarget VLP-based vaccine shows a promising anti-tumor effect in an aggressive murine mammary carcinoma model. Future clinical application using this strategy is readily feasible and practical, as click chemistry coupling of personalized synthetic peptides to the nanoparticles can be done at the bedside directly before injection.

Immunopeptidomic analysis of influenza A virus infected human tissues identifies internal proteins as a rich source of HLA ligands

CD8+ and CD4+ T cells provide cell-mediated cross-protection against multiple influenza strains by recognising epitopes bound as peptides to human leukocyte antigen (HLA) class I and -II molecules respectively. Two challenges in identifying the immunodominant epitopes needed to generate a universal T cell influenza vaccine are: A lack of cell models susceptible to influenza infection which present population-prevalent HLA allotypes, and an absence of a reliable in-vitro method of identifying class II HLA peptides. Here we present a mass spectrometry-based proteomics strategy for identifying viral peptides derived from the A/H3N2/X31 and A/H3N2/Wisconsin/67/2005 strains of influenza. We compared the HLA-I and -II immunopeptidomes presented by ex-vivo influenza challenged human lung tissues. We then compared these with directly infected immortalised macrophage-like cell line (THP1) and primary dendritic cells fed apoptotic influenza-infected respiratory epithelial cells. In each of the three experimental conditions we identified novel influenza class I and II HLA peptides with motifs specific for the host allotype. Ex-vivo infected lung tissues yielded few class-II HLA peptides despite significant numbers of alveolar macrophages, including directly infected ones, present within the tissues. THP1 cells presented HLA-I viral peptides derived predominantly from internal proteins. Primary dendritic cells presented predominantly viral envelope-derived HLA class II peptides following phagocytosis of apoptotic infected cells. The most frequent viral source protein for HLA-I and -II was matrix 1 protein (M1). This work confirms that internal influenza proteins, particularly M1, are a rich source of CD4+ and CD8+ T cell epitopes. Moreover, we demonstrate the utility of two ex-vivo fully human infection models which enable direct HLA-I and -II immunopeptide identification without significant viral tropism limitations. Application of this epitope discovery strategy in a clinical setting will provide more certainty in rational vaccine design against influenza and other emergent viruses.

CAMAP: Artificial neural networks unveil the role of codon arrangement in modulating MHC-I peptides presentation

MHC-I associated peptides (MAPs) play a central role in the elimination of virus-infected and neoplastic cells by CD8 T cells. However, accurately predicting the MAP repertoire remains difficult, because only a fraction of the transcriptome generates MAPs. In this study, we investigated whether codon arrangement (usage and placement) regulates MAP biogenesis. We developed an artificial neural network called Codon Arrangement MAP Predictor (CAMAP), predicting MAP presentation solely from mRNA sequences flanking the MAP-coding codons (MCCs), while excluding the MCC per se. CAMAP predictions were significantly more accurate when using original codon sequences than shuffled codon sequences which reflect amino acid usage. Furthermore, predictions were independent of mRNA expression and MAP binding affinity to MHC-I molecules and applied to several cell types and species. Combining MAP ligand scores, transcript expression level and CAMAP scores was particularly useful to increase MAP prediction accuracy. Using an in vitro assay, we showed that varying the synonymous codons in the regions flanking the MCCs (without changing the amino acid sequence) resulted in significant modulation of MAP presentation at the cell surface. Taken together, our results demonstrate the role of codon arrangement in the regulation of MAP presentation and support integration of both translational and post-translational events in predictive algorithms to ameliorate modeling of the immunopeptidome.

MHC-I associated peptides (MAPs) are small fragments of intracellular proteins presented at the surface of cells and used by the immune system to detect and eliminate cancerous or virus-infected cells. While it is theoretically possible to predict which portions of the intracellular proteins will be naturally processed by the cells to ultimately reach the surface, current methodologies have prohibitively high false discovery rates. Here we introduce an artificial neural network called Codon Arrangement MAP Predictor (CAMAP) which integrates information from mRNA-to-protein translation to other factors regulating MAP biogenesis (e.g. MAP ligand score and transcript expression levels) to improve MAP prediction accuracy. While most MAP predictive approaches focus on MAP sequences per se, CAMAP’s novelty is to analyze the MAP-flanking mRNA sequences, thereby providing completely independent information for MAP prediction. We show on several datasets that the integration of CAMAP scores with other known factors involved in MAP presentation (i.e. MAP ligand score and mRNA expression) significantly improves MAP prediction accuracy, and further validate CAMAP learned features using an in-vitro assay. These findings may have major implications for the design of vaccines against cancers and viruses, and in times of pandemics could accelerate the identification of relevant MAPs of viral origins.

Connecting MHC-I-binding motifs with HLA alleles via deep learning

The selection of peptides presented by MHC molecules is crucial for antigen discovery. Previously, several predictors have shown impressive performance on binding affinity. However, the decisive MHC residues and their relation to the selection of binding peptides are still unrevealed. Here, we connected HLA alleles with binding motifs via our deep learning-based framework, MHCfovea. MHCfovea expanded the knowledge of MHC-I-binding motifs from 150 to 13,008 alleles. After clustering N-terminal and C-terminal sub-motifs on both observed and unobserved alleles, MHCfovea calculated the hyper-motifs and the corresponding allele signatures on the important positions to disclose the relation between binding motifs and MHC-I sequences. MHCfovea delivered 32 pairs of hyper-motifs and allele signatures (HLA-A: 13, HLA-B: 12, and HLA-C: 7). The paired hyper-motifs and allele signatures disclosed the critical polymorphic residues that determine the binding preference, which are believed to be valuable for antigen discovery and vaccine design when allele specificity is concerned.

Ko-Han Lee et al. develop MHCfovea, a machine-learning method for predicting peptide-binding by MHC molecules and inferring peptide motifs and MHC allele signatures. They demonstrate that MHCfovea is capable of detecting meaningful hyper-motifs and allele signatures, making it a useful resource for the community.

Characterization of the Class I MHC Peptidome Resulting From DNCB Exposure of HaCaT Cells

Skin sensitization following the covalent modification of proteins by low molecular weight chemicals (haptenation) is mediated by cytotoxic T lymphocyte (CTL) recognition of human leukocyte antigen (HLA) molecules presented on the surface of almost all nucleated cells. There exist 3 nonmutually exclusive hypotheses for how haptens mediate CTL recognition: direct stimulation by haptenated peptides, hapten modification of HLA leading to an altered HLA-peptide repertoire, or a hapten altered proteome leading to an altered HLA-peptide repertoire. To shed light on the mechanism underpinning skin sensitization, we set out to utilize proteomic analysis of keratinocyte presented antigens following exposure to 2,4-dinitrochlorobenzene (DNCB). We show that the following DNCB exposure, cultured keratinocytes present cysteine haptenated (dinitrophenylated) peptides in multiple HLA molecules. In addition, we find that one of the DNCB modified peptides derives from the active site of cytosolic glutathione-S transferase-ω. These results support the current view that a key mechanism of skin sensitization is stimulation of CTLs by haptenated peptides. Data are available via ProteomeXchange with identifier PXD021373.

The Choice of Search Engine Affects Sequencing Depth and HLA Class I Allele-Specific Peptide Repertoires

Standardization of immunopeptidomics experiments across laboratories is a pressing issue within the field, and currently a variety of different methods for sample preparation and data analysis tools are applied. Here, we compared different software packages to interrogate immunopeptidomics datasets and found that Peaks reproducibly reports substantially more peptide sequences (~30-70%) compared with Maxquant, Comet, and MS-GF+ at a global false discovery rate (FDR) of <1%. We noted that these differences are driven by search space and spectral ranking. Furthermore, we observed differences in the proportion of peptides binding the human leukocyte antigen (HLA) alleles present in the samples, indicating that sequence-related differences affected the performance of each tested engine. Utilizing data from single HLA allele expressing cell lines, we observed significant differences in amino acid frequency among the peptides reported, with a broadly higher representation of hydrophobic amino acids L, I, P, and V reported by Peaks. We validated these results using data generated with a synthetic library of 2000 HLA-associated peptides from four common HLA alleles with distinct anchor residues. Our investigation highlights that search engines create a bias in peptide sequence depth and peptide amino acid composition, and resulting data should be interpreted with caution.

Profiling SARS-CoV-2 HLA-I peptidome reveals T cell epitopes from out-of-frame ORFs

T cell-mediated immunity plays an important role in controlling SARS-CoV-2 infection, but the repertoire of naturally processed and presented viral epitopes on class I human leukocyte antigen (HLA-I) remains uncharacterized. Here, we report the first HLA-I immunopeptidome of SARS-CoV-2 in two cell lines at different times post infection using mass spectrometry. We found HLA-I peptides derived not only from canonical open reading frames (ORFs) but also from internal out-of-frame ORFs in spike and nucleocapsid not captured by current vaccines. Some peptides from out-of-frame ORFs elicited T cell responses in a humanized mouse model and individuals with COVID-19 that exceeded responses to canonical peptides, including some of the strongest epitopes reported to date. Whole-proteome analysis of infected cells revealed that early expressed viral proteins contribute more to HLA-I presentation and immunogenicity. These biological insights, as well as the discovery of out-of-frame ORF epitopes, will facilitate selection of peptides for immune monitoring and vaccine development.

Challenges targeting cancer neoantigens in 2021: a systematic literature review

Introduction: Cancer neoantigens represent important targets of cancer immunotherapy. The goal of cancer neoantigen vaccines is to induce neoantigen-specific immune responses and antitumor immunity while minimizing the potential for autoimmune toxicity. Advances in sequencing technologies, neoantigen prediction algorithms, and other technologies have dramatically improved the ability to identify and prioritize cancer neoantigens. Unfortunately, results from preclinical studies and early phase clinical trials highlight important challenges to the successful clinical translation of neoantigen cancer vaccines.Areas covered: In this review, we provide an overview of current strategies for the identification and prioritization of cancer neoantigens with a particular emphasis on the two most common strategies used for neoantigen identification: (1) direct identification of peptide ligands eluted from peptide-MHC complexes, and (2) next-generation sequencing combined with neoantigen prediction algorithms. We highlight the limitations of current neoantigen prediction pipelines, and discuss broader challenges associated with cancer neoantigen vaccines including tumor purity/heterogeneity and the immunosuppressive tumor microenvironment.Expert opinion: Despite current limitations, neoantigen prediction is likely to improve rapidly based on advances in sequencing, machine learning, and information sharing. The successful development of robust cancer neoantigen prediction strategies is likely to have a significant impact, with the potential to facilitate cancer neoantigen vaccine design.

BERTMHC: Improved MHC-peptide class II interaction prediction with transformer and multiple instance learning

Motivation

Increasingly comprehensive characterization of cancer-associated genetic alterations has paved the way for the development of highly specific therapeutic vaccines. Predicting precisely the binding and presentation of peptides to major histocompatibility complex (MHC) alleles is an important step toward such therapies. Recent data suggest that presentation of both class I and II epitopes are critical for the induction of a sustained effective immune response. However, the prediction performance for MHC class II has been limited compared to class I.

Results

We present a transformer neural network model which leverages self-supervised pretraining from a large corpus of protein sequences. We also propose a multiple instance learning (MIL) framework to deconvolve mass spectrometry data where multiple potential MHC alleles may have presented each peptide. We show that pretraining boosted the performance for these tasks. Combining pretraining and the novel MIL approach, our model outperforms state-of-the-art models based on peptide and MHC sequence only for both binding and cell surface presentation predictions.

Availability and implementation

Our source code is available at https://github.com/s6juncheng/BERTMHC under a noncommercial license. A webserver is available at https://bertmhc.privacy.nlehd.de/

Supplementary information

Supplementary data are available at Bioinformatics online.

DeepNetBim: deep learning model for predicting HLA-epitope interactions based on network analysis by harnessing binding and immunogenicity information

BACKGROUND

Epitope prediction is a useful approach in cancer immunology and immunotherapy. Many computational methods, including machine learning and network analysis, have been developed quickly for such purposes. However, regarding clinical applications, the existing tools are insufficient because few of the predicted binding molecules are immunogenic. Hence, to develop more potent and effective vaccines, it is important to understand binding and immunogenic potential. Here, we observed that the interactive association constituted by human leukocyte antigen (HLA)-peptide pairs can be regarded as a network in which each HLA and peptide is taken as a node. We speculated whether this network could detect the essential interactive propensities embedded in HLA-peptide pairs. Thus, we developed a network-based deep learning method called DeepNetBim by harnessing binding and immunogenic information to predict HLA-peptide interactions.

RESULTS

Quantitative class I HLA-peptide binding data and qualitative immunogenic data (including data generated from T cell activation assays, major histocompatibility complex (MHC) binding assays and MHC ligand elution assays) were retrieved from the Immune Epitope Database database. The weighted HLA-peptide binding network and immunogenic network were integrated into a network-based deep learning algorithm constituted by a convolutional neural network and an attention mechanism. The results showed that the integration of network centrality metrics increased the power of both binding and immunogenicity predictions, while the new model significantly outperformed those that did not include network features and those with shuffled networks. Applied on benchmark and independent datasets, DeepNetBim achieved an AUC score of 93.74% in HLA-peptide binding prediction, outperforming 11 state-of-the-art relevant models. Furthermore, the performance enhancement of the combined model, which filtered out negative immunogenic predictions, was confirmed on neoantigen identification by an increase in both positive predictive value (PPV) and the proportion of neoantigen recognition.

CONCLUSIONS

We developed a network-based deep learning method called DeepNetBim as a pan-specific epitope prediction tool. It extracted the attributes of the network as new features from HLA-peptide binding and immunogenic models. We observed that not only did DeepNetBim binding model outperform other updated methods but the combination of our two models showed better performance. This indicates further applications in clinical practice.

Proteogenomic interrogation of cancer cell lines: an overview of the field

Introduction: Cancer cell lines (CCLs) have been a major resource for cancer research. Over the past couple of decades, they have been instrumental in omic profiling method development and as model systems to generate new knowledge in cell and cancer biology. More recently, with the increasing amount of genomic, transcriptomic and proteomic data being generated in hundreds of CCLs, there is growing potential for integrative proteogenomic data analyses to be performed.Areas covered: In this review, we first describe the most commonly used proteome profiling methods in CCLs. We then discuss how these proteomics data can be integrated with genomics data for proteogenomics analyses. Finally, we highlight some of the recent biological discoveries that have arisen from proteogenomics analyses of CCLs.Expert opinion: Protegeonomics analyses of CCLs have so far enabled the discovery of novel proteins and proteoforms. It has also improved our understanding of biological processes including post-transcriptional regulation of protein abundance and the presentation of antigens by major histocompatibility complex alleles. With proteomics data to be generated in hundreds to thousands of CCLs in coming years, there will be further potential for large-scale proteogenomics analyses and data integration with the phenotypically well-characterized CCLs.

Applications of Machine and Deep Learning in Adaptive Immunity

Adaptive immunity is mediated by lymphocyte B and T cells, which respectively express a vast and diverse repertoire of B cell and T cell receptors and, in conjunction with peptide antigen presentation through major histocompatibility complexes (MHCs), can recognize and respond to pathogens and diseased cells. In recent years, advances in deep sequencing have led to a massive increase in the amount of adaptive immune receptor repertoire data; additionally, proteomics techniques have led to a wealth of data on peptide-MHC presentation. These large-scale data sets are now making it possible to train machine and deep learning models, which can be used to identify complex and high-dimensional patterns in immune repertoires. This article introduces adaptive immune repertoires and machine and deep learning related to biological sequence data and then summarizes the many applications in this field, which span from predicting the immunological status of a host to the antigen specificity of individual receptors and the engineering of immunotherapeutics.

Sensitive Immunopeptidomics by Leveraging Available Large-Scale Multi-HLA Spectral Libraries, Data-Independent Acquisition, and MS/MS Prediction

Mass spectrometry (MS) is the state-of-the-art methodology for capturing the breadth and depth of the immunopeptidome across human leukocyte antigen (HLA) allotypes and cell types. The majority of studies in the immunopeptidomics field are discovery driven. Hence, data-dependent tandem MS (MS/MS) acquisition (DDA) is widely used, as it generates high-quality references of peptide fingerprints. However, DDA suffers from the stochastic selection of abundant ions that impairs sensitivity and reproducibility. In contrast, in data-independent acquisition (DIA), the systematic fragmentation and acquisition of all fragment ions within given isolation m/z windows yield a comprehensive map for a given sample. However, many DIA approaches commonly require generating comprehensive DDA-based spectrum libraries, which can become impractical for studying noncanonical and personalized neoantigens. Because the amount of HLA peptides eluted from biological samples such as small tissue biopsies is typically not sufficient for acquiring both meaningful DDA data necessary for generating comprehensive spectral libraries and DIA MS measurements, the implementation of DIA in the immunopeptidomics translational research domain has remained limited. We implemented a DIA immunopeptidomics workflow and assessed its sensitivity and accuracy by matching DIA data against libraries with growing complexity-from sample-specific libraries to libraries combining 2 to 40 different immunopeptidomics samples. Analyzing DIA immunopeptidomics data against a complex multi-HLA spectral library resulted in a two-fold increase in peptide identification compared with sample-specific library and in a three-fold increase compared with DDA measurements, yet with no detrimental effect on the specificity. Furthermore, we demonstrated the implementation of DIA for sensitive personalized neoantigen discovery through the analysis of DIA data with predicted MS/MS spectra of clinically relevant HLA ligands. We conclude that a comprehensive multi-HLA library for DIA approach in combination with MS/MS prediction is highly advantageous for clinical immunopeptidomics, especially when low amounts of biological samples are available.

Integral Use of Immunopeptidomics and Immunoinformatics for the Characterization of Antigen Presentation and Rational Identification of BoLA-DR-Presented Peptides and Epitopes

MHC peptide binding and presentation is the most selective event defining the landscape of T cell epitopes. Consequently, understanding the diversity of MHC alleles in a given population and the parameters that define the set of ligands that can be bound and presented by each of these alleles (the immunopeptidome) has an enormous impact on our capacity to predict and manipulate the potential of protein Ags to elicit functional T cell responses. Liquid chromatography-mass spectrometry analysis of MHC-eluted ligand data has proven to be a powerful technique for identifying such peptidomes, and methods integrating such data for prediction of Ag presentation have reached a high level of accuracy for both MHC class I and class II. In this study, we demonstrate how these techniques and prediction methods can be readily extended to the bovine leukocyte Ag class II DR locus (BoLA-DR). BoLA-DR binding motifs were characterized by eluted ligand data derived from bovine cell lines expressing a range of DRB3 alleles prevalent in Holstein-Friesian populations. The model generated (NetBoLAIIpan, available as a Web server at www.cbs.dtu.dk/services/NetBoLAIIpan) was shown to have unprecedented predictive power to identify known BoLA-DR-restricted CD4 epitopes. In summary, the results demonstrate the power of an integrated approach combining advanced mass spectrometry peptidomics with immunoinformatics for characterization of the BoLA-DR Ag presentation system and provide a prediction tool that can be used to assist in rational evaluation and selection of bovine CD4 T cell epitopes.

CIITA-Transduced Glioblastoma Cells Uncover a Rich Repertoire of Clinically Relevant Tumor-Associated HLA-II Antigens

CD4+ T cell responses are crucial for inducing and maintaining effective anticancer immunity, and the identification of human leukocyte antigen class II (HLA-II) cancer-specific epitopes is key to the development of potent cancer immunotherapies. In many tumor types, and especially in glioblastoma (GBM), HLA-II complexes are hardly ever naturally expressed. Hence, little is known about immunogenic HLA-II epitopes in GBM. With stable expression of the class II major histocompatibility complex transactivator (CIITA) coupled to a detailed and sensitive mass spectrometry-based immunopeptidomics analysis, we here uncovered a remarkable breadth of the HLA-ligandome in HROG02, HROG17, and RA GBM cell lines. The effect of CIITA expression on the induction of the HLA-II presentation machinery was striking in each of the three cell lines, and it was significantly higher compared with interferon gamma (IFNɣ) treatment. In total, we identified 16,123 unique HLA-I peptides and 32,690 unique HLA-II peptides. In order to genuinely define the identified peptides as true HLA ligands, we carefully characterized their association with the different HLA allotypes. In addition, we identified 138 and 279 HLA-I and HLA-II ligands, respectively, most of which are novel in GBM, derived from known GBM-associated tumor antigens that have been used as source proteins for a variety of GBM vaccines. Our data further indicate that CIITA-expressing GBM cells acquired an antigen presenting cell-like phenotype as we found that they directly present external proteins as HLA-II ligands. Not only that CIITA-expressing GBM cells are attractive models for antigen discovery endeavors, but also such engineered cells have great therapeutic potential through massive presentation of a diverse antigenic repertoire.

RBM-MHC: A Semi-Supervised Machine-Learning Method for Sample-Specific Prediction of Antigen Presentation by HLA-I Alleles

The recent increase of immunopeptidomics data, obtained by mass spectrometry or binding assays, opens up possibilities for investigating endogenous antigen presentation by the highly polymorphic human leukocyte antigen class I (HLA-I) protein. State-of-the-art methods predict with high accuracy presentation by HLA alleles that are well represented in databases at the time of release but have a poorer performance for rarer and less characterized alleles. Here, we introduce a method based on Restricted Boltzmann Machines (RBMs) for prediction of antigens presented on the Major Histocompatibility Complex (MHC) encoded by HLA genes-RBM-MHC. RBM-MHC can be trained on custom and newly available samples with no or a small amount of HLA annotations. RBM-MHC ensures improved predictions for rare alleles and matches state-of-the-art performance for well-characterized alleles while being less data demanding. RBM-MHC is shown to be a flexible and easily interpretable method that can be used as a predictor of cancer neoantigens and viral epitopes, as a tool for feature discovery, and to reconstruct peptide motifs presented on specific HLA molecules.

SARS-CoV-2 infected cells present HLA-I peptides from canonical and out-of-frame ORFs

T cell-mediated immunity may play a critical role in controlling and establishing protective immunity against SARS-CoV-2 infection; yet the repertoire of viral epitopes responsible for T cell response activation remains mostly unknown. Identification of viral peptides presented on class I human leukocyte antigen (HLA-I) can reveal epitopes for recognition by cytotoxic T cells and potential incorporation into vaccines. Here, we report the first HLA-I immunopeptidome of SARS-CoV-2 in two human cell lines at different times post-infection using mass spectrometry. We found HLA-I peptides derived not only from canonical ORFs, but also from internal out-of-frame ORFs in Spike and Nucleoprotein not captured by current vaccines. Proteomics analyses of infected cells revealed that SARS-CoV-2 may interfere with antigen processing and immune signaling pathways. Based on the endogenously processed and presented viral peptides that we identified, we estimate that a pool of 24 peptides would provide one or more peptides for presentation by at least one HLA allele in 99% of the human population. These biological insights and the list of naturally presented SARS-CoV-2 peptides will facilitate data-driven selection of peptides for immune monitoring and vaccine development.

Antitumour dendritic cell vaccination in a priming and boosting approach

Mobilizing antitumour immunity through vaccination potentially constitutes a powerful anticancer strategy but has not yet provided robust clinical benefits in large patient populations. Although major hurdles still exist, we believe that currently available strategies for vaccines that target dendritic cells or use them to present antitumour antigens could be integrated into existing clinical practice using prime-boost approaches. In the priming phase, these approaches capitalize on either standard treatment modalities to trigger in situ vaccination and release tumour antigens or vaccination with dendritic cells loaded with tumour lysates or patient-specific neoantigens. In a second boost phase, personalized synthetic vaccines specifically boost T cells that were triggered during the priming phase. This immunotherapy approach has been enabled by the substantial recent improvements in dendritic cell vaccines. In this Perspective, we discuss these improvements, highlight how the prime-boost approach can be translated into clinical practice and provide solutions for various anticipated hurdles.

NetMHCpan-4.1 and NetMHCIIpan-4.0: improved predictions of MHC antigen presentation by concurrent motif deconvolution and integration of MS MHC eluted ligand data

Major histocompatibility complex (MHC) molecules are expressed on the cell surface, where they present peptides to T cells, which gives them a key role in the development of T-cell immune responses. MHC molecules come in two main variants: MHC Class I (MHC-I) and MHC Class II (MHC-II). MHC-I predominantly present peptides derived from intracellular proteins, whereas MHC-II predominantly presents peptides from extracellular proteins. In both cases, the binding between MHC and antigenic peptides is the most selective step in the antigen presentation pathway. Therefore, the prediction of peptide binding to MHC is a powerful utility to predict the possible specificity of a T-cell immune response. Commonly MHC binding prediction tools are trained on binding affinity or mass spectrometry-eluted ligands. Recent studies have however demonstrated how the integration of both data types can boost predictive performances. Inspired by this, we here present NetMHCpan-4.1 and NetMHCIIpan-4.0, two web servers created to predict binding between peptides and MHC-I and MHC-II, respectively. Both methods exploit tailored machine learning strategies to integrate different training data types, resulting in state-of-the-art performance and outperforming their competitors. The servers are available at http://www.cbs.dtu.dk/services/NetMHCpan-4.1/ and http://www.cbs.dtu.dk/services/NetMHCIIpan-4.0/.

Immunoinformatics: Predicting Peptide-MHC Binding

Immunoinformatics is a discipline that applies methods of computer science to study and model the immune system. A fundamental question addressed by immunoinformatics is how to understand the rules of antigen presentation by MHC molecules to T cells, a process that is central to adaptive immune responses to infections and cancer. In the modern era of personalized medicine, the ability to model and predict which antigens can be presented by MHC is key to manipulating the immune system and designing strategies for therapeutic intervention. Since the MHC is both polygenic and extremely polymorphic, each individual possesses a personalized set of MHC molecules with different peptide-binding specificities, and collectively they present a unique individualized peptide imprint of the ongoing protein metabolism. Mapping all MHC allotypes is an enormous undertaking that cannot be achieved without a strong bioinformatics component. Computational tools for the prediction of peptide-MHC binding have thus become essential in most pipelines for T cell epitope discovery and an inescapable component of vaccine and cancer research. Here, we describe the development of several such tools, from pioneering efforts to the current state-of-the-art methods, that have allowed for accurate predictions of peptide binding of all MHC molecules, even including those that have not yet been characterized experimentally.

Immunopeptidomic Data Integration to Artificial Neural Networks Enhances Protein-Drug Immunogenicity Prediction

Recombinant DNA technology has, in the last decades, contributed to a vast expansion of the use of protein drugs as pharmaceutical agents. However, such biological drugs can lead to the formation of anti-drug antibodies (ADAs) that may result in adverse effects, including allergic reactions and compromised therapeutic efficacy. Production of ADAs is most often associated with activation of CD4 T cell responses resulting from proteolysis of the biotherapeutic and loading of drug-specific peptides into major histocompatibility complex (MHC) class II on professional antigen-presenting cells. Recently, readouts from MHC-associated peptide proteomics (MAPPs) assays have been shown to correlate with the presence of CD4 T cell epitopes. However, the limited sensitivity of MAPPs challenges its use as an immunogenicity biomarker. In this work, MAPPs data was used to construct an artificial neural network (ANN) model for MHC class II antigen presentation. Using Infliximab and Rituximab as showcase stories, the model demonstrated an unprecedented performance for predicting MAPPs and CD4 T cell epitopes in the context of protein-drug immunogenicity, complementing results from MAPPs assays and outperforming conventional prediction models trained on binding affinity data.