Predicting peptide presentation by major histocompatibility complex class I: an improved machine learning approach to the immunopeptidome

Recent Findings on Therapeutic Cancer Vaccines: An Updated Review

Cancer remains one of the global leading causes of death and various vaccines have been developed over the years against it, including cell-based, nucleic acid-based, and viral-based cancer vaccines. Although many vaccines have been effective in in vivo and clinical studies and some have been FDA-approved, there are major limitations to overcome: (1) developing one universal vaccine for a specific cancer is difficult, as tumors with different antigens are different for different individuals, (2) the tumor antigens may be similar to the body's own antigens, and (3) there is the possibility of cancer recurrence. Therefore, developing personalized cancer vaccines with the ability to distinguish between the tumor and the body's antigens is indispensable. This paper provides a comprehensive review of different types of cancer vaccines and highlights important factors necessary for developing efficient cancer vaccines. Moreover, the application of other technologies in cancer therapy is discussed. Finally, several insights and conclusions are presented, such as the possibility of using cold plasma and cancer stem cells in developing future cancer vaccines, to tackle the major limitations in the cancer vaccine developmental process.

ConvNeXt-MHC: improving MHC-peptide affinity prediction by structure-derived degenerate coding and the ConvNeXt model

Peptide binding to major histocompatibility complex (MHC) proteins plays a critical role in T-cell recognition and the specificity of the immune response. Experimental validation such peptides is extremely resource-intensive. As a result, accurate computational prediction of binding peptides is highly important, particularly in the context of cancer immunotherapy applications, such as the identification of neoantigens. In recent years, there is a significant need to continually improve the existing prediction methods to meet the demands of this field. We developed ConvNeXt-MHC, a method for predicting MHC-I-peptide binding affinity. It introduces a degenerate encoding approach to enhance well-established panspecific methods and integrates transfer learning and semi-supervised learning methods into the cutting-edge deep learning framework ConvNeXt. Comprehensive benchmark results demonstrate that ConvNeXt-MHC outperforms state-of-the-art methods in terms of accuracy. We expect that ConvNeXt-MHC will help us foster new discoveries in the field of immunoinformatics in the distant future. We constructed a user-friendly website at http://www.combio-lezhang.online/predict/, where users can access our data and application.

Informing immunotherapy with multi-omics driven machine learning

Progress in sequencing technologies and clinical experiments has revolutionized immunotherapy on solid and hematologic malignancies. However, the benefits of immunotherapy are limited to specific patient subsets, posing challenges for broader application. To improve its effectiveness, identifying biomarkers that can predict patient response is crucial. Machine learning (ML) play a pivotal role in harnessing multi-omic cancer datasets and unlocking new insights into immunotherapy. This review provides an overview of cutting-edge ML models applied in omics data for immunotherapy analysis, including immunotherapy response prediction and immunotherapy-relevant tumor microenvironment identification. We elucidate how ML leverages diverse data types to identify significant biomarkers, enhance our understanding of immunotherapy mechanisms, and optimize decision-making process. Additionally, we discuss current limitations and challenges of ML in this rapidly evolving field. Finally, we outline future directions aimed at overcoming these barriers and improving the efficiency of ML in immunotherapy research.

Challenges and solutions for therapeutic TCR-based agents

Recent development of methods to discover and engineer therapeutic T-cell receptors (TCRs) or antibody mimics of TCRs, and to understand their immunology and pharmacology, lag two decades behind therapeutic antibodies. Yet we have every expectation that TCR-based agents will be similarly important contributors to the treatment of a variety of medical conditions, especially cancers. TCR engineered cells, soluble TCRs and their derivatives, TCR-mimic antibodies, and TCR-based CAR T cells promise the possibility of highly specific drugs that can expand the scope of immunologic agents to recognize intracellular targets, including mutated proteins and undruggable transcription factors, not accessible by traditional antibodies. Hurdles exist regarding discovery, specificity, pharmacokinetics, and best modality of use that will need to be overcome before the full potential of TCR-based agents is achieved. HLA restriction may limit each agent to patient subpopulations and off-target reactivities remain important barriers to widespread development and use of these new agents. In this review we discuss the unique opportunities for these new classes of drugs, describe their unique antigenic targets, compare them to traditional antibody therapeutics and CAR T cells, and review the various obstacles that must be overcome before full application of these drugs can be realized.

Neoantigen identification: Technological advances and challenges

Neoantigens have emerged as promising targets for cutting-edge immunotherapies, such as cancer vaccines and adoptive cell therapy. These neoantigens are unique to tumors and arise exclusively from somatic mutations or non-genomic aberrations in tumor proteins. They encompass a wide range of alterations, including genomic mutations, post-transcriptomic variants, and viral oncoproteins. With the advancements in technology, the identification of immunogenic neoantigens has seen rapid progress, raising new opportunities for enhancing their clinical significance. Prediction of neoantigens necessitates the acquisition of high-quality samples and sequencing data, followed by mutation calling. Subsequently, the pipeline involves integrating various tools that can predict the expression, processing, binding, and recognition potential of neoantigens. However, the continuous improvement of computational tools is constrained by the availability of datasets which contain validated immunogenic neoantigens. This review article aims to provide a comprehensive summary of the current knowledge as well as limitations in neoantigen prediction and validation. Additionally, it delves into the origin and biological role of neoantigens, offering a deeper understanding of their significance in the field of cancer immunotherapy. This article thus seeks to contribute to the ongoing efforts to harness neoantigens as powerful weapons in the fight against cancer.

What Can Ribo-Seq, Immunopeptidomics, and Proteomics Tell Us About the Noncanonical Proteome?

Ribosome profiling (Ribo-Seq) has proven transformative for our understanding of the human genome and proteome by illuminating thousands of noncanonical sites of ribosome translation outside the currently annotated coding sequences (CDSs). A conservative estimate suggests that at least 7000 noncanonical ORFs are translated, which, at first glance, has the potential to expand the number of human protein CDSs by 30%, from ∼19,500 annotated CDSs to over 26,000 annotated CDSs. Yet, additional scrutiny of these ORFs has raised numerous questions about what fraction of them truly produce a protein product and what fraction of those can be understood as proteins according to conventional understanding of the term. Adding further complication is the fact that published estimates of noncanonical ORFs vary widely by around 30-fold, from several thousand to several hundred thousand. The summation of this research has left the genomics and proteomics communities both excited by the prospect of new coding regions in the human genome but searching for guidance on how to proceed. Here, we discuss the current state of noncanonical ORF research, databases, and interpretation, focusing on how to assess whether a given ORF can be said to be "protein coding."

Improved prediction of MHC-peptide binding using protein language models

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

What can Ribo-seq and proteomics tell us about the non-canonical proteome?

Ribosome profiling (Ribo-seq) has proven transformative for our understanding of the human genome and proteome by illuminating thousands of non-canonical sites of ribosome translation outside of the currently annotated coding sequences (CDSs). A conservative estimate suggests that at least 7,000 non-canonical open reading frames (ORFs) are translated, which, at first glance, has the potential to expand the number of human protein-coding sequences by 30%, from ∼19,500 annotated CDSs to over 26,000. Yet, additional scrutiny of these ORFs has raised numerous questions about what fraction of them truly produce a protein product and what fraction of those can be understood as proteins according to conventional understanding of the term. Adding further complication is the fact that published estimates of non-canonical ORFs vary widely by around 30-fold, from several thousand to several hundred thousand. The summation of this research has left the genomics and proteomics communities both excited by the prospect of new coding regions in the human genome, but searching for guidance on how to proceed. Here, we discuss the current state of non-canonical ORF research, databases, and interpretation, focusing on how to assess whether a given ORF can be said to be "protein-coding".

In brief

The human genome encodes thousands of non-canonical open reading frames (ORFs) in addition to protein-coding genes. As a nascent field, many questions remain regarding non-canonical ORFs. How many exist? Do they encode proteins? What level of evidence is needed for their verification? Central to these debates has been the advent of ribosome profiling (Ribo-seq) as a method to discern genome-wide ribosome occupancy, and immunopeptidomics as a method to detect peptides that are processed and presented by MHC molecules and not observed in traditional proteomics experiments. This article provides a synthesis of the current state of non-canonical ORF research and proposes standards for their future investigation and reporting.

Highlights

Combined use of Ribo-seq and proteomics-based methods enables optimal confidence in detecting non-canonical ORFs and their protein products.Ribo-seq can provide more sensitive detection of non-canonical ORFs, but data quality and analytical pipelines will impact results.Non-canonical ORF catalogs are diverse and span both high-stringency and low-stringency ORF nominations.A framework for standardized non-canonical ORF evidence will advance the research field.

Artificial intelligence-assisted selection and efficacy prediction of antineoplastic strategies for precision cancer therapy

The rapid development of artificial intelligence (AI) technologies in the context of the vast amount of collectable data obtained from high-throughput sequencing has led to an unprecedented understanding of cancer and accelerated the advent of a new era of clinical oncology with a tone of precision treatment and personalized medicine. However, the gains achieved by a variety of AI models in clinical oncology practice are far from what one would expect, and in particular, there are still many uncertainties in the selection of clinical treatment options that pose significant challenges to the application of AI in clinical oncology. In this review, we summarize emerging approaches, relevant datasets and open-source software of AI and show how to integrate them to address problems from clinical oncology and cancer research. We focus on the principles and procedures for identifying different antitumor strategies with the assistance of AI, including targeted cancer therapy, conventional cancer therapy, and cancer immunotherapy. In addition, we also highlight the current challenges and directions of AI in clinical oncology translation. Overall, we hope this article will provide researchers and clinicians with a deeper understanding of the role and implications of AI in precision cancer therapy, and help AI move more quickly into accepted cancer guidelines.

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

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

Challenges in neoantigen-directed therapeutics

A fundamental prerequisite for the efficacy of cancer immunotherapy is the presence of functional, antigen-specific T cells within the tumor. Neoantigen-directed therapy is a promising strategy that aims at targeting the host's immune response against tumor-specific antigens, thereby eradicating cancer cells. Initial forays have been made in clinical environments utilizing vaccines and adoptive cell therapy; however, many challenges lie ahead. We provide an in-depth overview of the current state of the field with an emphasis on in silico neoantigen discovery and the clinical aspects that need to be addressed to unlock the full potential of this therapy.

Artificial intelligence for prediction of response to cancer immunotherapy

Artificial intelligence (AI) indicates the application of machines to imitate intelligent behaviors for solving complex tasks with minimal human intervention, including machine learning and deep learning. The use of AI in medicine improves health-care systems in multiple areas such as diagnostic confirmation, risk stratification, analysis, prognosis prediction, treatment surveillance, and virtual health support, which has considerable potential to revolutionize and reshape medicine. In terms of immunotherapy, AI has been applied to unlock underlying immune signatures to associate with responses to immunotherapy indirectly as well as predict responses to immunotherapy responses directly. The AI-based analysis of high-throughput sequences and medical images can provide useful information for management of cancer immunotherapy considering the excellent abilities in selecting appropriate subjects, improving therapeutic regimens, and predicting individualized prognosis. In present review, we aim to evaluate a broad framework about AI-based computational approaches for prediction of response to cancer immunotherapy on both indirect and direct manners. Furthermore, we summarize our perspectives about challenges and opportunities of further AI applications on cancer immunotherapy relating to clinical practicability.

Improving MHC class I antigen-processing predictions using representation learning and cleavage site-specific kernels

In this work, we propose a new deep-learning model, MHCrank, to predict the probability that a peptide will be processed for presentation by MHC class I molecules. We find that the performance of our model is significantly higher than that of two previously published baseline methods: MHCflurry and netMHCpan. This improvement arises from utilizing both cleavage site-specific kernels and learned embeddings for amino acids. By visualizing site-specific amino acid enrichment patterns, we observe that MHCrank's top-ranked peptides exhibit enrichments at biologically relevant positions and are consistent with previous work. Furthermore, the cosine similarity matrix derived from MHCrank's learned embeddings for amino acids correlates highly with physiochemical properties that have been experimentally demonstrated to be instrumental in determining a peptide's favorability for processing. Altogether, the results reported in this work indicate that MHCrank demonstrates strong performance compared with existing methods and could have vast applicability in aiding drug and vaccine development.

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.

Promoting the formation of Pi-stacking interaction to improve CTL cells activation between modified peptide and HLA

OBJECTIVE

This study aims to investigate the use of single residue substitution to promote the formation of pi-stacking interactions between peptides and Human leukocyte antigen (HLA)-A*2402 molecules to improve the affinity of peptides and HLA molecules, as well as the level of cytotoxic T lymphocyte (CTL) cells activated by peptides-HLA (p-HLA) complex.

METHODS

Molecular docking and molecular dynamics simulation were used to simulate and analyze the interactions and binding free energies between HLA-A*2402-restricted antigen peptides and HLA molecules, before and after the single residue substitution. HLA-A*2402 restricted antigen peptides before and after the single residue replacement were loaded into dendritic cells (DCs) in vitro, and further Enzyme-Linked ImmunoSpot (ELispot) test was carried out to evaluate the effect of modified antigen peptides on the immune activation of CTL cells.

RESULT

After replacing the antigen peptides with a single residue, some of them could promote the formation of pi-stacking interaction. The binding free energy between the modified antigen peptides and HLA-A*2402, as well as the level of immune activation of CTL cells were mostly higher than before, especially after the replacement of the 9th residue of the polypeptide, such as C9F and C9W. There was a significant negative correlation between the level of activated CTL cells by modified antigen peptides and the total interaction amount of hydrogen bonds and salt bridges.

CONCLUSION

Promoting the formation of pi-stacking interaction between antigen peptides and HLA-A*2402 molecules could increase the total binding free energy of p-HLA complex and the level of CTL cells activation. In addition, the amount of hydrogen bonds and salt bridges between peptides and HLA could reduce the level of immune activation. All the characteristics above can improve the immunogenicities of the weak antigens.

The role of neoantigens in tumor immunotherapy

Tumor neoantigens are aberrant polypeptides produced by tumor cells as a result of genomic mutations. They are also tumor-specific antigens (TSA). Neoantigens are more immunogenic than tumor-related antigens and do not induce autoimmunity. Based on the rapid development of bioinformatics and the continuous update of sequencing technology, cancer immunotherapy with tumor neoantigens has made promising breakthroughs and progress. In this review, the generation, prediction, and identification of novel antigens, as well as the individualized treatments of neoantigens, were first introduced. Secondly, the mechanism of Chimeric Antigen Receptor T-Cell Immunotherapy (CAR-T) therapy and immune checkpoint blockade therapy in the treatment of tumors were outlined, and the three treatment methods were compared. Thirdly, the application of neoantigens in CAR-T therapy and PD-1/PD-L1 blockade therapy was briefly described. The benefits of the neoantigen vaccines over common vaccines were summarized as well. Finally, the prospect of neoantigen therapy was presented.

A Highly Effective System for Predicting MHC-II Epitopes With Immunogenicity

In the past decade, the substantial achievements of therapeutic cancer vaccines have shed a new light on cancer immunotherapy. The major challenge for designing potent therapeutic cancer vaccines is to identify neoantigens capable of inducing sufficient immune responses, especially involving major histocompatibility complex (MHC)-II epitopes. However, most previous studies on T-cell epitopes were focused on either ligand binding or antigen presentation by MHC rather than the immunogenicity of T-cell epitopes. In order to better facilitate a therapeutic vaccine design, in this study, we propose a revolutionary new tool: a convolutional neural network model named FIONA (Flexible Immunogenicity Optimization Neural-network Architecture) trained on IEDB datasets. FIONA could accurately predict the epitopes presented by the given specific MHC-II subtypes, as well as their immunogenicity. By leveraging the human leukocyte antigen allele hierarchical encoding model together with peptide dense embedding fusion encoding, FIONA (with AUC = 0.94) outperforms several other tools in predicting epitopes presented by MHC-II subtypes in head-to-head comparison; moreover, FIONA has unprecedentedly incorporated the capacity to predict the immunogenicity of epitopes with MHC-II subtype specificity. Therefore, we developed a reliable pipeline to effectively predict CD4+ T-cell immune responses against cancer and infectious diseases.

PredMHC: An Effective Predictor of Major Histocompatibility Complex Using Mixed Features

The major histocompatibility complex (MHC) is a large locus on vertebrate DNA that contains a tightly linked set of polymorphic genes encoding cell surface proteins essential for the adaptive immune system. The groups of proteins encoded in the MHC play an important role in the adaptive immune system. Therefore, the accurate identification of the MHC is necessary to understand its role in the adaptive immune system. An effective predictor called PredMHC is established in this study to identify the MHC from protein sequences. Firstly, PredMHC encoded a protein sequence with mixed features including 188D, APAAC, KSCTriad, CKSAAGP, and PAAC. Secondly, three classifiers including SGD, SMO, and random forest were trained on the mixed features of the protein sequence. Finally, the prediction result was obtained by the voting of the three classifiers. The experimental results of the 10-fold cross-validation test in the training dataset showed that PredMHC can obtain 91.69% accuracy. Experimental results on comparison with other features, classifiers, and existing methods showed the effectiveness of PredMHC in predicting the MHC.

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.

Positional SHAP (PoSHAP) for Interpretation of machine learning models trained from biological sequences

Machine learning with multi-layered artificial neural networks, also known as "deep learning," is effective for making biological predictions. However, model interpretation is challenging, especially for sequential input data used with recurrent neural network architectures. Here, we introduce a framework called "Positional SHAP" (PoSHAP) to interpret models trained from biological sequences by utilizing SHapely Additive exPlanations (SHAP) to generate positional model interpretations. We demonstrate this using three long short-term memory (LSTM) regression models that predict peptide properties, including binding affinity to major histocompatibility complexes (MHC), and collisional cross section (CCS) measured by ion mobility spectrometry. Interpretation of these models with PoSHAP reproduced MHC class I (rhesus macaque Mamu-A1*001 and human A*11:01) peptide binding motifs, reflected known properties of peptide CCS, and provided new insights into interpositional dependencies of amino acid interactions. PoSHAP should have widespread utility for interpreting a variety of models trained from biological sequences.

Applying artificial intelligence for cancer immunotherapy

Artificial intelligence (AI) is a general term that refers to the use of a machine to imitate intelligent behavior for performing complex tasks with minimal human intervention, such as machine learning; this technology is revolutionizing and reshaping medicine. AI has considerable potential to perfect health-care systems in areas such as diagnostics, risk analysis, health information administration, lifestyle supervision, and virtual health assistance. In terms of immunotherapy, AI has been applied to the prediction of immunotherapy responses based on immune signatures, medical imaging and histological analysis. These features could also be highly useful in the management of cancer immunotherapy given their ever-increasing performance in improving diagnostic accuracy, optimizing treatment planning, predicting outcomes of care and reducing human resource costs. In this review, we present the details of AI and the current progression and state of the art in employing AI for cancer immunotherapy. Furthermore, we discuss the challenges, opportunities and corresponding strategies in applying the technology for widespread clinical deployment. Finally, we summarize the impact of AI on cancer immunotherapy and provide our perspectives about underlying applications of AI in the future.

Predicting MHC class I binder: existing approaches and a novel recurrent neural network solution

Major histocompatibility complex (MHC) possesses important research value in the treatment of complex human diseases. A plethora of computational tools has been developed to predict MHC class I binders. Here, we comprehensively reviewed 27 up-to-date MHC I binding prediction tools developed over the last decade, thoroughly evaluating feature representation methods, prediction algorithms and model training strategies on a benchmark dataset from Immune Epitope Database. A common limitation was identified during the review that all existing tools can only handle a fixed peptide sequence length. To overcome this limitation, we developed a bilateral and variable long short-term memory (BVLSTM)-based approach, named BVLSTM-MHC. It is the first variable-length MHC class I binding predictor. In comparison to the 10 mainstream prediction tools on an independent validation dataset, BVLSTM-MHC achieved the best performance in six out of eight evaluated metrics. A web server based on the BVLSTM-MHC model was developed to enable accurate and efficient MHC class I binder prediction in human, mouse, macaque and chimpanzee.

Recent progress on MHC-I epitope prediction in tumor immunotherapy

Tumor immunotherapy has now become one of the most potential therapy for those intractable cancer diseases. The antigens on the cancer cell surfaces are the keys for the immune system to recognize and eliminate them. As reported, the immunogenicity of the tumor antigens could be determined by the binding between the key epitope peptides and MHC molecules. In recent years, the approaches to anticipate the peptides from the candidate epitopes have gradually changed into more efficient methods. Including the improved conventional methods, more diverse methods were coming into view. Here we review the anticipated methods of the tumor associated epitopes that specifically bind with major histocompatibility complex (MHC) class I molecules, and the recent advances and applications of those epitope prediction methods.

Ranking-Based Convolutional Neural Network Models for Peptide-MHC Class I Binding Prediction

T-cell receptors can recognize foreign peptides bound to major histocompatibility complex (MHC) class-I proteins, and thus trigger the adaptive immune response. Therefore, identifying peptides that can bind to MHC class-I molecules plays a vital role in the design of peptide vaccines. Many computational methods, for example, the state-of-the-art allele-specific method MHCflurry , have been developed to predict the binding affinities between peptides and MHC molecules. In this manuscript, we develop two allele-specific Convolutional Neural Network-based methods named ConvM and SpConvM to tackle the binding prediction problem. Specifically, we formulate the problem as to optimize the rankings of peptide-MHC bindings via ranking-based learning objectives. Such optimization is more robust and tolerant to the measurement inaccuracy of binding affinities, and therefore enables more accurate prioritization of binding peptides. In addition, we develop a new position encoding method in ConvM and SpConvM to better identify the most important amino acids for the binding events. We conduct a comprehensive set of experiments using the latest Immune Epitope Database (IEDB) datasets. Our experimental results demonstrate that our models significantly outperform the state-of-the-art methods including MHCflurry with an average percentage improvement of 6.70% on AUC and 17.10% on ROC5 across 128 alleles.

Using the antibody-antigen binding interface to train image-based deep neural networks for antibody-epitope classification

High-throughput B-cell sequencing has opened up new avenues for investigating complex mechanisms underlying our adaptive immune response. These technological advances drive data generation and the need to mine and analyze the information contained in these large datasets, in particular the identification of therapeutic antibodies (Abs) or those associated with disease exposure and protection. Here, we describe our efforts to use artificial intelligence (AI)-based image-analyses for prospective classification of Abs based solely on sequence information. We hypothesized that Abs recognizing the same part of an antigen share a limited set of features at the binding interface, and that the binding site regions of these Abs share share common structure and physicochemical property patterns that can serve as a "fingerprint" to recognize uncharacterized Abs. We combined large-scale sequence-based protein-structure predictions to generate ensembles of 3-D Ab models, reduced the Ab binding interface to a 2-D image (fingerprint), used pre-trained convolutional neural networks to extract features, and trained deep neural networks (DNNs) to classify Abs. We evaluated this approach using Ab sequences derived from human HIV and Ebola viral infections to differentiate between two Abs, Abs belonging to specific B-cell family lineages, and Abs with different epitope preferences. In addition, we explored a different type of DNN method to detect one class of Abs from a larger pool of Abs. Testing on Ab sets that had been kept aside during model training, we achieved average prediction accuracies ranging from 71-96% depending on the complexity of the classification task. The high level of accuracies reached during these classification tests suggests that the DNN models were able to learn a series of structural patterns shared by Abs belonging to the same class. The developed methodology provides a means to apply AI-based image recognition techniques to analyze high-throughput B-cell sequencing datasets (repertoires) for Ab classification.

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.

Large-Scale Structure-Based Prediction of Stable Peptide Binding to Class I HLAs Using Random Forests

Prediction of stable peptide binding to Class I HLAs is an important component for designing immunotherapies. While the best performing predictors are based on machine learning algorithms trained on peptide-HLA (pHLA) sequences, the use of structure for training predictors deserves further exploration. Given enough pHLA structures, a predictor based on the residue-residue interactions found in these structures has the potential to generalize for alleles with little or no experimental data. We have previously developed APE-Gen, a modeling approach able to produce pHLA structures in a scalable manner. In this work we use APE-Gen to model over 150,000 pHLA structures, the largest dataset of its kind, which were used to train a structure-based pan-allele model. We extract simple, homogenous features based on residue-residue distances between peptide and HLA, and build a random forest model for predicting stable pHLA binding. Our model achieves competitive AUROC values on leave-one-allele-out validation tests using significantly less data when compared to popular sequence-based methods. Additionally, our model offers an interpretation analysis that can reveal how the model composes the features to arrive at any given prediction. This interpretation analysis can be used to check if the model is in line with chemical intuition, and we showcase particular examples. Our work is a significant step toward using structure to achieve generalizable and more interpretable prediction for stable pHLA binding.

TCRs with Distinct Specificity Profiles Use Different Binding Modes to Engage an Identical Peptide-HLA Complex

The molecular rules driving TCR cross-reactivity are poorly understood and, consequently, it is unclear the extent to which TCRs targeting the same Ag recognize the same off-target peptides. We determined TCR-peptide-HLA crystal structures and, using a single-chain peptide-HLA phage library, we generated peptide specificity profiles for three newly identified human TCRs specific for the cancer testis Ag NY-ESO-1_157-165-HLA-A2. Two TCRs engaged the same central peptide feature, although were more permissive at peripheral peptide positions and, accordingly, possessed partially overlapping peptide specificity profiles. The third TCR engaged a flipped peptide conformation, leading to the recognition of off-target peptides sharing little similarity with the cognate peptide. These data show that TCRs specific for a cognate peptide recognize discrete peptide repertoires and reconciles how an individual's limited TCR repertoire following negative selection in the thymus is able to recognize a vastly larger antigenic pool.

Neoantigens in Hematologic Malignancies

T cell cancer neoantigens are created from peptides derived from cancer-specific aberrant proteins, such as mutated and fusion proteins, presented in complex with human leukocyte antigens on the cancer cell surface. Because expression of the aberrant target protein is exclusive to malignant cells, immunotherapy directed against neoantigens should avoid “on-target, off-tumor” toxicity. The efficacy of neoantigen vaccines in melanoma and glioblastoma and of adoptive transfer of neoantigen-specific T cells in epithelial tumors indicates that neoantigens are valid therapeutic targets. Improvements in sequencing technology and innovations in antigen discovery approaches have facilitated the identification of neoantigens. In comparison to many solid tumors, hematologic malignancies have few mutations and thus fewer potential neoantigens. Despite this, neoantigens have been identified in a wide variety of hematologic malignancies. These include mutated nucleophosmin1 and PML-RARA in acute myeloid leukemia, ETV6-RUNX1 fusions and other mutated proteins in acute lymphoblastic leukemia, BCR-ABL1 fusions in chronic myeloid leukemia, driver mutations in myeloproliferative neoplasms, immunoglobulins in lymphomas, and proteins derived from patient-specific mutations in chronic lymphoid leukemias. We will review advances in the field of neoantigen discovery, describe the spectrum of identified neoantigens in hematologic malignancies, and discuss the potential of these neoantigens for clinical translation.

High-Throughput Prediction of MHC Class I and II Neoantigens with MHCnuggets

Computational prediction of binding between neoantigen peptides and major histocompatibility complex (MHC) proteins can be used to predict patient response to cancer immunotherapy. Current neoantigen predictors focus on in silico estimation of MHC binding affinity and are limited by low predictive value for actual peptide presentation, inadequate support for rare MHC alleles, and poor scalability to high-throughput data sets. To address these limitations, we developed MHCnuggets, a deep neural network method that predicts peptide-MHC binding. MHCnuggets can predict binding for common or rare alleles of MHC class I or II with a single neural network architecture. Using a long short-term memory network (LSTM), MHCnuggets accepts peptides of variable length and is faster than other methods. When compared with methods that integrate binding affinity and MHC-bound peptide (HLAp) data from mass spectrometry, MHCnuggets yields a 4-fold increase in positive predictive value on independent HLAp data. We applied MHCnuggets to 26 cancer types in The Cancer Genome Atlas, processing 26.3 million allele-peptide comparisons in under 2.3 hours, yielding 101,326 unique predicted immunogenic missense mutations (IMM). Predicted IMM hotspots occurred in 38 genes, including 24 driver genes. Predicted IMM load was significantly associated with increased immune cell infiltration (P < 2 × 10^-16), including CD8⁺ T cells. Only 0.16% of predicted IMMs were observed in more than 2 patients, with 61.7% of these derived from driver mutations. Thus, we describe a method for neoantigen prediction and its performance characteristics and demonstrate its utility in data sets representing multiple human cancers.

Next-generation computational tools for interrogating cancer immunity

The remarkable success of cancer therapies with immune checkpoint blockers is revolutionizing oncology and has sparked intensive basic and translational research into the mechanisms of cancer-immune cell interactions. In parallel, numerous novel cutting-edge technologies for comprehensive molecular and cellular characterization of cancer immunity have been developed, including single-cell sequencing, mass cytometry and multiplexed spatial cellular phenotyping. In order to process, analyse and visualize multidimensional data sets generated by these technologies, computational methods and software tools are required. Here, we review computational tools for interrogating cancer immunity, discuss advantages and limitations of the various methods and provide guidelines to assist in method selection.

Bioinformatic methods for cancer neoantigen prediction

Tumor cells accumulate aberrations not present in normal cells, leading to presentation of neoantigens on MHC molecules on their surface. These non-self neoantigens distinguish tumor cells from normal cells to the immune system and are thus targets for cancer immunotherapy. The rapid development of molecular profiling platforms, such as next-generation sequencing, has enabled the generation of large datasets characterizing tumor cells. The simultaneous development of algorithms has enabled rapid and accurate processing of these data. Bioinformatic software tools encoding the algorithms can be strung together in a workflow to identify neoantigens. Here, with a focus on high-throughput sequencing, we review state-of-the art bioinformatic tools along with the steps and challenges involved in neoantigen identification and recognition.

Radiation therapy and anti-tumor immunity: exposing immunogenic mutations to the immune system

The expression of antigens that are recognized by self-reactive T cells is essential for immune-mediated tumor rejection by immune checkpoint blockade (ICB) therapy. Growing evidence suggests that mutation-associated neoantigens drive ICB responses in tumors with high mutational burden. In most patients, only a few of the mutations in the cancer exome that are predicted to be immunogenic are recognized by T cells. One factor that limits this recognition is the level of expression of the mutated gene product in cancer cells. Substantial preclinical data show that radiation can convert the irradiated tumor into a site for priming of tumor-specific T cells, that is, an in situ vaccine, and can induce responses in otherwise ICB-resistant tumors. Critical for radiation-elicited T-cell activation is the induction of viral mimicry, which is mediated by the accumulation of cytosolic DNA in the irradiated cells, with consequent activation of the cyclic GMP-AMP synthase (cGAS)/stimulator of interferon (IFN) genes (STING) pathway and downstream production of type I IFN and other pro-inflammatory cytokines. Recent data suggest that radiation can also enhance cancer cell antigenicity by upregulating the expression of a large number of genes that are involved in the response to DNA damage and cellular stress, thus potentially exposing immunogenic mutations to the immune system. Here, we discuss how the principles of antigen presentation favor the presentation of peptides that are derived from newly synthesized proteins in irradiated cells. These concepts support a model that incorporates the presence of immunogenic mutations in genes that are upregulated by radiation to predict which patients might benefit from treatment with combinations of radiotherapy and ICB.