Deciphering HLA-I motifs across HLA peptidomes improves neo-antigen predictions and identifies allostery regulating HLA specificity

Precision Neoantigen Discovery Using Large-Scale Immunopeptidomes and Composite Modeling of MHC Peptide Presentation

Major histocompatibility complex (MHC)-bound peptides that originate from tumor-specific genetic alterations, known as neoantigens, are an important class of anticancer therapeutic targets. Accurately predicting peptide presentation by MHC complexes is a key aspect of discovering therapeutically relevant neoantigens. Technological improvements in mass spectrometry-based immunopeptidomics and advanced modeling techniques have vastly improved MHC presentation prediction over the past 2 decades. However, improvement in the accuracy of prediction algorithms is needed for clinical applications like the development of personalized cancer vaccines, the discovery of biomarkers for response to immunotherapies, and the quantification of autoimmune risk in gene therapies. Toward this end, we generated allele-specific immunopeptidomics data using 25 monoallelic cell lines and created Systematic Human Leukocyte Antigen (HLA) Epitope Ranking Pan Algorithm (SHERPA), a pan-allelic MHC-peptide algorithm for predicting MHC-peptide binding and presentation. In contrast to previously published large-scale monoallelic data, we used an HLA-null K562 parental cell line and a stable transfection of HLA allele to better emulate native presentation. Our dataset includes five previously unprofiled alleles that expand MHC diversity in the training data and extend allelic coverage in underprofiled populations. To improve generalizability, SHERPA systematically integrates 128 monoallelic and 384 multiallelic samples with publicly available immunoproteomics data and binding assay data. Using this dataset, we developed two features that empirically estimate the propensities of genes and specific regions within gene bodies to engender immunopeptides to represent antigen processing. Using a composite model constructed with gradient boosting decision trees, multiallelic deconvolution, and 2.15 million peptides encompassing 167 alleles, we achieved a 1.44-fold improvement of positive predictive value compared with existing tools when evaluated on independent monoallelic datasets and a 1.17-fold improvement when evaluating on tumor samples. With a high degree of accuracy, SHERPA has the potential to enable precision neoantigen discovery for future clinical applications.

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.

Mass spectrometric profiling of HLA-B44 peptidomes provides evidence for tapasin-mediated tryptophan editing

Activation of CD8 + T cells against pathogens and cancers involves the recognition of antigenic peptides bound to human leukocyte antigen (HLA) class-I proteins. Peptide binding to HLA class I proteins is coordinated by a multi-protein complex called the peptide loading complex (PLC). Tapasin, a key PLC component, facilitates the binding and optimization of HLA class I peptides. However, different HLA class I allotypes have variable requirements for tapasin for their assembly and surface expression. HLA-B*44:02 and HLA-B*44:05, which differ only at residue 116 of their heavy chain sequences, fall at opposite ends of the tapasin-dependency spectrum. HLA-B*44:02 (D116) is highly tapasin-dependent, whereas HLA-B*44:05 (Y116) is highly tapasinindependent. Mass spectrometric comparisons of HLA-B*4405 and HLA-B*44:02 peptidomes were undertaken to better understand the influences of tapasin upon HLA-B44 peptidome compositions. Analyses of the HLA-B*44:05 peptidomes in the presence and absence of tapasin reveal that peptides with the C-terminal tryptophan residues and those with higher predicted binding affinities are selected in the presence of tapasin. Additionally, when tapasin is present, C-terminal tryptophans are also more highly represented among peptides unique to B*44:02 and those shared between B*44:02 and B*44:05, compared with peptides unique to B*44:05. Overall, our findings demonstrate that tapasin influences the C-terminal composition of HLA class I-bound peptides and favors the binding of higher affinity peptides. For the HLA-B44 family, the presence of tapasin or high tapasin-dependence of an allotype results in better binding of peptides with C-terminal tryptophans, consistent with a role for tapasin in stabilizing an open conformation to accommodate bulky C-terminal residues.

Post-translational modifications reshape the antigenic landscape of the MHC I immunopeptidome in tumors

Post-translational modification (PTM) of antigens provides an additional source of specificities targeted by immune responses to tumors or pathogens, but identifying antigen PTMs and assessing their role in shaping the immunopeptidome is challenging. Here we describe the Protein Modification Integrated Search Engine (PROMISE), an antigen discovery pipeline that enables the analysis of 29 different PTM combinations from multiple clinical cohorts and cell lines. We expanded the antigen landscape, uncovering human leukocyte antigen class I binding motifs defined by specific PTMs with haplotype-specific binding preferences and revealing disease-specific modified targets, including thousands of new cancer-specific antigens that can be shared between patients and across cancer types. Furthermore, we uncovered a subset of modified peptides that are specific to cancer tissue and driven by post-translational changes that occurred in the tumor proteome. Our findings highlight principles of PTM-driven antigenicity, which may have broad implications for T cell-mediated therapies in cancer and beyond.

MHC II immunogenicity shapes the neoepitope landscape in human tumors

Despite advances in predicting physical peptide-major histocompatibility complex I (pMHC I) binding, it remains challenging to identify functionally immunogenic neoepitopes, especially for MHC II. By using the results of >36,000 immunogenicity assay, we developed a method to identify pMHC whose structural alignment facilitates T cell reaction. Our method predicted neoepitopes for MHC II and MHC I that were responsive to checkpoint blockade when applied to >1,200 samples of various tumor types. To investigate selection by spontaneous immunity at the single epitope level, we analyzed the frequency spectrum of >25 million mutations in >9,000 treatment-naive tumors with >100 immune phenotypes. MHC II immunogenicity specifically lowered variant frequencies in tumors under high immune pressure, particularly with high TCR clonality and MHC II expression. A similar trend was shown for MHC I neoepitopes, but only in particular tissue types. In summary, we report immune selection imposed by MHC II-restricted natural or therapeutic T cell reactivity.

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.

NetCleave: An Open-Source Algorithm for Predicting C-Terminal Antigen Processing for MHC-I and MHC-II

T cell epitopes presented on the surface of mammalian cells are subjected to a complex network of antigen processing and presentation. Among them, C-terminal antigen processing constitutes one of the main bottlenecks for the generation of epitopes, as it defines the C-terminal end of the final epitope and delimits the peptidome that will be presented downstream. Previously (Amengual-Rigo and Guallar, Sci Rep 111(11):1-8, 2021), we demonstrated that NetCleave stands out as one of the best algorithms for the prediction of C-terminal processing, which in its turn can be crucial to design peptide-based vaccination strategies. In this chapter, we provide a pipeline to exploit the full capabilities of NetCleave, an open-source and retrainable algorithm for predicting the C-terminal antigen processing for the MHC-I and MHC-II pathways.

inSPIRE: An Open-Source Tool for Increased Mass Spectrometry Identification Rates Using Prosit Spectral Prediction

Rescoring of mass spectrometry (MS) search results using spectral predictors can strongly increase peptide spectrum match (PSM) identification rates. This approach is particularly effective when aiming to search MS data against large databases, for example, when dealing with nonspecific cleavage in immunopeptidomics or inflation of the reference database for noncanonical peptide identification. Here, we present inSPIRE (in silico Spectral Predictor Informed REscoring), a flexible and performant open-source rescoring pipeline built on Prosit MS spectral prediction, which is compatible with common database search engines. inSPIRE allows large-scale rescoring with data from multiple MS search files, increases sensitivity to minor differences in amino acid residue position, and can be applied to various MS sample types, including tryptic proteome digestions and immunopeptidomes. inSPIRE boosts PSM identification rates in immunopeptidomics, leading to better performance than the original Prosit rescoring pipeline, as confirmed by benchmarking of inSPIRE performance on ground truth datasets. The integration of various features in the inSPIRE backbone further boosts the PSM identification in immunopeptidomics, with a potential benefit for the identification of noncanonical peptides.

The Second Asia-Oceania Human Proteome Organization (AOHUPO) Online Education Series on the Renaissance of Clinical Proteomics: Biomarkers, Imaging and Therapeutics

In 2021, the Asia-Oceania Human Proteome Organization (AOHUPO) initiated a new endeavor named the AOHUPO Online Education Series with the aim to promote scientific education and collaboration, exchange of ideas and culture among the young scientists in the AO region. Following the warm participation, the AOHUPO organized the second series in 2022, with the theme "The Renaissance of Clinical Proteomics: Biomarkers, Imaging and Therapeutics". This time, the second AOHUPO Online Education Series was hosted by the UKM Medical Molecular Biology Institute (UMBI) affiliated to the National University of Malaysia (UKM) in Kuala Lumpur, Malaysia on three consecutive Fridays (11th, 18th and 25th of March). More than 300 participants coming from 29 countries/regions registered for this 3-days event. This event provided an amalgamation of six prominent speakers and all participants whose interests lay mainly in applying MS-based and non-MS-based proteomics for clinical investigation.

Hydrophobicity identifies false positives and false negatives in peptide-MHC binding

Major Histocompability Complex (MHC) Class I molecules allow cells to present foreign and endogenous peptides to T-Cells so that cells infected by pathogens can be identified and killed. Neural networks tools such as NetMHC-4.0 and NetMHCpan-4.1 are used to predict whether peptides will bind to variants of MHC molecules. These tools are trained on data gathered from binding affinity and eluted ligand experiments. However, these tools do not track hydrophobicity, a significant biochemical factor relevant to peptide binding, in their predictions. A previous study had concluded that the peptides predicted to bind to HLA-A*0201 by NetMHC-4.0 were much more hydrophobic than expected. This paper expands that study by also focusing on HLA-B*2705 and HLA-B*0801, which prefer binding hydrophilic and balanced peptides respectively. The correlation of hydrophobicity of 9-mer peptides with their predicted binding strengths to these various HLAs was investigated. Two studies were performed, one using the data that the two neural networks were trained on, and the other using a sample of the human proteome. NetMHC-4.0 was found to have a statistically significant bias towards predicting highly hydrophobic peptides as strong binders to HLA-A*0201 and HLA-B*2705 in both studies. Machine Learning metrics were used to identify the causes for this bias: hydrophobic false positives and hydrophilic false negatives. These results suggest that the retraining the neural networks with biochemical attributes such as hydrophobicity and better training data could increase the accuracy of their predictions. This would increase their impact in applications such as vaccine design and neoantigen identification.

Antigenic molecular mimicry in viral-mediated protection from cancer: the HIV case

Background

People living with HIV/AIDS (PLWHA) show a reduced incidence for three cancer types, namely breast, prostate and colon cancers. In the present study, we assessed whether a molecular mimicry between HIV epitopes and tumor associated antigens and, consequently, a T cell cross-reactivity could provide an explanation for such an epidemiological evidence.

Methods

Homology between published TAAs and non-self HIV-derived epitopes have been assessed by BLAST homology. Structural analyses have been performed by bioinformatics tools. Immunological validation of CD8⁺ T cell cross-reactivity has been evaluated ex vivo by tetramer staining.

Findings

Sequence homologies between multiple TAAs and HIV epitopes have been found. High structural similarities between the paired TAAs and HIV epitopes as well as comparable patterns of contact with HLA and TCR α and β chains have been observed. Furthermore, cross-reacting CD8⁺ T cells have been identified.

Interpretation

This is the first study showing a molecular mimicry between HIV antigens an TAAs identified in breast, prostate and colon cancers. Therefore, it is highly reasonable that memory CD8⁺ T cells elicited during the HIV infection may play a key role in controlling development and progression of such cancers in the PLWHA lifetime. This represents the first demonstration ever that a viral infection may induce a natural “preventive” anti-cancer memory T cells, with highly relevant implications beyond the HIV infection.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12967-022-03681-4.

Sources of Cancer Neoantigens beyond Single-Nucleotide Variants

The success of checkpoint blockade therapy against cancer has unequivocally shown that cancer cells can be effectively recognized by the immune system and eliminated. However, the identity of the cancer antigens that elicit protective immunity remains to be fully explored. Over the last decade, most of the focus has been on somatic mutations derived from non-synonymous single-nucleotide variants (SNVs) and small insertion/deletion mutations (indels) that accumulate during cancer progression. Mutated peptides can be presented on MHC molecules and give rise to novel antigens or neoantigens, which have been shown to induce potent anti-tumor immune responses. A limitation with SNV-neoantigens is that they are patient-specific and their accurate prediction is critical for the development of effective immunotherapies. In addition, cancer types with low mutation burden may not display sufficient high-quality [SNV/small indels] neoantigens to alone stimulate effective T cell responses. Accumulating evidence suggests the existence of alternative sources of cancer neoantigens, such as gene fusions, alternative splicing variants, post-translational modifications, and transposable elements, which may be attractive novel targets for immunotherapy. In this review, we describe the recent technological advances in the identification of these novel sources of neoantigens, the experimental evidence for their presentation on MHC molecules and their immunogenicity, as well as the current clinical development stage of immunotherapy targeting these neoantigens.

CD8 T cell function and cross-reactivity explored by stepwise increased peptide-HLA versus TCR affinity

Recruitment and activation of CD8 T cells occur through specific triggering of T cell receptor (TCR) by peptide-bound human leucocyte antigen (HLA) ligands. Within the generated trimeric TCR-peptide:HLA complex, the molecular binding affinities between peptide and HLA, and between TCR and peptide:HLA both impact T cell functional outcomes. However, how their individual and combined effects modulate immunogenicity and overall T cell responsiveness has not been investigated systematically. Here, we established two panels of human tumor peptide variants differing in their affinity to HLA. For precise characterization, we developed the “blue peptide assay”, an upgraded cell-based approach to measure the peptide:HLA affinity. These peptide variants were then used to investigate the cross-reactivity of tumor antigen-specific CD8 T cell clonotypes derived from blood of cancer patients after vaccination with either the native or an affinity-optimized Melan-A/MART-1 epitope, or isolated from tumor infiltrated lymph nodes (TILNs). Vaccines containing the native tumor epitope generated T cells with better functionality, and superior cross-reactivity against potential low affinity escape epitopes, as compared to T cells induced by vaccines containing an HLA affinity-optimized epitope. Comparatively, Melan-A/MART-1-specific TILN cells displayed functional and cross-reactive profiles that were heterogeneous and clonotype-dependent. Finally, we took advantage of a collection of T cells expressing affinity-optimized NY-ESO-1-specific TCRs to interrogate the individual and combined impact of peptide:HLA and TCR-pHLA affinities on overall CD8 T cell responses. We found profound and distinct effects of both biophysical parameters, with additive contributions and absence of hierarchical dominance. Altogether, the biological impact of peptide:HLA and TCR-pHLA affinities on T cell responses was carefully dissected in two antigenic systems, frequently targeted in human cancer immunotherapy. Our technology and stepwise comparison open new insights into the rational design and selection of vaccine-associated tumor-specific epitopes and highlight the functional and cross-reactivity profiles that endow T cells with best tumor control capacity.

MS2Rescore: Data-driven rescoring dramatically boosts immunopeptide identification rates

Immunopeptidomics aims to identify major histocompatibility complex (MHC)-presented peptides on almost all cells that can be used in anti-cancer vaccine development. However, existing immunopeptidomics data analysis pipelines suffer from the nontryptic nature of immunopeptides, complicating their identification. Previously, peak intensity predictions by MS²PIP and retention time predictions by DeepLC have been shown to improve tryptic peptide identifications when rescoring peptide-spectrum matches with Percolator. However, as MS²PIP was tailored toward tryptic peptides, we have here retrained MS²PIP to include nontryptic peptides. Interestingly, the new models not only greatly improve predictions for immunopeptides but also yield further improvements for tryptic peptides. We show that the integration of new MS²PIP models, DeepLC, and Percolator in one software package, MS²Rescore, increases spectrum identification rate and unique identified peptides with 46% and 36% compared to standard Percolator rescoring at 1% FDR. Moreover, MS²Rescore also outperforms the current state-of-the-art in immunopeptide-specific identification approaches. Altogether, MS²Rescore thus allows substantially improved identification of novel epitopes from existing immunopeptidomics workflows.

•

MS²Rescore significantly boosts immunopeptide identification rates

•

Data-driven post-processing allows for a ten-fold increase in specificity

•

MS²PIP and DeepLC predictors are integrated with Percolator post-processing

•

MS²Rescore accepts identification results from MaxQuant, PEAKS, MS-GF+ and X!Tandem

•

MS²Rescore shows great promise to extend current neo- and xeno-epitope landscapes

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.

HLAB: learning the BiLSTM features from the ProtBert-encoded proteins for the class I HLA-peptide binding prediction

Human Leukocyte Antigen (HLA) is a type of molecule residing on the surfaces of most human cells and exerts an essential role in the immune system responding to the invasive items. The T cell antigen receptors may recognize the HLA-peptide complexes on the surfaces of cancer cells and destroy these cancer cells through toxic T lymphocytes. The computational determination of HLA-binding peptides will facilitate the rapid development of cancer immunotherapies. This study hypothesized that the natural language processing-encoded peptide features may be further enriched by another deep neural network. The hypothesis was tested with the Bi-directional Long Short-Term Memory-extracted features from the pretrained Protein Bidirectional Encoder Representations from Transformers-encoded features of the class I HLA (HLA-I)-binding peptides. The experimental data showed that our proposed HLAB feature engineering algorithm outperformed the existing ones in detecting the HLA-I-binding peptides. The extensive evaluation data show that the proposed HLAB algorithm outperforms all the seven existing studies on predicting the peptides binding to the HLA-A^*01:01 allele in AUC and achieves the best average AUC values on the six out of the seven k-mers (k=8,9,...,14, respectively represent the prediction task of a polypeptide consisting of k amino acids) except for the 9-mer prediction tasks. The source code and the fine-tuned feature extraction models are available at http://www.healthinformaticslab.org/supp/resources.php.

Sensitive identification of neoantigens and cognate TCRs in human solid tumors

The identification of patient-specific tumor antigens is complicated by the low frequency of T cells specific for each tumor antigen. Here we describe NeoScreen, a method that enables the sensitive identification of rare tumor (neo)antigens and of cognate T cell receptors (TCRs) expressed by tumor-infiltrating lymphocytes. T cells transduced with tumor antigen-specific TCRs identified by NeoScreen mediate regression of established tumors in patient-derived xenograft mice.

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.

Identification of neoantigens for individualized therapeutic cancer vaccines

Somatic mutations in cancer cells can generate tumour-specific neoepitopes, which are recognized by autologous T cells in the host. As neoepitopes are not subject to central immune tolerance and are not expressed in healthy tissues, they are attractive targets for therapeutic cancer vaccines. Because the vast majority of cancer mutations are unique to the individual patient, harnessing the full potential of this rich source of targets requires individualized treatment approaches. Many computational algorithms and machine-learning tools have been developed to identify mutations in sequence data, to prioritize those that are more likely to be recognized by T cells and to design tailored vaccines for every patient. In this Review, we fill the gaps between the understanding of basic mechanisms of T cell recognition of neoantigens and the computational approaches for discovery of somatic mutations and neoantigen prediction for cancer immunotherapy. We present a new classification of neoantigens, distinguishing between guarding, restrained and ignored neoantigens, based on how they confer proficient antitumour immunity in a given clinical context. Such context-based differentiation will contribute to a framework that connects neoantigen biology to the clinical setting and medical peculiarities of cancer, and will enable future neoantigen-based therapies to provide greater clinical benefit.

NeoScore Integrates Characteristics of the Neoantigen:MHC Class I Interaction and Expression to Accurately Prioritize Immunogenic Neoantigens

Accurate prioritization of immunogenic neoantigens is key to developing personalized cancer vaccines and distinguishing those patients likely to respond to immune checkpoint inhibition. However, there is no consensus regarding which characteristics best predict neoantigen immunogenicity, and no model to date has both high sensitivity and specificity and a significant association with survival in response to immunotherapy. We address these challenges in the prioritization of immunogenic neoantigens by (1) identifying which neoantigen characteristics best predict immunogenicity; (2) integrating these characteristics into an immunogenicity score, the NeoScore; and (3) demonstrating a significant association of the NeoScore with survival in response to immune checkpoint inhibition. One thousand random and evenly split combinations of immunogenic and nonimmunogenic neoantigens from a validated dataset were analyzed using a regularized regression model for characteristic selection. The selected characteristics, the dissociation constant and binding stability of the neoantigen:MHC class I complex and expression of the mutated gene in the tumor, were integrated into the NeoScore. A web application is provided for calculation of the NeoScore. The NeoScore results in improved, or equivalent, performance in four test datasets as measured by sensitivity, specificity, and area under the receiver operator characteristics curve compared with previous models. Among cutaneous melanoma patients treated with immune checkpoint inhibition, a high maximum NeoScore was associated with improved survival. Overall, the NeoScore has the potential to improve neoantigen prioritization for the development of personalized vaccines and contribute to the determination of which patients are likely to respond to immunotherapy.

Cancer Neoantigens: Challenges and Future Directions for Prediction, Prioritization, and Validation

Prioritization of immunogenic neoantigens is key to enhancing cancer immunotherapy through the development of personalized vaccines, adoptive T cell therapy, and the prediction of response to immune checkpoint inhibition. Neoantigens are tumor-specific proteins that allow the immune system to recognize and destroy a tumor. Cancer immunotherapies, such as personalized cancer vaccines, adoptive T cell therapy, and immune checkpoint inhibition, rely on an understanding of the patient-specific neoantigen profile in order to guide personalized therapeutic strategies. Genomic approaches to predicting and prioritizing immunogenic neoantigens are rapidly expanding, raising new opportunities to advance these tools and enhance their clinical relevance. Predicting neoantigens requires acquisition of high-quality samples and sequencing data, followed by variant calling and variant annotation. Subsequently, prioritizing which of these neoantigens may elicit a tumor-specific immune response requires application and integration of tools to predict the expression, processing, binding, and recognition potentials of the neoantigen. Finally, improvement of the computational tools is held in constant tension with the availability of datasets with validated immunogenic neoantigens. The goal of this review article is to summarize the current knowledge and limitations in neoantigen prediction, prioritization, and validation and propose future directions that will improve personalized cancer treatment.

Identification of alternative splicing-derived cancer neoantigens for mRNA vaccine development

Messenger RNA (mRNA) vaccines have shown great potential for anti-tumor therapy due to the advantages in safety, efficacy and industrial production. However, it remains a challenge to identify suitable cancer neoantigens that can be targeted for mRNA vaccines. Abnormal alternative splicing occurs in a variety of tumors, which may result in the translation of abnormal transcripts into tumor-specific proteins. High-throughput technologies make it possible for systematic characterization of alternative splicing as a source of suitable target neoantigens for mRNA vaccine development. Here, we summarized difficulties and challenges for identifying alternative splicing-derived cancer neoantigens from RNA-seq data and proposed a conceptual framework for designing personalized mRNA vaccines based on alternative splicing-derived cancer neoantigens. In addition, several points were presented to spark further discussion toward improving the identification of alternative splicing-derived cancer neoantigens.

Combined assessment of MHC binding and antigen abundance improves T cell epitope predictions

Many steps of the MHC class I antigen processing pathway can be predicted using computational methods. Here we show that epitope predictions can be further improved by considering abundance levels of peptides' source proteins. We utilized biophysical principles and existing MHC binding prediction tools in concert with abundance estimates of source proteins to derive a function that estimates the likelihood of a peptide to be an MHC class I ligand. We found that this combination improved predictions for both naturally eluted ligands and cancer neoantigen epitopes. We compared the use of different measures of antigen abundance, including mRNA expression by RNA-Seq, gene translation by Ribo-Seq, and protein abundance by proteomics on a dataset of SARS-CoV-2 epitopes. Epitope predictions were improved above binding predictions alone in all cases and gave the highest performance when using proteomic data. Our results highlight the value of incorporating antigen abundance levels to improve epitope predictions.

An Update on "Reverse Vaccinology": The Pathway from Genomes and Epitope Predictions to Tailored, Recombinant Vaccines

In this chapter, we review the computational approaches that have led to a new generation of vaccines in recent years. There are many alternative routes to develop vaccines based on the concept of reverse vaccinology. They all follow the same basic principles-mining available genome and proteome information for antigen candidates, and recombinantly expressing them for vaccine production. Some of the same principles have been used successfully for cancer therapy approaches. In this review, we focus on infectious diseases, describing the general workflow from bioinformatic predictions of antigens and epitopes down to examples where such predictions have been used successfully for vaccine development.

A tale of solving two computational challenges in protein science: neoantigen prediction and protein structure prediction

In this article, we review two challenging computational questions in protein science: neoantigen prediction and protein structure prediction. Both topics have seen significant leaps forward by deep learning within the past five years, which immediately unlocked new developments of drugs and immunotherapies. We show that deep learning models offer unique advantages, such as representation learning and multi-layer architecture, which make them an ideal choice to leverage a huge amount of protein sequence and structure data to address those two problems. We also discuss the impact and future possibilities enabled by those two applications, especially how the data-driven approach by deep learning shall accelerate the progress towards personalized biomedicine.

Structural Prediction of Peptide-MHC Binding Modes

The immune system is constantly protecting its host from the invasion of pathogens and the development of cancer cells. The specific CD8⁺ T-cell immune response against virus-infected cells and tumor cells is based on the T-cell receptor recognition of antigenic peptides bound to class I major histocompatibility complexes (MHC) at the surface of antigen presenting cells. Consequently, the peptide binding specificities of the highly polymorphic MHC have important implications for the design of vaccines, for the treatment of autoimmune diseases, and for personalized cancer immunotherapy. Evidence-based machine-learning approaches have been successfully used for the prediction of peptide binders and are currently being developed for the prediction of peptide immunogenicity. However, understanding and modeling the structural details of peptide/MHC binding is crucial for a better understanding of the molecular mechanisms triggering the immunological processes, estimating peptide/MHC affinity using universal physics-based approaches, and driving the design of novel peptide ligands. Unfortunately, due to the large diversity of MHC allotypes and possible peptides, the growing number of 3D structures of peptide/MHC (pMHC) complexes in the Protein Data Bank only covers a small fraction of the possibilities. Consequently, there is a growing need for rapid and efficient approaches to predict 3D structures of pMHC complexes. Here, we review the key characteristics of the 3D structure of pMHC complexes before listing databases and other sources of information on pMHC structures and MHC specificities. Finally, we discuss some of the most prominent pMHC docking software.

In silico tools and databases for designing cancer immunotherapy

Immunotherapy is a rapidly growing therapy for cancer which have numerous benefits over conventional treatments like surgery, chemotherapy, and radiation. Overall survival of cancer patients has improved significantly due to the use of immunotherapy. It acts as a novel pillar for treating different malignancies from their primary to the metastatic stage. Recent preferments in high-throughput sequencing and computational immunology leads to the development of targeted immunotherapy for precision oncology. In the last few decades, several computational methods and resources have been developed for designing immunotherapy against cancer. In this review, we have summarized cancer-associated genomic, transcriptomic, and mutation profile repositories. We have also enlisted in silico methods for the prediction of vaccine candidates, HLA binders, cytokines inducing peptides, and potential neoepitopes. Of note, we have incorporated the most important bioinformatics pipelines and resources for the designing of cancer immunotherapy. Moreover, to facilitate the scientific community, we have developed a web portal entitled ImmCancer (https://webs.iiitd.edu.in/raghava/immcancer/), comprises cancer immunotherapy tools and repositories.

Immuno-transcriptomic profiling of extracranial pediatric solid malignancies

We perform an immunogenomics analysis utilizing whole-transcriptome sequencing of 657 pediatric extracranial solid cancer samples representing 14 diagnoses, and additionally utilize transcriptomes of 131 pediatric cancer cell lines and 147 normal tissue samples for comparison. We describe patterns of infiltrating immune cells, T cell receptor (TCR) clonal expansion, and translationally relevant immune checkpoints. We find that tumor-infiltrating lymphocytes and TCR counts vary widely across cancer types and within each diagnosis, and notably are significantly predictive of survival in osteosarcoma patients. We identify potential cancer-specific immunotherapeutic targets for adoptive cell therapies including cell-surface proteins, tumor germline antigens, and lineage-specific transcription factors. Using an orthogonal immunopeptidomics approach, we find several potential immunotherapeutic targets in osteosarcoma and Ewing sarcoma and validated PRAME as a bona fide multi-pediatric cancer target. Importantly, this work provides a critical framework for immune targeting of extracranial solid tumors using parallel immuno-transcriptomic and -peptidomic approaches.

NeoFox: annotating neoantigen candidates with neoantigen features

SUMMARY

The detection and prediction of true neoantigens is of great importance for the field of cancer immunotherapy. Wesearched the literature for proposed neoantigen features and integrated them into a toolbox called NEOantigen Feature toolbOX (NeoFox). NeoFox is an easy-to-use Python package that enables the annotation of neoantigen candidates with 16 neoantigen features.

AVAILABILITY AND IMPLEMENTATION

NeoFox is freely available as an open source Python package released under the GNU General Public License (GPL) v3 license at https://github.com/TRON-Bioinformatics/neofox.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

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.

Alterations in HLA Class I-Presented Immunopeptidome and Class I-Interactome upon Osimertinib Resistance in EGFR Mutant Lung Adenocarcinoma

Simple Summary

We sought to identify molecular mechanisms of lower efficacy of immunotherapy in epidermal growth factor receptor (EGFR) mutant lung adenocarcinoma and the differences in those mechanisms with the emergence of tyrosine kinase inhibitor (TKI)-resistance. To this end, we conducted affinity purification and quantitative mass spectrometry-based proteomic profiling of human leukocyte antigen (HLA) Class I-presented immunopeptides and Class I-interacting proteins. This large-scale dataset revealed that the Class I-presented immunopeptidome was suppressed in two third-generation EGFR TKI, osimertinib-resistant lung adenocarcinoma cell lines compared to their isogenic TKI-sensitive counterparts. The whole-cell proteomic profiling show that antigen presentation complex proteins and immunoproteasome were downregulated upon EGFR TKI resistance. Furthermore, HLA class I-interactome profiling demonstrated altered interaction with key apoptosis and autophagy pathway proteins. In summary, our comprehensive multi-proteomic characterization in antigen presentation machinery provides potentially novel evidence of poor immune response in osimertinib-resistant lung adenocarcinoma.

Abstract

Immune checkpoint inhibitor (ICI) therapy has been a paradigm shift in the treatment of cancer. ICI therapy results in durable responses and survival benefit for a large number of tumor types. Osimertinib, a third-generation epidermal growth factor receptor (EGFR) tyrosine kinase inhibitor (TKI) has shown great efficacy treating EGFR mutant lung cancers; however, all patients eventually develop resistance. ICI therapy has not benefitted EGFR mutant lung cancer. Herein, we employed stable isotope labeling by amino acids in cell culture (SILAC) quantitative mass spectrometry-based proteomics to investigate potential immune escape molecular mechanisms in osimertinib resistant EGFR mutant lung adenocarcinoma by interrogating the alterations in the human leukocyte antigen (HLA) Class I-presented immunopeptidome, Class I-interactome, and the whole cell proteome between isogenic osimertinib-sensitive and -resistant human lung adenocarcinoma cells. Our study demonstrates an overall reduction in HLA class I-presented immunopeptidome and downregulation of antigen presentation core complex (e.g., TAP1 and ERAP1/2) and immunoproteasome in osimertinib resistant lung adenocarcinoma cells. Several key components in autophagy pathway are differentially altered. S100 proteins and SLC3A2 may play critical roles in reduced antigen presentation. Our dataset also includes ~1000 novel HLA class I interaction partners and hundreds of Class I-presented immunopeptides in EGFR mutant lung adenocarcinoma. This large-scale unbiased proteomics study provides novel insights and potential mechanisms of immune evasion of EGFR mutant lung adenocarcinoma.

Implications of Antigen Selection on T Cell-Based Immunotherapy

Many immunotherapies rely on CD8+ effector T cells to recognize and kill cognate tumor cells. These T cell-based immunotherapies include adoptive cell therapy, such as CAR T cells or transgenic TCR T cells, and anti-cancer vaccines which expand endogenous T cell populations. Tumor mutation burden and the choice of antigen are among the most important aspects of T cell-based immunotherapies. Here, we highlight various classes of cancer antigens, including self, neojunction-derived, human endogenous retrovirus (HERV)-derived, and somatic nucleotide variant (SNV)-derived antigens, and consider their utility in T cell-based immunotherapies. We further discuss the respective anti-tumor/anti-self-properties that influence both the degree of immunotolerance and potential off-target effects associated with each antigen class.

The Cancer Epitope Database and Analysis Resource: A Blueprint for the Establishment of a New Bioinformatics Resource for Use by the Cancer Immunology Community

Recent years have witnessed a dramatic rise in interest towards cancer epitopes in general and particularly neoepitopes, antigens that are encoded by somatic mutations that arise as a consequence of tumorigenesis. There is also an interest in the specific T cell and B cell receptors recognizing these epitopes, as they have therapeutic applications. They can also aid in basic studies to infer the specificity of T cells or B cells characterized in bulk and single-cell sequencing data. The resurgence of interest in T cell and B cell epitopes emphasizes the need to catalog all cancer epitope-related data linked to the biological, immunological, and clinical contexts, and most importantly, making this information freely available to the scientific community in a user-friendly format. In parallel, there is also a need to develop resources for epitope prediction and analysis tools that provide researchers access to predictive strategies and provide objective evaluations of their performance. For example, such tools should enable researchers to identify epitopes that can be effectively used for immunotherapy or in defining biomarkers to predict the outcome of checkpoint blockade therapies. We present here a detailed vision, blueprint, and work plan for the development of a new resource, the Cancer Epitope Database and Analysis Resource (CEDAR). CEDAR will provide a freely accessible, comprehensive collection of cancer epitope and receptor data curated from the literature and provide easily accessible epitope and T cell/B cell target prediction and analysis tools. The curated cancer epitope data will provide a transparent benchmark dataset that can be used to assess how well prediction tools perform and to develop new prediction tools relevant to the cancer research community.

Identification of presented SARS-CoV-2 HLA class I and HLA class II peptides using HLA peptidomics

The human leukocyte antigen (HLA)-bound viral antigens serve as an immunological signature that can be selectively recognized by T cells. As viruses evolve by acquiring mutations, it is essential to identify a range of presented viral antigens. Using HLA peptidomics, we are able to identify severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-derived peptides presented by highly prevalent HLA class I (HLA-I) molecules by using infected cells as well as overexpression of SARS-CoV-2 genes. We find 26 HLA-I peptides and 36 HLA class II (HLA-II) peptides. Among the identified peptides, some are shared between different cells and some are derived from out-of-frame open reading frames (ORFs). Seven of these peptides were previously shown to be immunogenic, and we identify two additional immunoreactive peptides by using HLA multimer staining. These results may aid the development of the next generation of SARS-CoV-2 vaccines based on presented viral-specific antigens that span several of the viral genes.

Withdrawn: Precision Neoantigen Discovery Using Large-scale Immunopeptidomes and Composite Modeling of MHC Peptide Presentation

This article has been withdrawn by the authors. A publication of the manuscript with the correct figures and tables has been approved and the authors state the conclusions of the manuscript remain unaffected. Specifically, errors are in Figure 6A, Supplementary Figure 10B, Supplementary Figure 10C, and Supplementary Table 5. The details of the errors are as follows: the HLA types for one sample were incorrectly assigned because of a tumor/normal mislabeling from the biobank vendor. Due to the differing HLA types between the tumor and normal sample, the sequence analysis established that the HLA alleles for this patient had been deleted (HLA LOH). The authors conclude that this was an artifact caused by the normal sample mislabeling. The corrected version can be accessed (Pyke, R.M., Mellacheruvu, D., Dea, S., Abbott, C.W., Zhang, S.V., Philips, N.A., Harris, J., Bartha, G., Desai, S., McClory, R., West, J., Snyder, M,P., Chen, R., Boyle, S.M. (2022) Precision Neoantigen Discovery Using Large-Scale Immunopeptidomics and Composite Modeling of MHC Peptide Presentation. Mol. Cell. Proteomics 22, 100506

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.

Artificial intelligence in early drug discovery enabling precision medicine

Introduction: Precision medicine is the concept of treating diseases based on environmental factors, lifestyles, and molecular profiles of patients. This approach has been found to increase success rates of clinical trials and accelerate drug approvals. However, current precision medicine applications in early drug discovery use only a handful of molecular biomarkers to make decisions, whilst clinics gear up to capture the full molecular landscape of patients in the near future. This deep multi-omics characterization demands new analysis strategies to identify appropriate treatment regimens, which we envision will be pioneered by artificial intelligence.Areas covered: In this review, the authors discuss the current state of drug discovery in precision medicine and present our vision of how artificial intelligence will impact biomarker discovery and drug design.Expert opinion: Precision medicine is expected to revolutionize modern medicine; however, its traditional form is focusing on a few biomarkers, thus not equipped to leverage the full power of molecular landscapes. For learning how the development of drugs can be tailored to the heterogeneity of patients across their molecular profiles, artificial intelligence algorithms are the next frontier in precision medicine and will enable a fully personalized approach in drug design, and thus ultimately impacting clinical practice.

Improvement of Neoantigen Identification Through Convolution Neural Network

Accurate prediction of neoantigens and the subsequent elicited protective anti-tumor response are particularly important for the development of cancer vaccine and adoptive T-cell therapy. However, current algorithms for predicting neoantigens are limited by in vitro binding affinity data and algorithmic constraints, inevitably resulting in high false positives. In this study, we proposed a deep convolutional neural network named APPM (antigen presentation prediction model) to predict antigen presentation in the context of human leukocyte antigen (HLA) class I alleles. APPM is trained on large mass spectrometry (MS) HLA-peptides datasets and evaluated with an independent MS benchmark. Results show that APPM outperforms the methods recommended by the immune epitope database (IEDB) in terms of positive predictive value (PPV) (0.40 vs. 0.22), which will further increase after combining these two approaches (PPV = 0.51). We further applied our model to the prediction of neoantigens from consensus driver mutations and identified 16,000 putative neoantigens with hallmarks of 'drivers'.

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.

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.

Total predicted MHC-I epitope load is inversely associated with population mortality from SARS-CoV-2

Polymorphisms in MHC-I protein sequences across human populations significantly affect viral peptide binding capacity, and thus alter T cell immunity to infection. In the present study, we assess the relationship between observed SARS-CoV-2 population mortality and the predicted viral binding capacities of 52 common MHC-I alleles. Potential SARS-CoV-2 MHC-I peptides are identified using a consensus MHC-I binding and presentation prediction algorithm called EnsembleMHC. Starting with nearly 3.5 million candidates, we resolve a few hundred highly probable MHC-I peptides. By weighing individual MHC allele-specific SARS-CoV-2 binding capacity with population frequency in 23 countries, we discover a strong inverse correlation between predicted population SARS-CoV-2 peptide binding capacity and mortality rate. Our computations reveal that peptides derived from the structural proteins of the virus produce a stronger association with observed mortality rate, highlighting the importance of S, N, M, and E proteins in driving productive immune responses.

Personalized cancer vaccine strategy elicits polyfunctional T cells and demonstrates clinical benefits in ovarian cancer

T cells are important for controlling ovarian cancer (OC). We previously demonstrated that combinatorial use of a personalized whole-tumor lysate-pulsed dendritic cell vaccine (OCDC), bevacizumab (Bev), and cyclophosphamide (Cy) elicited neoantigen-specific T cells and prolonged OC survival. Here, we hypothesize that adding acetylsalicylic acid (ASA) and low-dose interleukin (IL)-2 would increase the vaccine efficacy in a recurrent advanced OC phase I trial (NCT01132014). By adding ASA and low-dose IL-2 to the OCDC-Bev-Cy combinatorial regimen, we elicited vaccine-specific T-cell responses that positively correlated with patients' prolonged time-to-progression and overall survival. In the ID8 ovarian model, animals receiving the same regimen showed prolonged survival, increased tumor-infiltrating perforin-producing T cells, increased neoantigen-specific CD8⁺ T cells, and reduced endothelial Fas ligand expression and tumor-infiltrating T-regulatory cells. This combinatorial strategy was efficacious and also highlighted the predictive value of the ID8 model for future ovarian trial development.

Prediction of neo-epitope immunogenicity reveals TCR recognition determinants and provides insight into immunoediting

CD8+ T cell recognition of peptide epitopes plays a central role in immune responses against pathogens and tumors. However, the rules that govern which peptides are truly recognized by existing T cell receptors (TCRs) remain poorly understood, precluding accurate predictions of neo-epitopes for cancer immunotherapy. Here, we capitalize on recent (neo-)epitope data to train a predictor of immunogenic epitopes (PRIME), which captures molecular properties of both antigen presentation and TCR recognition. PRIME not only improves prioritization of neo-epitopes but also correlates with T cell potency and unravels biophysical determinants of TCR recognition that we experimentally validate. Analysis of cancer genomics data reveals that recurrent mutations tend to be less frequent in patients where they are predicted to be immunogenic, providing further evidence for immunoediting in human cancer. PRIME will facilitate identification of pathogen epitopes in infectious diseases and neo-epitopes in cancer immunotherapy.

The immunopeptidomes of two transmissible cancers and their host have a common, dominant peptide motif

Transmissible cancers are malignant cells that can spread between individuals of a population, akin to both a parasite and a mobile graft. The survival of the Tasmanian devil, the largest remaining marsupial carnivore, is threatened by the remarkable emergence of two independent lineages of transmissible cancer, devil facial tumour (DFT) 1 and devil facial tumour 2 (DFT2). To aid the development of a vaccine and to interrogate how histocompatibility barriers can be overcome, we analysed the peptides bound to major histocompatibility complex class I (MHC‐I) molecules from Tasmanian devil cells and representative cell lines of each transmissible cancer. Here, we show that DFT1 + IFN‐γ and DFT2 cell lines express a restricted repertoire of MHC‐I allotypes compared with fibroblast cells, potentially reducing the breadth of peptide presentation. Comparison of the peptidomes from DFT1 + IFNγ, DFT2 and host fibroblast cells demonstrates a dominant motif, despite differences in MHC‐I allotypes between the cell lines, with preference for a hydrophobic leucine residue at position 3 and position Ω of peptides. DFT1 and DFT2 both present peptides derived from neural proteins, which reflects a shared cellular origin that could be exploited for vaccine design. These results suggest that polymorphisms in MHC‐I molecules between tumours and host can be ‘hidden’ by a common peptide motif, providing the potential for permissive passage of infectious cells and demonstrating complexity in mammalian histocompatibility barriers.

Anthem: a user customised tool for fast and accurate prediction of binding between peptides and HLA class I molecules

Neopeptide-based immunotherapy has been recognised as a promising approach for the treatment of cancers. For neopeptides to be recognised by CD8+ T cells and induce an immune response, their binding to human leukocyte antigen class I (HLA-I) molecules is a necessary first step. Most epitope prediction tools thus rely on the prediction of such binding. With the use of mass spectrometry, the scale of naturally presented HLA ligands that could be used to develop such predictors has been expanded. However, there are rarely efforts that focus on the integration of these experimental data with computational algorithms to efficiently develop up-to-date predictors. Here, we present Anthem for accurate HLA-I binding prediction. In particular, we have developed a user-friendly framework to support the development of customisable HLA-I binding prediction models to meet challenges associated with the rapidly increasing availability of large amounts of immunopeptidomic data. Our extensive evaluation, using both independent and experimental datasets shows that Anthem achieves an overall similar or higher area under curve value compared with other contemporary tools. It is anticipated that Anthem will provide a unique opportunity for the non-expert user to analyse and interpret their own in-house or publicly deposited datasets.