Machine learning reveals a non-canonical mode of peptide binding to MHC class II molecules

Integrated image and location analysis for wound classification: a deep learning approach

The global burden of acute and chronic wounds presents a compelling case for enhancing wound classification methods, a vital step in diagnosing and determining optimal treatments. Recognizing this need, we introduce an innovative multi-modal network based on a deep convolutional neural network for categorizing wounds into four categories: diabetic, pressure, surgical, and venous ulcers. Our multi-modal network uses wound images and their corresponding body locations for more precise classification. A unique aspect of our methodology is incorporating a body map system that facilitates accurate wound location tagging, improving upon traditional wound image classification techniques. A distinctive feature of our approach is the integration of models such as VGG16, ResNet152, and EfficientNet within a novel architecture. This architecture includes elements like spatial and channel-wise Squeeze-and-Excitation modules, Axial Attention, and an Adaptive Gated Multi-Layer Perceptron, providing a robust foundation for classification. Our multi-modal network was trained and evaluated on two distinct datasets comprising relevant images and corresponding location information. Notably, our proposed network outperformed traditional methods, reaching an accuracy range of 74.79-100% for Region of Interest (ROI) without location classifications, 73.98-100% for ROI with location classifications, and 78.10-100% for whole image classifications. This marks a significant enhancement over previously reported performance metrics in the literature. Our results indicate the potential of our multi-modal network as an effective decision-support tool for wound image classification, paving the way for its application in various clinical contexts.

MHCII-peptide presentation: an assessment of the state-of-the-art prediction methods

Major histocompatibility complex Class II (MHCII) proteins initiate and regulate immune responses by presentation of antigenic peptides to CD4+ T-cells and self-restriction. The interactions between MHCII and peptides determine the specificity of the immune response and are crucial in immunotherapy and cancer vaccine design. With the ever-increasing amount of MHCII-peptide binding data available, many computational approaches have been developed for MHCII-peptide interaction prediction over the last decade. There is thus an urgent need to provide an up-to-date overview and assessment of these newly developed computational methods. To benchmark the prediction performance of these methods, we constructed an independent dataset containing binding and non-binding peptides to 20 human MHCII protein allotypes from the Immune Epitope Database, covering DP, DR and DQ alleles. After collecting 11 known predictors up to January 2022, we evaluated those available through a webserver or standalone packages on this independent dataset. The benchmarking results show that MixMHC2pred and NetMHCIIpan-4.1 achieve the best performance among all predictors. In general, newly developed methods perform better than older ones due to the rapid expansion of data on which they are trained and the development of deep learning algorithms. Our manuscript not only draws a full picture of the state-of-art of MHCII-peptide binding prediction, but also guides researchers in the choice among the different predictors. More importantly, it will inspire biomedical researchers in both academia and industry for the future developments in this field.

Accurate modeling of peptide-MHC structures with AlphaFold

Major histocompatibility complex (MHC) proteins present peptides on the cell surface for T cell surveillance. Reliable in silico prediction of which peptides would be presented and which T cell receptors would recognize them is an important problem in structural immunology. Here, we introduce an AlphaFold-based pipeline for predicting the three-dimensional structures of peptide-MHC complexes for class I and class II MHC molecules. Our method demonstrates high accuracy, outperforming existing tools in class I modeling accuracy and class II peptide register prediction. We validate its performance and utility with new experimental data on a recently described cancer neoantigen/wild-type peptide pair and explore applications toward improving peptide-MHC binding prediction.

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.

Accurate modeling of peptide-MHC structures with AlphaFold

Major histocompatibility complex (MHC) proteins present peptides on the cell surface for T-cell surveillance. Reliable in silico prediction of which peptides would be presented and which T-cell receptors would recognize them is an important problem in structural immunology. Here, we introduce an AlphaFold-based pipeline for predicting the three-dimensional structures of peptide-MHC complexes for class I and class II MHC molecules. Our method demonstrates high accuracy, outperforming existing tools in class I modeling precision and class II peptide register prediction. We explore applications of this method towards improving peptide-MHC binding prediction.

Assessment of commercial polymers with and without reactive groups using amino acid derivative reactivity assay based on both molar concentration approach and gravimetric approach

The amino acid derivative reactivity assay (ADRA), an alternative method for testing skin sensitization, has been established based on the molar concentration approach. However, the additional development of gravimetric concentration and fluorescence detection methods has expanded its range of application to mixtures, which cannot be evaluated using the conventional testing method, the direct peptide reactivity assay (DPRA). Although polymers are generally treated as mixtures, there have been no reports of actual polymer evaluations using alternative methods owing to their insolubility. Therefore, in this study, we evaluated skin sensitization potential of polymers, which is difficult to predict, using ADRA. As polymers have molecular weights ranging from several thousand to more than several tens of thousand Daltons, they are unlikely to cause skin sensitization due to their extremely low penetration into the skin, according to the 500-Da rule. However, if highly reactive functional groups remain at the ends or side chains of polymers, relatively low-molecular-weight polymer components may penetrate the skin to cause sensitization. Polymers can be roughly classified into three major types based on the features of their constituent monomers; we investigated the sensitization capacity of each type of polymer. Polymers with alert sensitization structures at their ends were classified as skin sensitizers, whereas those with no residual reactive groups were classified as nonsensitizers. Although polymers with a glycidyl group need to be evaluated carefully, we concluded that ADRA (0.5 mg/ml) is generally sufficient for polymer hazard assessment.

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.

Multiclass wound image classification using an ensemble deep CNN-based classifier

Acute and chronic wounds are a challenge to healthcare systems around the world and affect many people's lives annually. Wound classification is a key step in wound diagnosis that would help clinicians to identify an optimal treatment procedure. Hence, having a high-performance classifier assists wound specialists to classify wound types with less financial and time costs. Different wound classification methods based on machine learning and deep learning have been proposed in the literature. In this study, we have developed an ensemble Deep Convolutional Neural Network-based classifier to categorize wound images into multiple classes including surgical, diabetic, and venous ulcers. The output classification scores of two classifiers (namely, patch-wise and image-wise) are fed into a Multilayer Perceptron to provide a superior classification performance. A 5-fold cross-validation approach is used to evaluate the proposed method. We obtained maximum and average classification accuracy values of 96.4% and 94.28% for binary and 91.9% and 87.7% for 3-class classification problems. The proposed classifier was compared with some common deep classifiers and showed significantly higher accuracy metrics. We also tested the proposed method on the Medetec wound image dataset, and the accuracy values of 91.2% and 82.9% were obtained for binary and 3-class classifications. The results show that our proposed method can be used effectively as a decision support system in classification of wound images or other related clinical applications.

IDENTIFICATION OF MHC PEPTIDES USING MASS SPECTROMETRY FOR NEOANTIGEN DISCOVERY AND CANCER VACCINE DEVELOPMENT

Immunotherapy with neoantigens presented by major histocompatibility complex (MHC) is one of the most promising approaches in cancer treatment. Using this approach, cancer vaccines can be designed to target tumor-specific mutations that are not found in normal tissues. Clinical trials have demonstrated an increased immune response and eradication of tumors after injecting synthetic peptides selected from the immunopeptidome. Although the sequence of MHC binding peptides can be predicted from genome sequencing and prediction algorithms, this approach results in large numbers of predicted peptides, requiring the confirmation by mass spectrometry (MS) analysis. Identification of MHC peptides by direct MS analysis of immunopeptidome is accurate and sensitive, with tens of thousands of unique peptides potentially identified from either cancer cell line or tumor tissue. Peptides with mutations can also be identified with patient-specific protein databases constructed from genome or transcriptome sequencing data. MS analysis also enables the characterization of the post-translational modifications (PTMs) of those antigens that cannot be predicted. Moreover, PTMs were found to be more efficient in triggering an immune response. In addition to reviewing recent advances in the identification of neoantigens using MS, the techniques for cancer vaccine candidate selection and formulation, vaccine delivery systems, and the potential for use in combination with other therapeutics are also discussed. It is anticipated that MS-based techniques will play an important role in future cancer vaccine development. © 2019 John Wiley & Sons Ltd. Mass Spec Rev 40:110-125, 2021.

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.

Improved Prediction of MHC II Antigen Presentation through Integration and Motif Deconvolution of Mass Spectrometry MHC Eluted Ligand Data

Major histocompatibility complex II (MHC II) molecules play a vital role in the onset and control of cellular immunity. In a highly selective process, MHC II presents peptides derived from exogenous antigens on the surface of antigen-presenting cells for T cell scrutiny. Understanding the rules defining this presentation holds critical insights into the regulation and potential manipulation of the cellular immune system. Here, we apply the NNAlign_MA machine learning framework to analyze and integrate large-scale eluted MHC II ligand mass spectrometry (MS) data sets to advance prediction of CD4+ epitopes. NNAlign_MA allows integration of mixed data types, handling ligands with multiple potential allele annotations, encoding of ligand context, leveraging information between data sets, and has pan-specific power allowing accurate predictions outside the set of molecules included in the training data. Applying this framework, we identified accurate binding motifs of more than 50 MHC class II molecules described by MS data, particularly expanding coverage for DP and DQ beyond that obtained using current MS motif deconvolution techniques. Furthermore, in large-scale benchmarking, the final model termed NetMHCIIpan-4.0 demonstrated improved performance beyond current state-of-the-art predictors for ligand and CD4+ T cell epitope prediction. These results suggest that NNAlign_MA and NetMHCIIpan-4.0 are powerful tools for analysis of immunopeptidome MS data, prediction of T cell epitopes, and development of personalized immunotherapies.

T Cell Epitope Predictions

Throughout the body, T cells monitor MHC-bound ligands expressed on the surface of essentially all cell types. MHC ligands that trigger a T cell immune response are referred to as T cell epitopes. Identifying such epitopes enables tracking, phenotyping, and stimulating T cells involved in immune responses in infectious disease, allergy, autoimmunity, transplantation, and cancer. The specific T cell epitopes recognized in an individual are determined by genetic factors such as the MHC molecules the individual expresses, in parallel to the individual's environmental exposure history. The complexity and importance of T cell epitope mapping have motivated the development of computational approaches that predict what T cell epitopes are likely to be recognized in a given individual or in a broader population. Such predictions guide experimental epitope mapping studies and enable computational analysis of the immunogenic potential of a given protein sequence region.

Development of tumour peptide vaccines: From universalization to personalization

In recent years, relying on the human immune system to kill tumour cells has become an effective means of cancer treatment. The development of peptide vaccines, which not only break the immune tolerance of a tumour but also attack malignant cells via specific antitumour immunity, has received increased attention in tumour immunization therapy due to their safety and easy preparation. The use of large-scale sequencing technology enables the continuous discovery of new tumour antigens. With improved accuracy of epitope prediction by computer simulation and the usage of a tetramer assay, cytotoxic lymphocyte epitopes can be screened and identified more easily. Transmembrane peptide and nanoparticle technologies promote more effective intake and delivery of antigens. Consequently, considerable evolution from universal to personalized peptide vaccines has taken place, and such vaccines induce an efficient and specific immune response targeting tumour neoantigens. Recently, genomic analysis and bioinformatics approaches have greatly facilitated the breakthrough of personalized peptide vaccines targeting neoantigens, resulting in a renewed interest in this field. Further, the combination of tumour peptide vaccines with checkpoint blockades may improve patient outcomes. In this review, we discuss the development of tumour peptide vaccines and the new technological progress, from universalization to personalization, to highlight the substantial promise of tumour peptide vaccines in clinical cancer immunotherapy.

TEX19 promotes ovarian carcinoma progression and is a potential target for epitope vaccine immunotherapy

AIMS

Testis Expressed 19 (TEX19) is one of cancer/testis antigens identified in recent years and is related to the oncogenesis and progress of several cancers. This study aimed to reveal the role of TEX19 in ovarian cancer (OC) and searched for potential candidate epitope peptides of TEX19 to facilitate clinical application.

MAIN METHODS

TEX19 levels were evaluated by immunohistochemistry (IHC) in 98 human ovarian tissue samples. The correlation of TEX19 levels with patients' clinicopathological features was assessed. Quantitative real-time polymerase chain reaction (qRT-PCR) and western blotting analysis were utilized to detect TEX19 levels in ovarian cell lines and TEX19-deficient cells. The level of TEX19 in OVCAR-3 and A2780 was knocked down by small interfering RNA (siRNA), and loss-of-function assays were used to determine the biological effects of TEX19 on the proliferation, migration, and invasion of OC cells. Subsequently, candidate epitope peptides from TEX19 were predicted and verified by the IEDB database, pepsite2 website, MOE software, and T2 cell binding assay.

KEY FINDINGS

TEX19 was significantly upregulated in OC which correlated to higher TNM stage, lymph node involvement, and invasiveness. Knockdown of TEX19 inhibited proliferation, migration, and invasion of OC cells. Additionally, we screened four peptides derived from TEX19 and found TL to be the dominant peptide with the greatest affinity with HLA-A*0201.

SIGNIFICANCE

Our data indicated a cancer-promoting effect of TEX19 in OC and demonstrated that TL could be a potential candidate for an anti-tumor epitope vaccine of OC, suggesting that TEX19 is a promising biomarker and immunotherapeutic target for OC.

Machine Learning for Cancer Immunotherapies Based on Epitope Recognition by T Cell Receptors

In the last years, immunotherapies have shown tremendous success as treatments for multiple types of cancer. However, there are still many obstacles to overcome in order to increase response rates and identify effective therapies for every individual patient. Since there are many possibilities to boost a patient's immune response against a tumor and not all can be covered, this review is focused on T cell receptor-mediated therapies. CD8+ T cells can detect and destroy malignant cells by binding to peptides presented on cell surfaces by MHC (major histocompatibility complex) class I molecules. CD4+ T cells can also mediate powerful immune responses but their peptide recognition by MHC class II molecules is more complex, which is why the attention has been focused on CD8+ T cells. Therapies based on the power of T cells can, on the one hand, enhance T cell recognition by introducing TCRs that preferentially direct T cells to tumor sites (so called TCR-T therapy) or through vaccination to induce T cells in vivo. On the other hand, T cell activity can be improved by immune checkpoint inhibition or other means that help create a microenvironment favorable for cytotoxic T cell activity. The manifold ways in which the immune system and cancer interact with each other require not only the use of large omics datasets from gene, to transcript, to protein, and to peptide but also make the application of machine learning methods inevitable. Currently, discovering and selecting suitable TCRs is a very costly and work intensive in vitro process. To facilitate this process and to additionally allow for highly personalized therapies that can simultaneously target multiple patient-specific antigens, especially neoepitopes, breakthrough computational methods for predicting antigen presentation and TCR binding are urgently required. Particularly, potential cross-reactivity is a major consideration since off-target toxicity can pose a major threat to patient safety. The current speed at which not only datasets grow and are made available to the public, but also at which new machine learning methods evolve, is assuring that computational approaches will be able to help to solve problems that immunotherapies are still facing.

The role of artificial intelligence in orthopaedic surgery

Despite significant advances in orthopaedic surgery, variability still exists between providers and practice locations, and process inefficiencies are found throughout the health care continuum. Evolving technologies, namely artificial intelligence, challenge the status quo by improving patient care in four areas: diagnosis, management, research and systems analysis. Artificial intelligence shows promise in promoting practice efficiency, personalizing patient care, improving institutional research capacity, and expanding high quality orthopaedic care to lower resource settings. Physicians should be involved in the development of artificial intelligence algorithms to ensure that patients derive maximum benefit from new advances while considering the ethical challenges of implementation.

Alternative tumour-specific antigens

The study of tumour-specific antigens (TSAs) as targets for antitumour therapies has accelerated within the past decade. The most commonly studied class of TSAs are those derived from non-synonymous single-nucleotide variants (SNVs), or SNV neoantigens. However, to increase the repertoire of available therapeutic TSA targets, 'alternative TSAs', defined here as high-specificity tumour antigens arising from non-SNV genomic sources, have recently been evaluated. Among these alternative TSAs are antigens derived from mutational frameshifts, splice variants, gene fusions, endogenous retroelements and other processes. Unlike the patient-specific nature of SNV neoantigens, some alternative TSAs may have the advantage of being widely shared by multiple tumours, allowing for universal, off-the-shelf therapies. In this Opinion article, we will outline the biology, available computational tools, preclinical and/or clinical studies and relevant cancers for each alternative TSA class, as well as discuss both current challenges preventing the therapeutic application of alternative TSAs and potential solutions to aid in their clinical translation.

Computational Methods for Identification of T Cell Neoepitopes in Tumors

Cancer immunotherapy has experienced several major breakthroughs in the past decade. Most recently, technical advances in next-generation sequencing methods have enabled discovery of tumor-specific mutations leading to protective T cell neoepitopes. Many of the successes are enabled by computational methods, which facilitate processing of raw data, mapping of mutations, and prediction of neoepitopes. In this book chapter, we provide an overview of the computational tasks related to the identification of neoepitopes, propose specific tools and best practices, and discuss strengths, weaknesses, and future challenges.

Footprints of antigen processing boost MHC class II natural ligand predictions

Background

Major histocompatibility complex class II (MHC-II) molecules present peptide fragments to T cells for immune recognition. Current predictors for peptide to MHC-II binding are trained on binding affinity data, generated in vitro and therefore lacking information about antigen processing.

Methods

We generate prediction models of peptide to MHC-II binding trained with naturally eluted ligands derived from mass spectrometry in addition to peptide binding affinity data sets.

Results

We show that integrated prediction models incorporate identifiable rules of antigen processing. In fact, we observed detectable signals of protease cleavage at defined positions of the ligands. We also hypothesize a role of the length of the terminal ligand protrusions for trimming the peptide to the MHC presented ligand.

Conclusions

The results of integrating binding affinity and eluted ligand data in a combined model demonstrate improved performance for the prediction of MHC-II ligands and T cell epitopes and foreshadow a new generation of improved peptide to MHC-II prediction tools accounting for the plurality of factors that determine natural presentation of antigens.

Electronic supplementary material

The online version of this article (10.1186/s13073-018-0594-6) contains supplementary material, which is available to authorized users.

Predicting Antigen Presentation-What Could We Learn From a Million Peptides?

Antigen presentation lies at the heart of immune recognition of infected or malignant cells. For this reason, important efforts have been made to predict which peptides are more likely to bind and be presented by the human leukocyte antigen (HLA) complex at the surface of cells. These predictions have become even more important with the advent of next-generation sequencing technologies that enable researchers and clinicians to rapidly determine the sequences of pathogens (and their multiple variants) or identify non-synonymous genetic alterations in cancer cells. Here, we review recent advances in predicting HLA binding and antigen presentation in human cells. We argue that the very large amount of high-quality mass spectrometry data of eluted (mainly self) HLA ligands generated in the last few years provides unprecedented opportunities to improve our ability to predict antigen presentation and learn new properties of HLA molecules, as demonstrated in many recent studies of naturally presented HLA-I ligands. Although major challenges still lie on the road toward the ultimate goal of predicting immunogenicity, these experimental and computational developments will facilitate screening of putative epitopes, which may eventually help decipher the rules governing T cell recognition.

New tools for MHC research from machine learning and predictive algorithms to the tumour immunopeptidome

At a time when immunology seeks to progress ever more rapidly from characterization of a microbial or tumour antigen to the immune correlates that may define protective T-cell immunity, there is a need for robust tools to enable accurate predictions of peptide-major histocompatibility complex (pMHC) and peptide-MHC-T-cell receptor binding. Improvements in the curation of data sets from high throughput pMHC analysis, such as the NIH Immune Epitope Database (IEDB), and the associated developments of predictive tools rooted in machine-learning approaches, are having significant impact. When such approaches are linked to the powerful empirical immunopeptidome data sets from peptide MHC elution and mass spectrometry, there is considerable potential for rapid translation to T-cell therapies and vaccines.

Computational Tools for the Identification and Interpretation of Sequence Motifs in Immunopeptidomes

Recent advances in proteomics and mass-spectrometry have widely expanded the detectable peptide repertoire presented by major histocompatibility complex (MHC) molecules on the cell surface, collectively known as the immunopeptidome. Finely characterizing the immunopeptidome brings about important basic insights into the mechanisms of antigen presentation, but can also reveal promising targets for vaccine development and cancer immunotherapy. This report describes a number of practical and efficient approaches to analyze immunopeptidomics data, discussing the identification of meaningful sequence motifs in various scenarios and considering current limitations. Guidelines are provided for the filtering of false hits and contaminants, and to address the problem of motif deconvolution in cell lines expressing multiple MHC alleles, both for the MHC class I and class II systems. Finally, it is demonstrated how machine learning can be readily employed by non-expert users to generate accurate prediction models directly from mass-spectrometry eluted ligand data sets.