Robust prediction of HLA class II epitopes by deep motif deconvolution of immunopeptidomes

Neoantigen-specific T cell help outperforms non-specific help in multi-antigen DNA vaccination against cancer

CD4+ T helper antigens are essential components of cancer vaccines, but the relevance of the source of these MHC class II-restricted antigens remains underexplored. To compare the effectiveness of tumor-specific versus tumor-unrelated helper antigens, we designed three DNA vaccines for the murine MC-38 colon carcinoma, encoding CD8+ T cell neoantigens alone (noHELP) or in combination with either "universal" helper antigens (uniHELP) or helper neoantigens (neoHELP). Both types of helped vaccines increased the frequency of vaccine-induced CD8+ T cells, and particularly uniHELP increased the fraction of KLRG1+ and PD-1low effector cells. However, when mice were subsequently injected with MC-38 cells, only neoHELP vaccination resulted in significantly better tumor control than noHELP. In contrast to uniHELP, neoHELP-induced tumor control was dependent on the presence of CD4+ T cells, while both vaccines relied on CD8+ T cells. In line with this, neoHELP variants containing wild-type counterparts of the CD4+ or CD8+ T cell neoantigens displayed reduced tumor control. These data indicate that optimal personalized cancer vaccines should include MHC class II-restricted neoantigens to elicit tumor-specific CD4+ T cell help.

Deciphering the tumor immune microenvironment from a multidimensional omics perspective: insight into next-generation CAR-T cell immunotherapy and beyond

Tumor immune microenvironment (TIME) consists of intra-tumor immunological components and plays a significant role in tumor initiation, progression, metastasis, and response to therapy. Chimeric antigen receptor (CAR)-T cell immunotherapy has revolutionized the cancer treatment paradigm. Although CAR-T cell immunotherapy has emerged as a successful treatment for hematologic malignancies, it remains a conundrum for solid tumors. The heterogeneity of TIME is responsible for poor outcomes in CAR-T cell immunotherapy against solid tumors. The advancement of highly sophisticated technology enhances our exploration in TIME from a multi-omics perspective. In the era of machine learning, multi-omics studies could reveal the characteristics of TIME and its immune resistance mechanism. Therefore, the clinical efficacy of CAR-T cell immunotherapy in solid tumors could be further improved with strategies that target unfavorable conditions in TIME. Herein, this review seeks to investigate the factors influencing TIME formation and propose strategies for improving the effectiveness of CAR-T cell immunotherapy through a multi-omics perspective, with the ultimate goal of developing personalized therapeutic approaches.

A journey to your self: The vague definition of immune self and its practical implications

The identification of immunogenic peptides has become essential in an increasing number of fields in immunology, ranging from tumor immunotherapy to vaccine development. The nature of the adaptive immune response is shaped by the similarity between foreign and self-protein sequences, a concept extensively applied in numerous studies. Can we precisely define the degree of similarity to self? Furthermore, do we accurately define immune self? In the current work, we aim to unravel the conceptual and mechanistic vagueness hindering the assessment of self-similarity. Accordingly, we demonstrate the remarkably low consistency among commonly employed measures and highlight potential avenues for future research.

Artificial intelligence and neoantigens: paving the path for precision cancer immunotherapy

Cancer immunotherapy has witnessed rapid advancement in recent years, with a particular focus on neoantigens as promising targets for personalized treatments. The convergence of immunogenomics, bioinformatics, and artificial intelligence (AI) has propelled the development of innovative neoantigen discovery tools and pipelines. These tools have revolutionized our ability to identify tumor-specific antigens, providing the foundation for precision cancer immunotherapy. AI-driven algorithms can process extensive amounts of data, identify patterns, and make predictions that were once challenging to achieve. However, the integration of AI comes with its own set of challenges, leaving space for further research. With particular focus on the computational approaches, in this article we have explored the current landscape of neoantigen prediction, the fundamental concepts behind, the challenges and their potential solutions providing a comprehensive overview of this rapidly evolving field.

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

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

Individual and population-level variability in HLA-DR associated immunogenicity risk of biologics used for the treatment of rheumatoid arthritis

Hypothesis

While conventional in silico immunogenicity risk assessments focus on measuring immunogenicity based on the potential of therapeutic proteins to be processed and presented by a global population-wide set of human leukocyte antigen (HLA) alleles to T cells, future refinements might adjust for HLA allele frequencies in different geographic regions or populations, as well for as individuals in those populations. Adjustment by HLA allele distribution may reveal risk patterns that are specific to population groups or individuals, which current methods that rely on global-population HLA prevalence may obscure.

Key findings

This analysis uses HLA frequency-weighted binding predictions to define immunogenicity risk for global and sub-global populations. A comparison of assessments tuned for North American/European versus Japanese/Asian populations suggests that the potential for anti-therapeutic responses (anti-therapeutic antibodies or ATA) for several commonly prescribed Rheumatoid Arthritis (RA) therapeutic biologics may differ, significantly, between the Caucasian and Japanese populations. This appears to align with reports of differing product-related immunogenicity that is observed in different populations.

Relevance to clinical practice

Further definition of population-level (regional) and individual patient-specific immunogenic risk profiles may enable prescription of the RA therapeutic with the highest probability of success to each patient, depending on their population of origin and/or their individual HLA background. Furthermore, HLA-specific immunogenicity outcomes data are limited, thus there is a need to expand HLA-association studies that examine the relationship between HLA haplotype and ATA in the clinic.

Sliding Window INteraction Grammar (SWING): a generalized interaction language model for peptide and protein interactions

The explosion of sequence data has allowed the rapid growth of protein language models (pLMs). pLMs have now been employed in many frameworks including variant-effect and peptide-specificity prediction. Traditionally, for protein-protein or peptide-protein interactions (PPIs), corresponding sequences are either co-embedded followed by post-hoc integration or the sequences are concatenated prior to embedding. Interestingly, no method utilizes a language representation of the interaction itself. We developed an interaction LM (iLM), which uses a novel language to represent interactions between protein/peptide sequences. Sliding Window Interaction Grammar (SWING) leverages differences in amino acid properties to generate an interaction vocabulary. This vocabulary is the input into a LM followed by a supervised prediction step where the LM's representations are used as features. SWING was first applied to predicting peptide:MHC (pMHC) interactions. SWING was not only successful at generating Class I and Class II models that have comparable prediction to state-of-the-art approaches, but the unique Mixed Class model was also successful at jointly predicting both classes. Further, the SWING model trained only on Class I alleles was predictive for Class II, a complex prediction task not attempted by any existing approach. For de novo data, using only Class I or Class II data, SWING also accurately predicted Class II pMHC interactions in murine models of SLE (MRL/lpr model) and T1D (NOD model), that were validated experimentally. To further evaluate SWING's generalizability, we tested its ability to predict the disruption of specific protein-protein interactions by missense mutations. Although modern methods like AlphaMissense and ESM1b can predict interfaces and variant effects/pathogenicity per mutation, they are unable to predict interaction-specific disruptions. SWING was successful at accurately predicting the impact of both Mendelian mutations and population variants on PPIs. This is the first generalizable approach that can accurately predict interaction-specific disruptions by missense mutations with only sequence information. Overall, SWING is a first-in-class generalizable zero-shot iLM that learns the language of PPIs.

Predictability of B cell clonal persistence and immunosurveillance in breast cancer

B cells and T cells are important components of the adaptive immune system and mediate anticancer immunity. The T cell landscape in cancer is well characterized, but the contribution of B cells to anticancer immunosurveillance is less well explored. Here we show an integrative analysis of the B cell and T cell receptor repertoire from individuals with metastatic breast cancer and individuals with early breast cancer during neoadjuvant therapy. Using immune receptor, RNA and whole-exome sequencing, we show that both B cell and T cell responses seem to coevolve with the metastatic cancer genomes and mirror tumor mutational and neoantigen architecture. B cell clones associated with metastatic immunosurveillance and temporal persistence were more expanded and distinct from site-specific clones. B cell clonal immunosurveillance and temporal persistence are predictable from the clonal structure, with higher-centrality B cell antigen receptors more likely to be detected across multiple metastases or across time. This predictability was generalizable across other immune-mediated disorders. This work lays a foundation for prioritizing antibody sequences for therapeutic targeting in cancer.

CovEpiAb: a comprehensive database and analysis resource for immune epitopes and antibodies of human coronaviruses

Coronaviruses have threatened humans repeatedly, especially COVID-19 caused by SARS-CoV-2, which has posed a substantial threat to global public health. SARS-CoV-2 continuously evolves through random mutation, resulting in a significant decrease in the efficacy of existing vaccines and neutralizing antibody drugs. It is critical to assess immune escape caused by viral mutations and develop broad-spectrum vaccines and neutralizing antibodies targeting conserved epitopes. Thus, we constructed CovEpiAb, a comprehensive database and analysis resource of human coronavirus (HCoVs) immune epitopes and antibodies. CovEpiAb contains information on over 60 000 experimentally validated epitopes and over 12 000 antibodies for HCoVs and SARS-CoV-2 variants. The database is unique in (1) classifying and annotating cross-reactive epitopes from different viruses and variants; (2) providing molecular and experimental interaction profiles of antibodies, including structure-based binding sites and around 70 000 data on binding affinity and neutralizing activity; (3) providing virological characteristics of current and past circulating SARS-CoV-2 variants and in vitro activity of various therapeutics; and (4) offering site-level annotations of key functional features, including antibody binding, immunological epitopes, SARS-CoV-2 mutations and conservation across HCoVs. In addition, we developed an integrated pipeline for epitope prediction named COVEP, which is available from the webpage of CovEpiAb. CovEpiAb is freely accessible at https://pgx.zju.edu.cn/covepiab/.

TripHLApan: predicting HLA molecules binding peptides based on triple coding matrix and transfer learning

Human leukocyte antigen (HLA) recognizes foreign threats and triggers immune responses by presenting peptides to T cells. Computationally modeling the binding patterns between peptide and HLA is very important for the development of tumor vaccines. However, it is still a big challenge to accurately predict HLA molecules binding peptides. In this paper, we develop a new model TripHLApan for predicting HLA molecules binding peptides by integrating triple coding matrix, BiGRU + Attention models, and transfer learning strategy. We have found the main interaction site regions between HLA molecules and peptides, as well as the correlation between HLA encoding and binding motifs. Based on the discovery, we make the preprocessing and coding closer to the natural biological process. Besides, due to the input being based on multiple types of features and the attention module focused on the BiGRU hidden layer, TripHLApan has learned more sequence level binding information. The application of transfer learning strategies ensures the accuracy of prediction results under special lengths (peptides in length 8) and model scalability with the data explosion. Compared with the current optimal models, TripHLApan exhibits strong predictive performance in various prediction environments with different positive and negative sample ratios. In addition, we validate the superiority and scalability of TripHLApan's predictive performance using additional latest data sets, ablation experiments and binding reconstitution ability in the samples of a melanoma patient. The results show that TripHLApan is a powerful tool for predicting the binding of HLA-I and HLA-II molecular peptides for the synthesis of tumor vaccines. TripHLApan is publicly available at https://github.com/CSUBioGroup/TripHLApan.git.

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.

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.

Reducing Immunogenicity by Design: Approaches to Minimize Immunogenicity of Monoclonal Antibodies

Monoclonal antibodies (mAbs) have transformed therapeutic strategies for various diseases. Their high specificity to target antigens makes them ideal therapeutic agents for certain diseases. However, a challenge to their application in clinical practice is their potential risk to induce unwanted immune response, termed immunogenicity. This challenge drives the continued efforts to deimmunize these protein therapeutics while maintaining their pharmacokinetic properties and therapeutic efficacy. Because mAbs hold a central position in therapeutic strategies against an array of diseases, the importance of conducting comprehensive immunogenicity risk assessment during the drug development process cannot be overstated. Such assessment necessitates the employment of in silico, in vitro, and in vivo strategies to evaluate the immunogenicity risk of mAbs. Understanding the intricacies of the mechanisms that drive mAb immunogenicity is crucial to improving their therapeutic efficacy and safety and developing the most effective strategies to determine and mitigate their immunogenic risk. This review highlights recent advances in immunogenicity prediction strategies, with a focus on protein engineering strategies used throughout development to reduce immunogenicity.

Cancer neoepitopes viewed through negative selection and peripheral tolerance: a new path to cancer vaccines

A proportion of somatic mutations in tumors create neoepitopes that can prime T cell responses that target the MHC I-neoepitope complexes on tumor cells, mediating tumor control or rejection. Despite the compelling centrality of neoepitopes to cancer immunity, we know remarkably little about what constitutes a neoepitope that can mediate tumor control in vivo and what distinguishes such a neoepitope from the vast majority of similar candidate neoepitopes that are inefficacious in vivo. Studies in mice as well as clinical trials have begun to reveal the unexpected paradoxes in this area. Because cancer neoepitopes straddle that ambiguous ground between self and non-self, some rules that are fundamental to immunology of frankly non-self antigens, such as viral or model antigens, do not appear to apply to neoepitopes. Because neoepitopes are so similar to self-epitopes, with only small changes that render them non-self, immune response to them is regulated at least partially the way immune response to self is regulated. Therefore, neoepitopes are viewed and understood here through the clarifying lens of negative thymic selection. Here, the emergent questions in the biology and clinical applications of neoepitopes are discussed critically and a mechanistic and testable framework that explains the complexity and translational potential of these wonderful antigens is proposed.

Machine learning for functional protein design

Recent breakthroughs in AI coupled with the rapid accumulation of protein sequence and structure data have radically transformed computational protein design. New methods promise to escape the constraints of natural and laboratory evolution, accelerating the generation of proteins for applications in biotechnology and medicine. To make sense of the exploding diversity of machine learning approaches, we introduce a unifying framework that classifies models on the basis of their use of three core data modalities: sequences, structures and functional labels. We discuss the new capabilities and outstanding challenges for the practical design of enzymes, antibodies, vaccines, nanomachines and more. We then highlight trends shaping the future of this field, from large-scale assays to more robust benchmarks, multimodal foundation models, enhanced sampling strategies and laboratory automation.

Development and use of machine learning algorithms in vaccine target selection

Computer-aided discovery of vaccine targets has become a cornerstone of rational vaccine design. In this article, I discuss how Machine Learning (ML) can inform and guide key computational steps in rational vaccine design concerned with the identification of B and T cell epitopes and correlates of protection. I provide examples of ML models, as well as types of data and predictions for which they are built. I argue that interpretable ML has the potential to improve the identification of immunogens also as a tool for scientific discovery, by helping elucidate the molecular processes underlying vaccine-induced immune responses. I outline the limitations and challenges in terms of data availability and method development that need to be addressed to bridge the gap between advances in ML predictions and their translational application to vaccine design.

Synthetically mannosylated antigens induce antigen-specific humoral tolerance and reduce anti-drug antibody responses to immunogenic biologics

Immunogenic biologics trigger an anti-drug antibody (ADA) response in patients that reduces efficacy and increases adverse reactions. Our laboratory has shown that targeting protein antigen to the liver microenvironment can reduce antigen-specific T cell responses; herein, we present a strategy to increase delivery of otherwise immunogenic biologics to the liver via conjugation to a synthetic mannose polymer, p(Man). This delivery leads to reduced antigen-specific T follicular helper cell and B cell responses resulting in diminished ADA production, which is maintained throughout subsequent administrations of the native biologic. We find that p(Man)-antigen treatment impairs the ADA response against recombinant uricase, a highly immunogenic biologic, without a dependence on hapten immunodominance or control by T regulatory cells. We identify increased T cell receptor signaling and increased apoptosis and exhaustion in T cells as effects of p(Man)-antigen treatment via transcriptomic analyses. This modular platform may enhance tolerance to biologics, enabling long-term solutions for an ever-increasing healthcare problem.

Historical perspective and future directions: computational science in immuno-oncology

Immuno-oncology holds promise for transforming patient care having achieved durable clinical response rates across a variety of advanced and metastatic cancers. Despite these achievements, only a minority of patients respond to immunotherapy, underscoring the importance of elucidating molecular mechanisms responsible for response and resistance to inform the development and selection of treatments. Breakthroughs in molecular sequencing technologies have led to the generation of an immense amount of genomic and transcriptomic sequencing data that can be mined to uncover complex tumor-immune interactions using computational tools. In this review, we discuss existing and emerging computational methods that contextualize the composition and functional state of the tumor microenvironment, infer the reactivity and clonal dynamics from reconstructed immune cell receptor repertoires, and predict the antigenic landscape for immune cell recognition. We further describe the advantage of multi-omics analyses for capturing multidimensional relationships and artificial intelligence techniques for integrating omics data with histopathological and radiological images to encapsulate patterns of treatment response and tumor-immune biology. Finally, we discuss key challenges impeding their widespread use and clinical application and conclude with future perspectives. We are hopeful that this review will both serve as a guide for prospective researchers seeking to use existing tools for scientific discoveries and inspire the optimization or development of novel tools to enhance precision, ultimately expediting advancements in immunotherapy that improve patient survival and quality of life.

The SysteMHC Atlas v2.0, an updated resource for mass spectrometry-based immunopeptidomics

The SysteMHC Atlas v1.0 was the first public repository dedicated to mass spectrometry-based immunopeptidomics. Here we introduce a newly released version of the SysteMHC Atlas v2.0 (https://systemhc.sjtu.edu.cn), a comprehensive collection of 7190 MS files from 303 allotypes. We extended and optimized a computational pipeline that allows the identification of MHC-bound peptides carrying on unexpected post-translational modifications (PTMs), thereby resulting in 471K modified peptides identified over 60 distinct PTM types. In total, we identified approximately 1.0 million and 1.1 million unique peptides for MHC class I and class II immunopeptidomes, respectively, indicating a 6.8-fold increase and a 28-fold increase to those in v1.0. The SysteMHC Atlas v2.0 introduces several new features, including the inclusion of non-UniProt peptides, and the incorporation of several novel computational tools for FDR estimation, binding affinity prediction and motif deconvolution. Additionally, we enhanced the user interface, upgraded website framework, and provided external links to other resources related. Finally, we built and provided various spectral libraries as community resources for data mining and future immunopeptidomic and proteomic analysis. We believe that the SysteMHC Atlas v2.0 is a unique resource to provide key insights to the immunology and proteomics community and will accelerate the development of vaccines and immunotherapies.

How to Predict Binding Specificity and Ligands for New MHC-II Alleles with MixMHC2pred

MHC-II molecules are key mediators of antigen presentation in vertebrate species and bind to their ligands with high specificity. The very high polymorphism of MHC-II genes within species and the fast-evolving nature of these genes across species has resulted in tens of thousands of different alleles, with hundreds of new alleles being discovered yearly through large sequencing projects in different species. Here we describe how to use MixMHC2pred to predict the binding specificity of any MHC-II allele directly from its amino acid sequence. We then show how both MHC-II ligands and CD4+ T cell epitopes can be predicted in different species with our approach. MixMHC2pred is available at http://mixmhc2pred.gfellerlab.org/ .

In Silico Tools for Predicting Novel Epitopes

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

Systems immunology spanning tumors, lymph nodes, and periphery

The immune system defines a complex network of tissues and cell types that orchestrate responses across the body in a dynamic manner. The local and systemic interactions between immune and cancer cells contribute to disease progression. Lymphocytes are activated in lymph nodes, traffic through the periphery, and impact cancer progression through their interactions with tumor cells. As a result, therapeutic response and resistance are mediated across tissues, and a comprehensive understanding of lymphocyte dynamics requires a systems-level approach. In this review, we highlight experimental and computational methods that can leverage the study of leukocyte trafficking through an immunomics lens and reveal how adaptive immunity shapes cancer.

CD4 T cell-activating neoantigens enhance personalized cancer vaccine efficacy

Personalized cancer vaccines aim to activate and expand cytotoxic antitumor CD8+ T cells to recognize and kill tumor cells. However, the role of CD4+ T cell activation in the clinical benefit of these vaccines is not well defined. We previously established a personalized neoantigen vaccine (PancVAX) for the pancreatic cancer cell line Panc02, which activates tumor-specific CD8+ T cells but required combinatorial checkpoint modulators to achieve therapeutic efficacy. To determine the effects of neoantigen-specific CD4+ T cell activation, we generated a vaccine (PancVAX2) targeting both major histocompatibility complex class I- (MHCI-) and MHCII-specific neoantigens. Tumor-bearing mice vaccinated with PancVAX2 had significantly improved control of tumor growth and long-term survival benefit without concurrent administration of checkpoint inhibitors. PancVAX2 significantly enhanced priming and recruitment of neoantigen-specific CD8+ T cells into the tumor with lower PD-1 expression after reactivation compared with the CD8+ vaccine alone. Vaccine-induced neoantigen-specific Th1 CD4+ T cells in the tumor were associated with decreased Tregs. Consistent with this, PancVAX2 was associated with more proimmune myeloid-derived suppressor cells and M1-like macrophages in the tumor, demonstrating a less immunosuppressive tumor microenvironment. This study demonstrates the biological importance of prioritizing and including CD4+ T cell-specific neoantigens for personalized cancer vaccine modalities.

PANDORA v2.0: Benchmarking peptide-MHC II models and software improvements

T-cell specificity to differentiate between self and non-self relies on T-cell receptor (TCR) recognition of peptides presented by the Major Histocompatibility Complex (MHC). Investigations into the three-dimensional (3D) structures of peptide:MHC (pMHC) complexes have provided valuable insights of MHC functions. Given the limited availability of experimental pMHC structures and considerable diversity of peptides and MHC alleles, it calls for the development of efficient and reliable computational approaches for modeling pMHC structures. Here we present an update of PANDORA and the systematic evaluation of its performance in modelling 3D structures of pMHC class II complexes (pMHC-II), which play a key role in the cancer immune response. PANDORA is a modelling software that can build low-energy models in a few minutes by restraining peptide residues inside the MHC-II binding groove. We benchmarked PANDORA on 136 experimentally determined pMHC-II structures covering 44 unique αβ chain pairs. Our pipeline achieves a median backbone Ligand-Root Mean Squared Deviation (L-RMSD) of 0.42 Å on the binding core and 0.88 Å on the whole peptide for the benchmark dataset. We incorporated software improvements to make PANDORA a pan-allele framework and improved the user interface and software quality. Its computational efficiency allows enriching the wealth of pMHC binding affinity and mass spectrometry data with 3D models. These models can be used as a starting point for molecular dynamics simulations or structure-boosted deep learning algorithms to identify MHC-binding peptides. PANDORA is available as a Python package through Conda or as a source installation at https://github.com/X-lab-3D/PANDORA.

Accurate prediction of HLA class II antigen presentation across all loci using tailored data acquisition and refined machine learning

Accurate prediction of antigen presentation by human leukocyte antigen (HLA) class II molecules is crucial for rational development of immunotherapies and vaccines targeting CD4+ T cell activation. So far, most prediction methods for HLA class II antigen presentation have focused on HLA-DR because of limited availability of immunopeptidomics data for HLA-DQ and HLA-DP while not taking into account alternative peptide binding modes. We present an update to the NetMHCIIpan prediction method, which closes the performance gap between all three HLA class II loci. We accomplish this by first integrating large immunopeptidomics datasets describing the HLA class II specificity space across all loci using a refined machine learning framework that accommodates inverted peptide binders. Next, we apply targeted immunopeptidomics assays to generate data that covers additional HLA-DP specificities. The final method, NetMHCIIpan-4.3, achieves high accuracy and molecular coverage across all HLA class II allotypes.

Multiple instance learning to predict immune checkpoint blockade efficacy using neoantigen candidates

Previous studies showed that the neoantigen candidate load is an imperfect predictor of immune checkpoint blockade (ICB) efficacy. Further studies provided evidence that the response to ICB is also affected by the qualitative properties of a few or even single candidates, limiting the predictive power based on candidate quantity alone. Here, we predict ICB efficacy based on neoantigen candidates and their neoantigen features in the context of the mutation type, using Multiple-Instance Learning via Embedded Instance Selection (MILES). Multiple instance learning is a type of supervised machine learning that classifies labeled bags that are formed by a set of unlabeled instances. MILES performed better compared with neoantigen candidate load alone for low-abundant fusion genes in renal cell carcinoma. Our findings suggest that MILES is an appropriate method to predict the efficacy of ICB therapy based on neoantigen candidates without requiring direct T cell response information.

Experimental validation of immunogenic SARS-CoV-2 T cell epitopes identified by artificial intelligence

During the COVID-19 pandemic we utilized an AI-driven T cell epitope prediction tool, the NEC Immune Profiler (NIP) to scrutinize and predict regions of T cell immunogenicity (hotspots) from the entire SARS-CoV-2 viral proteome. These immunogenic regions offer potential for the development of universally protective T cell vaccine candidates. Here, we validated and characterized T cell responses to a set of minimal epitopes from these AI-identified universal hotspots. Utilizing a flow cytometry-based T cell activation-induced marker (AIM) assay, we identified 59 validated screening hits, of which 56% (33 peptides) have not been previously reported. Notably, we found that most of these novel epitopes were derived from the non-spike regions of SARS-CoV-2 (Orf1ab, Orf3a, and E). In addition, ex vivo stimulation with NIP-predicted peptides from the spike protein elicited CD8+ T cell response in PBMC isolated from most vaccinated donors. Our data confirm the predictive accuracy of AI platforms modelling bona fide immunogenicity and provide a novel framework for the evaluation of vaccine-induced T cell responses.

Recent advances in immunopeptidomic-based tumor neoantigen discovery

The role of aberrantly expressed proteins in tumors in driving immune-mediated control of cancer has been well documented for more than five decades. Today, we know that both aberrantly expressed normal proteins as well as mutant proteins (neoantigens) can function as tumor antigens in both humans and mice. Next-generation sequencing (NGS) and high-resolution mass spectrometry (MS) technologies have made significant advances since the early 2010s, enabling detection of rare but clinically relevant neoantigens recognized by T cells. MS profiling of tumor-specific immunopeptidomes remains the most direct method to identify mutant peptides bound to cellular MHC. However, the need for use of large numbers of cells or significant amounts of tumor tissue to achieve neoantigen detection has historically limited the application of MS. Newer, more sensitive MS technologies have recently demonstrated the capacities to detect neoantigens from fewer cells. Here, we highlight recent advancements in immunopeptidomics-based characterization of tumor-specific neoantigens. Various tumor antigen categories and neoantigen identification approaches are also discussed. Furthermore, we summarize recent reports that achieved successful tumor neoantigen detection by MS using a variety of starting materials, MS acquisition modes, and novel ion mobility devices.

Harnessing the power of artificial intelligence to advance cell therapy

Cell therapies are powerful technologies in which human cells are reprogrammed for therapeutic applications such as killing cancer cells or replacing defective cells. The technologies underlying cell therapies are increasing in effectiveness and complexity, making rational engineering of cell therapies more difficult. Creating the next generation of cell therapies will require improved experimental approaches and predictive models. Artificial intelligence (AI) and machine learning (ML) methods have revolutionized several fields in biology including genome annotation, protein structure prediction, and enzyme design. In this review, we discuss the potential of combining experimental library screens and AI to build predictive models for the development of modular cell therapy technologies. Advances in DNA synthesis and high-throughput screening techniques enable the construction and screening of libraries of modular cell therapy constructs. AI and ML models trained on this screening data can accelerate the development of cell therapies by generating predictive models, design rules, and improved designs.

Expanding the MAPPs Assay to Accommodate MHC-II Pan Receptors for Improved Predictability of Potential T Cell Epitopes

A critical step in the immunogenicity cascade is attributed to human leukocyte antigen (HLA) II presentation triggering T cell immune responses. The liquid chromatography-tandem mass spectrometry (LC-MS/MS)-based major histocompatibility complex (MHC) II-associated peptide proteomics (MAPPs) assay is implemented during preclinical risk assessments to identify biotherapeutic-derived T cell epitopes. Although studies indicate that HLA-DP and HLA-DQ alleles are linked to immunogenicity, most MAPPs studies are restricted to using HLA-DR as the dominant HLA II genotype due to the lack of well-characterized immunoprecipitating antibodies. Here, we address this issue by testing various commercially available clones of MHC-II pan (CR3/43, WR18, and Tü39), HLA-DP (B7/21), and HLA-DQ (SPV-L3 and 1a3) antibodies in the MAPPs assay, and characterizing identified peptides according to binding specificity. Our results reveal that HLA II receptor-precipitating reagents with similar reported specificities differ based on clonality and that MHC-II pan antibodies do not entirely exhibit pan-specific tendencies. Since no individual antibody clone is able to recover the complete HLA II peptide repertoire, we recommend a mixed strategy of clones L243, WR18, and SPV-L3 in a single immunoprecipitation step for more robust compound-specific peptide detection. Ultimately, our optimized MAPPs strategy improves the predictability and additional identification of T cell epitopes in immunogenicity risk assessments.

Synthetically mannosylated antigens induce antigen-specific humoral tolerance and reduce anti-drug antibody responses to immunogenic biologics

Immunogenic biologics trigger an anti-drug antibody (ADA) response in patients, which reduces efficacy and increases adverse reactions. Our laboratory has previously shown that targeting protein antigen to the liver microenvironment can reduce antigen-specific T cell responses; herein, we present a strategy to increase delivery of otherwise immunogenic biologics to the liver via conjugation to a synthetic mannose polymer (p(Man)). This delivery leads to reduced antigen-specific T follicular helper cell and B cell responses resulting in diminished ADA production, which is maintained throughout subsequent administrations of the native biologic. We found that p(Man)-antigen treatment impairs the ADA response against recombinant uricase, a highly immunogenic biologic, without a dependence on hapten immunodominance or control by Tregs. We identify increased TCR signaling and increased apoptosis and exhaustion in T cells as effects of p(Man)-antigen treatment via transcriptomic analyses. This modular platform may enhance tolerance to biologics, enabling long-term solutions for an ever-increasing healthcare problem.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Assessment of HLA-DPB1 genetic variation using an HLA-DP tool and its implications in clinical transplantation

HLA-DP is a classic transplantation antigen that mediates alloreactivity through T-cell epitope (TCE) diversity and expression levels. A current challenge is to integrate these functional features into the prospective selection of unrelated donor candidates for transplantation. Genetically, HLA-DPB1 exon 2 defines the permissive and nonpermissive TCE groups, and exons 2 and 3 (in linkage with rs9277534) indicate low- and high-expression allotypes. In this study, we analyzed 356 272 exon 2-exon 3-phased sequences from individuals across 5 self-identified race and ethnicity categories: White, Hispanic, Asian or Pacific Islander, Black or African American, and American Indian or Alaskan Native. This sequence data set revealed the complex relationship between TCE and expression models and the importance of exon 3 sequence data. We also studied archived donor search lists for 2545 patients who underwent transplantation from an HLA-11/12 unrelated donor mismatched for a single HLA-DPB1 allele. Depending on the order in which the TCE and expression criteria were considered, some patients had different TCE- and expression-favorable donors. In addition, this data set revealed that many expression-favorable alternatives existed in the search lists. To improve the selection of candidate donors, we provide, disseminate, and automate our findings through our multifaceted tool called Expression of HLA-DP Assessment Tool, consisting of a public web application, Python package, and analysis pipeline.

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

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

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."

Investigating the human and nonobese diabetic mouse MHC class II immunopeptidome using protein language modeling

MOTIVATION

Identifying peptides associated with the major histocompability complex class II (MHCII) is a central task in the evaluation of the immunoregulatory function of therapeutics and drug prototypes. MHCII-peptide presentation prediction has multiple biopharmaceutical applications, including the safety assessment of biologics and engineered derivatives in silico, or the fast progression of antigen-specific immunomodulatory drug discovery programs in immune disease and cancer. This has resulted in the collection of large-scale datasets on adaptive immune receptor antigenic responses and MHC-associated peptide proteomics. In parallel, recent deep learning algorithmic advances in protein language modeling have shown potential in leveraging large collections of sequence data and improve MHC presentation prediction.

RESULTS

Here, we train a compact transformer model (AEGIS) on human and mouse MHCII immunopeptidome data, including a preclinical murine model, and evaluate its performance on the peptide presentation prediction task. We show that the transformer performs on par with existing deep learning algorithms and that combining datasets from multiple organisms increases model performance. We trained variants of the model with and without MHCII information. In both alternatives, the inclusion of peptides presented by the I-Ag7 MHC class II molecule expressed by nonobese diabetic mice enabled for the first time the accurate in silico prediction of presented peptides in a preclinical type 1 diabetes model organism, which has promising therapeutic applications.

AVAILABILITY AND IMPLEMENTATION

The source code is available at https://github.com/Novartis/AEGIS.

HLA-II immunopeptidome profiling and deep learning reveal features of antigenicity to inform antigen discovery

CD4+ T cell responses are exquisitely antigen specific and directed toward peptide epitopes displayed by human leukocyte antigen class II (HLA-II) on antigen-presenting cells. Underrepresentation of diverse alleles in ligand databases and an incomplete understanding of factors affecting antigen presentation in vivo have limited progress in defining principles of peptide immunogenicity. Here, we employed monoallelic immunopeptidomics to identify 358,024 HLA-II binders, with a particular focus on HLA-DQ and HLA-DP. We uncovered peptide-binding patterns across a spectrum of binding affinities and enrichment of structural antigen features. These aspects underpinned the development of context-aware predictor of T cell antigens (CAPTAn), a deep learning model that predicts peptide antigens based on their affinity to HLA-II and full sequence of their source proteins. CAPTAn was instrumental in discovering prevalent T cell epitopes from bacteria in the human microbiome and a pan-variant epitope from SARS-CoV-2. Together CAPTAn and associated datasets present a resource for antigen discovery and the unraveling genetic associations of HLA alleles with immunopathologies.

A microfluidics-enabled automated workflow of sample preparation for MS-based immunopeptidomics

Mass spectrometry (MS)-based immunopeptidomics is an attractive antigen discovery method with growing clinical implications. However, the current experimental approach to extract HLA-restricted peptides requires a bulky sample source, which remains a challenge for obtaining clinical specimens. We present an innovative workflow that requires a low sample volume, which streamlines the immunoaffinity purification (IP) and C18 peptide cleanup on a single microfluidics platform with automated liquid handling and minimal sample transfers, resulting in higher assay sensitivity. We also demonstrate how the state-of-the-art data-independent acquisition (DIA) method further enhances the depth of tandem MS spectra-based peptide sequencing. Consequently, over 4,000 and 5,000 HLA-I-restricted peptides were identified from as few as 0.2 million RA957 cells and a melanoma tissue of merely 5 mg, respectively. We also identified multiple immunogenic tumor-associated antigens and hundreds of peptides derived from non-canonical protein sources. This workflow represents a powerful tool for identifying the immunopeptidome of sparse samples.

Unraveling the glycosylated immunopeptidome with HLA-Glyco

Recent interest in targeted therapies has been sparked by the study of MHC-associated peptides (MAPs) that undergo post-translational modifications (PTMs), particularly glycosylation. In this study, we introduce a fast computational workflow that merges the MSFragger-Glyco search algorithm with a false discovery rate control for glycopeptide analysis from mass spectrometry-based immunopeptidome data. By analyzing eight large-scale publicly available studies, we find that glycosylated MAPs are predominantly presented by MHC class II. Here, we present HLA-Glyco, a comprehensive resource containing over 3,400 human leukocyte antigen (HLA) class II N-glycopeptides from 1,049 distinct protein glycosylation sites. This resource provides valuable insights, including high levels of truncated glycans, conserved HLA-binding cores, and differences in glycosylation positional specificity between HLA allele groups. We integrate the workflow within the FragPipe computational platform and provide HLA-Glyco as a free web resource. Overall, our work provides a valuable tool and resource to aid the nascent field of glyco-immunopeptidomics.

Novel Immunotherapeutics: Perspectives on Checkpoints, Bispecifics, and Vaccines in Development

Over the past decade, the advent of molecular techniques and deeper understanding of the tumor microenvironment (TME) have enabled the development of a multitude of immunotherapy targets and approaches. Despite the revolutionary advancement in immunotherapy, treatment resistance remains a challenge leading to decreased response rate in a significant proportion of patients. As such, there has recently been an evolving focus to enhance efficacy, durability, and toxicity profiles of immunotherapy. Although immune checkpoint inhibitors have revolutionized cancer treatment with many already-approved antibodies and several others in the pipeline, bispecific antibodies build on their success in an attempt to deliver an even more potent immune response against tumor cells. On the other hand, vaccines comprise the oldest and most versatile form of immunotherapy. Peptide and nucleic acid vaccines are relatively simple to manufacture compared with oncolytic virus-based vaccines, whereas the dendritic cell vaccines are the most complex, requiring autologous cell culture. Nevertheless, a crucial question in the development of cancer vaccines is the choice of antigen whereby shared and patient-private antigen approaches are currently being pursued. There is hope that cancer vaccines will join the repertoire of successful novel immunotherapeutics in the market. Better insights into the impact of immunotherapy on effector T cells and other immune cell populations in the TME shall be a major priority across the immune-oncology discipline and can help identify predictive biomarkers to evaluate response to treatment and identify patients who would most likely benefit from immunotherapy.

Vaccine boosts T cells that target pancreatic tumours

Efforts to tackle pancreatic cancer by harnessing immune cells have had limited success. A clinical trial reports promising results from testing a personalized approach to boosting immune responses to such tumours. See p.144

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.

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.

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.

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

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

Machine learning reveals limited contribution of trans-only encoded variants to the HLA-DQ immunopeptidome

Human leukocyte antigen (HLA) class II antigen presentation is key for controlling and triggering T cell immune responses. HLA-DQ molecules, which are believed to play a major role in autoimmune diseases, are heterodimers that can be formed as both cis and trans variants depending on whether the α- and β-chains are encoded on the same (cis) or opposite (trans) chromosomes. So far, limited progress has been made for predicting HLA-DQ antigen presentation. In addition, the contribution of trans-only variants (i.e. variants not observed in the population as cis) in shaping the HLA-DQ immunopeptidome remains largely unresolved. Here, we seek to address these issues by integrating state-of-the-art immunoinformatics data mining models with large volumes of high-quality HLA-DQ specific mass spectrometry immunopeptidomics data. The analysis demonstrates highly improved predictive power and molecular coverage for models trained including these novel HLA-DQ data. More importantly, investigating the role of trans-only HLA-DQ variants reveals a limited to no contribution to the overall HLA-DQ immunopeptidome. In conclusion, this study furthers our understanding of HLA-DQ specificities and casts light on the relative role of cis versus trans-only HLA-DQ variants in the HLA class II antigen presentation space. The developed method, NetMHCIIpan-4.2, is available at https://services.healthtech.dtu.dk/services/NetMHCIIpan-4.2 .

The 2022 Report on the Human Proteome from the HUPO Human Proteome Project

The 2022 Metrics of the Human Proteome from the HUPO Human Proteome Project (HPP) show that protein expression has now been credibly detected (neXtProt PE1 level) for 18 407 (93.2%) of the 19 750 predicted proteins coded in the human genome, a net gain of 50 since 2021 from data sets generated around the world and reanalyzed by the HPP. Conversely, the number of neXtProt PE2, PE3, and PE4 missing proteins has been reduced by 78 from 1421 to 1343. This represents continuing experimental progress on the human proteome parts list across all the chromosomes, as well as significant reclassifications. Meanwhile, applying proteomics in a vast array of biological and clinical studies continues to yield significant findings and growing integration with other omics platforms. We present highlights from the Chromosome-Centric HPP, Biology and Disease-driven HPP, and HPP Resource Pillars, compare features of mass spectrometry and Olink and Somalogic platforms, note the emergence of translation products from ribosome profiling of small open reading frames, and discuss the launch of the initial HPP Grand Challenge Project, "A Function for Each Protein".

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

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

Machine learning predictions of MHC-II specificities reveal alternative binding mode of class II epitopes

CD4⁺ T cells orchestrate the adaptive immune response against pathogens and cancer by recognizing epitopes presented on class II major histocompatibility complex (MHC-II) molecules. The high polymorphism of MHC-II genes represents an important hurdle toward accurate prediction and identification of CD4⁺ T cell epitopes. Here we collected and curated a dataset of 627,013 unique MHC-II ligands identified by mass spectrometry. This enabled us to precisely determine the binding motifs of 88 MHC-II alleles across humans, mice, cattle, and chickens. Analysis of these binding specificities combined with X-ray crystallography refined our understanding of the molecular determinants of MHC-II motifs and revealed a widespread reverse-binding mode in HLA-DP ligands. We then developed a machine-learning framework to accurately predict binding specificities and ligands of any MHC-II allele. This tool improves and expands predictions of CD4⁺ T cell epitopes and enables us to discover viral and bacterial epitopes following the aforementioned reverse-binding mode.

Evolutionary origins and interactomes of human, young microproteins and small peptides translated from short open reading frames

All species continuously evolve short open reading frames (sORFs) that can be templated for protein synthesis and may provide raw materials for evolutionary adaptation. We analyzed the evolutionary origins of 7,264 recently cataloged human sORFs and found that most were evolutionarily young and had emerged de novo. We additionally identified 221 previously missed sORFs potentially translated into peptides of up to 15 amino acids-all of which are smaller than the smallest human microprotein annotated to date. To investigate the bioactivity of sORF-encoded small peptides and young microproteins, we subjected 266 candidates to a mass-spectrometry-based interactome screen with motif resolution. Based on these interactomes and additional cellular assays, we can associate several candidates with mRNA splicing, translational regulation, and endocytosis. Our work provides insights into the evolutionary origins and interaction potential of young and small proteins, thereby helping to elucidate this underexplored territory of the human proteome.