APE-Gen: A Fast Method for Generating Ensembles of Bound Peptide-MHC Conformations

In silico advancements in Peptide-MHC interaction: A molecular dynamics study of predicted glypican-3 peptides and HLA-A*11:01

Our study employed molecular dynamics (MD) simulations to assess the binding affinity between short peptides derived from the tumor-associated antigen glypican 3 (GPC3) and the major histocompatibility complex (MHC) molecule HLA-A*11:01 in hepatocellular carcinoma. We aimed to improve the reliability of in silico predictions of peptide-MHC interactions, which are crucial for developing targeted cancer therapies. We used five algorithms to discover four peptides (TTDHLKFSK, VINTTDHLK, KLIMTQVSK, and STIHDSIQY), demonstrating the substantial potential for HLA-A11:01 presentation. The Anchored Peptide-MHC Ensemble Generator (APE-Gen) was used to create the initial structure of the peptide-MHC complex. This was followed by a 200 ns molecular dynamics (MD) simulation using AMBER22, which verified the precise positioning of the peptides in the binding groove of HLA-A*11:01, specifically at the A and F pockets. Notably, the 2nd residue, which serves as a critical anchor within the 2nd pocket, played a pivotal role in stabilising the binding interactions.VINTTDHLK (ΔG SIE = -14.46 ± 0.53 kcal/mol and ΔG MM/GBSA = -30.79 ± 0.49 kcal/mol) and STIHDSIQY (ΔG SIE and ΔG MM/GBSA = -14.55 ± 0.16 and -23.21 ± 2.23 kcal/mol) exhibited the most effective binding potential among the examined peptides, as indicated by both their binding free energies and its binding affinity on the T2 cell line (VINTTDHLK: IC50 = 0.45 nM; STIHDSIQY: IC50 = 0.35 nM). The remarkable concordance between in silico and in vitro binding affinity results was of particular significance, indicating that MD simulation is a potent instrument capable of bolstering confidence in in silico peptide predictions. By employing MD simulation as a method, our study provides a promising avenue for improving the prediction of potential peptide-MHC interactions, thereby facilitating the development of more effective and targeted cancer therapies.

MHC-Fine: Fine-tuned AlphaFold for precise MHC-peptide complex prediction

The precise prediction of major histocompatibility complex (MHC)-peptide complex structures is pivotal for understanding cellular immune responses and advancing vaccine design. In this study, we enhanced AlphaFold's capabilities by fine-tuning it with a specialized dataset consisting of exclusively high-resolution class I MHC-peptide crystal structures. This tailored approach aimed to address the generalist nature of AlphaFold's original training, which, while broad-ranging, lacked the granularity necessary for the high-precision demands of class I MHC-peptide interaction prediction. A comparative analysis was conducted against the homology-modeling-based method Pandora as well as the AlphaFold multimer model. Our results demonstrate that our fine-tuned model outperforms others in terms of root-mean-square deviation (median value for Cα atoms for peptides is 0.66 Å) and also provides enhanced predicted local distance difference test scores, offering a more reliable assessment of the predicted structures. These advances have substantial implications for computational immunology, potentially accelerating the development of novel therapeutics and vaccines by providing a more precise computational lens through which to view MHC-peptide interactions.

APE-Gen2.0: Expanding Rapid Class I Peptide-Major Histocompatibility Complex Modeling to Post-Translational Modifications and Noncanonical Peptide Geometries

The recognition of peptides bound to class I major histocompatibility complex (MHC-I) receptors by T-cell receptors (TCRs) is a determinant of triggering the adaptive immune response. While the exact molecular features that drive the TCR recognition are still unknown, studies have suggested that the geometry of the joint peptide-MHC (pMHC) structure plays an important role. As such, there is a definite need for methods and tools that accurately predict the structure of the peptide bound to the MHC-I receptor. In the past few years, many pMHC structural modeling tools have emerged that provide high-quality modeled structures in the general case. However, there are numerous instances of non-canonical cases in the immunopeptidome that the majority of pMHC modeling tools do not attend to, most notably, peptides that exhibit non-standard amino acids and post-translational modifications (PTMs) or peptides that assume non-canonical geometries in the MHC binding cleft. Such chemical and structural properties have been shown to be present in neoantigens; therefore, accurate structural modeling of these instances can be vital for cancer immunotherapy. To this end, we have developed APE-Gen2.0, a tool that improves upon its predecessor and other pMHC modeling tools, both in terms of modeling accuracy and the available modeling range of non-canonical peptide cases. Some of the improvements include (i) the ability to model peptides that have different types of PTMs such as phosphorylation, nitration, and citrullination; (ii) a new and improved anchor identification routine in order to identify and model peptides that exhibit a non-canonical anchor conformation; and (iii) a web server that provides a platform for easy and accessible pMHC modeling. We further show that structures predicted by APE-Gen2.0 can be used to assess the effects that PTMs have in binding affinity in a more accurate manner than just using solely the sequence of the peptide. APE-Gen2.0 is freely available at https://apegen.kavrakilab.org.

Repeated local ellipsoid protrusion supplements HLA surface characterization

Allorecognition of donor HLA is a major risk factor for long-term kidney graft survival. Although several molecular matching algorithms have been proposed that compare physiochemical and structural features of the donors' and recipients' HLA proteins in order to predict their compatibility, the exact underlying mechanisms are still not fully understood. We hypothesized that the ElliPro approach of single ellipsoid fitting and protrusion ranking lacks sensitivity for the characteristic shape of HLA molecules and developed a prediction pipeline named Snowball that is fitting smaller ellipsoids iteratively to substructures. Aggregated protrusion ranks of locally fitted ellipsoids were calculated for 712 publicly available HLA structures and 78 predicted structures using AlphaFold 2. Amino-acid sequence and protrusion ranks were used to train deep neural network predictors to infer protrusion ranks for all known HLA sequences. Snowball protrusion ranks appear to be more sensitive than ElliPro scores in fine parts of the HLA such as the helix structures forming the HLA binding groove in particular when the ellipsoids are fitted to substructures considering atoms within a 15 Å radius. A cloud-based web service was implemented based on amino-acid matching considering both protein- and position-specific surface area and protrusion ranks extending the previously presented Snowflake prediction pipeline.

MHC-Fine: Fine-tuned AlphaFold for Precise MHC-Peptide Complex Prediction

The precise prediction of Major Histocompatibility Complex (MHC)-peptide complex structures is pivotal for understanding cellular immune responses and advancing vaccine design. In this study, we enhanced AlphaFold's capabilities by fine-tuning it with a specialized dataset comprised by exclusively high-resolution MHC-peptide crystal structures. This tailored approach aimed to address the generalist nature of AlphaFold's original training, which, while broad-ranging, lacked the granularity necessary for the high-precision demands of MHC-peptide interaction prediction. A comparative analysis was conducted against the homology-modeling-based method Pandora [13], as well as the AlphaFold multimer model [8]. Our results demonstrate that our fine-tuned model outperforms both in terms of RMSD (median value is 0.65 Å) but also provides enhanced predicted lDDT scores, offering a more reliable assessment of the predicted structures. These advances have substantial implications for computational immunology, potentially accelerating the development of novel therapeutics and vaccines by providing a more precise computational lens through which to view MHC-peptide interactions.

HLA3DB: comprehensive annotation of peptide/HLA complexes enables blind structure prediction of T cell epitopes

The class I proteins of the major histocompatibility complex (MHC-I) display epitopic peptides derived from endogenous proteins on the cell surface for immune surveillance. Accurate modeling of peptides bound to the human MHC, HLA, has been mired by conformational diversity of the central peptide residues, which are critical for recognition by T cell receptors. Here, analysis of X-ray crystal structures within our curated database (HLA3DB) shows that pHLA complexes encompassing multiple HLA allotypes present a discrete set of peptide backbone conformations. Leveraging these backbones, we employ a regression model trained on terms of a physically relevant energy function to develop a comparative modeling approach for nonamer pHLA structures named RepPred. Our method outperforms the top pHLA modeling approach by up to 19% in structural accuracy, and consistently predicts blind targets not included in our training set. Insights from our work may be applied towards predicting antigen immunogenicity, and receptor cross-reactivity.

PepSim: T-cell cross-reactivity prediction via comparison of peptide sequence and peptide-HLA structure

Introduction

Peptide-HLA class I (pHLA) complexes on the surface of tumor cells can be targeted by cytotoxic T-cells to eliminate tumors, and this is one of the bases for T-cell-based immunotherapies. However, there exist cases where therapeutic T-cells directed towards tumor pHLA complexes may also recognize pHLAs from healthy normal cells. The process where the same T-cell clone recognizes more than one pHLA is referred to as T-cell cross-reactivity and this process is driven mainly by features that make pHLAs similar to each other. T-cell cross-reactivity prediction is critical for designing T-cell-based cancer immunotherapies that are both effective and safe.

Methods

Here we present PepSim, a novel score to predict T-cell cross-reactivity based on the structural and biochemical similarity of pHLAs.

Results and discussion

We show our method can accurately separate cross-reactive from non-crossreactive pHLAs in a diverse set of datasets including cancer, viral, and self-peptides. PepSim can be generalized to work on any dataset of class I peptide-HLAs and is freely available as a web server at pepsim.kavrakilab.org.

HLA3DB: comprehensive annotation of peptide/HLA complexes enables blind structure prediction of T cell epitopes

The class I proteins of the major histocompatibility complex (MHC-I) display epitopic peptides derived from endogenous proteins on the cell surface for immune surveillance. Accurate modeling of peptide/HLA (pHLA, the human MHC) structures has been mired by conformational diversity of the central peptide residues, which are critical for recognition by T cell receptors. Here, analysis of X-ray crystal structures within a curated database (HLA3DB) shows that pHLA complexes encompassing multiple HLA allotypes present a discrete set of peptide backbone conformations. Leveraging these representative backbones, we employ a regression model trained on terms of a physically relevant energy function to develop a comparative modeling approach for nonamer peptide/HLA structures named RepPred. Our method outperforms the top pHLA modeling approach by up to 19% in terms of structural accuracy, and consistently predicts blind targets not included in our training set. Insights from our work provide a framework for linking conformational diversity with antigen immunogenicity and receptor cross-reactivity.

Computational Approaches Drive Developments in Immune-Oncology Therapies for PD-1/PD-L1 Immune Checkpoint Inhibitors

Computational approaches in immune-oncology therapies focus on using data-driven methods to identify potential immune targets and develop novel drug candidates. In particular, the search for PD-1/PD-L1 immune checkpoint inhibitors (ICIs) has enlivened the field, leveraging the use of cheminformatics and bioinformatics tools to analyze large datasets of molecules, gene expression and protein-protein interactions. Up to now, there is still an unmet clinical need for improved ICIs and reliable predictive biomarkers. In this review, we highlight the computational methodologies applied to discovering and developing PD-1/PD-L1 ICIs for improved cancer immunotherapies with a greater focus in the last five years. The use of computer-aided drug design structure- and ligand-based virtual screening processes, molecular docking, homology modeling and molecular dynamics simulations methodologies essential for successful drug discovery campaigns focusing on antibodies, peptides or small-molecule ICIs are addressed. A list of recent databases and web tools used in the context of cancer and immunotherapy has been compilated and made available, namely regarding a general scope, cancer and immunology. In summary, computational approaches have become valuable tools for discovering and developing ICIs. Despite significant progress, there is still a need for improved ICIs and biomarkers, and recent databases and web tools have been compiled to aid in this pursuit.

MHC2AffyPred: A machine-learning approach to estimate affinity of MHC class II peptides based on structural interaction fingerprints

Understanding how MHC class II (MHC-II) binding peptides with differing lengths exhibit specific interaction at the core and extended sites within the large MHC-II pocket is a very important aspect of immunological research for designing peptides. Certain efforts were made to generate peptide conformations amenable for MHC-II binding and calculate the binding energy of such complex formation but not directed toward developing a relationship between the peptide conformation in MHC-II structures and the binding affinity (BA) (IC₅₀ ). We present here a machine-learning approach to calculate the BA of the peptides within the MHC-II pocket for HLA-DRA1, HLA-DRB1, HLA-DP, and HLA-DQ allotypes. Instead of generating ensembles of peptide conformations conventionally, the biased mode of conformations was created by considering the peptides in the crystal structures of pMHC-II complexes as the templates, followed by site-directed peptide docking. The structural interaction fingerprints generated from such docked pMHC-II structures along with the Moran autocorrelation descriptors were trained using a random forest regressor specific to each MHC-II peptide lengths (9-19). The entire workflow is automated using Linux shell and Perl scripts to promote the utilization of MHC2AffyPred program to any characterized MHC-II allotypes and is made for free access at https://github.com/SiddhiJani/MHC2AffyPred. The MHC2AffyPred attained better performance (correlation coefficient [CC] of .612-.898) than MHCII3D (.03-.594) and NetMHCIIpan-3.2 (.289-.692) programs in the HLA-DRA1, HLA-DRB1 types. Similarly, the MHC2AffyPred program achieved CC between .91 and .98 for HLA-DP and HLA-DQ peptides (13-mer to 17-mer). Further, a case study on MHC-II binding 15-mer peptides of severe acute respiratory syndrome coronavirus-2 showed very close competency in computing the IC₅₀ values compared to the sequence-based NetMHCIIpan v3.2 and v4.0 programs with a correlation of .998 and .570, respectively.

The PANDORA Software for Anchor-Restrained Peptide:MHC Modeling

Major histocompatibility complexes (MHC) play a key role in the immune surveillance system in all jawed vertebrates. MHC class I molecules randomly sample cytosolic peptides from inside the cell, while MHC class II sample exogenous peptides. Both types of peptide:MHC complex are then presented on the cell surface for recognition by αβ T cells (CD8+ and CD4+, respectively). The three-dimensional structure of such complexes can give crucial insights in the presentation and recognition mechanisms. For this reason, softwares like PANDORA have been developed to rapidly and accurately generate peptide:MHC (pMHC) 3D structures. In this chapter, we describe the protocol of PANDORA. PANDORA exploits the structural knowledge on anchor pockets that MHC molecules use to dock peptides. PANDORA provides anchor positions as restraints to guide the modeling process. This allows PANDORA to generate twenty 3D models in just about 5 min. PANDORA is highly customizable, easy to install, supports parallel processing, and is suitable to provide large datasets for deep learning algorithms.

Snowflake epitope matching correlates with child-specific antibodies during pregnancy and donor-specific antibodies after kidney transplantation

Development of donor-specific human leukocyte antigen (HLA) antibodies (DSA) remains a major risk factor for graft loss following organ transplantation, where DSA are directed towards patches on the three-dimensional structure of the respective organ donor's HLA proteins. Matching donors and recipients based on HLA epitopes appears beneficial for the avoidance of DSA. Defining surface epitopes however remains challenging and the concepts underlying their characterization are not fully understood. Based on our recently implemented computational deep learning pipeline to define HLA Class I protein-specific surface residues, we hypothesized a correlation between the number of HLA protein-specific solvent-accessible interlocus amino acid mismatches (arbitrarily called Snowflake) and the incidence of DSA. To validate our hypothesis, we considered two cohorts simultaneously. The kidney transplant cohort (KTC) considers 305 kidney-transplanted patients without DSA prior to transplantation. During the follow-up, HLA antibody screening was performed regularly to identify DSA. The pregnancy cohort (PC) considers 231 women without major sensitization events prior to pregnancy who gave live birth. Post-delivery serum was screened for HLA antibodies directed against the child's inherited paternal haplotype (CSA). Based on the involved individuals' HLA typings, the numbers of interlocus-mismatched antibody-verified eplets (AbvEPS), the T cell epitope PIRCHE-II model and Snowflake were calculated locus-specific (HLA-A, -B and -C), normalized and pooled. In both cohorts, Snowflake numbers were significantly elevated in recipients/mothers that developed DSA/CSA. Univariable regression revealed significant positive correlation between DSA/CSA and AbvEPS, PIRCHE-II and Snowflake. Snowflake numbers showed stronger correlation with numbers of AbvEPS compared to Snowflake numbers with PIRCHE-II. Our data shows correlation between Snowflake scores and the incidence of DSA after allo-immunization. Given both AbvEPS and Snowflake are B cell epitope models, their stronger correlation compared to PIRCHE-II and Snowflake appears plausible. Our data confirms that exploring solvent accessibility is a valuable approach for refining B cell epitope definitions.

Snowflake: A deep learning-based human leukocyte antigen matching algorithm considering allele-specific surface accessibility

Histocompatibility in solid-organ transplantation has a strong impact on long-term graft survival. Although recent advances in matching of both B-cell epitopes and T-cell epitopes have improved understanding of allorecognition, the immunogenic determinants are still not fully understood. We hypothesized that HLA solvent accessibility is allele-specific, thus supporting refinement of HLA B-cell epitope prediction. We developed a computational pipeline named Snowflake to calculate solvent accessibility of HLA Class I proteins for deposited HLA crystal structures, supplemented by constructed HLA structures through the AlphaFold protein folding predictor and peptide binding predictions of the APE-Gen docking framework. This dataset trained a four-layer long short-term memory bidirectional recurrent neural network, which in turn inferred solvent accessibility of all known HLA Class I proteins. We extracted 676 HLA Class-I experimental structures from the Protein Data Bank and supplemented it by 37 Class-I alleles for which structures were predicted. For each of the predicted structures, 10 known binding peptides as reported by the Immune Epitope DataBase were rendered into the binding groove. Although HLA Class I proteins predominantly are folded similarly, we found higher variation in root mean square difference of solvent accessibility between experimental structures of different HLAs compared to structures with identical amino acid sequence, suggesting HLA’s solvent accessible surface is protein specific. Hence, residues may be surface-accessible on e.g. HLA-A*02:01, but not on HLA-A*01:01. Mapping these data to antibody-verified epitopes as defined by the HLA Epitope Registry reveals patterns of (1) consistently accessible residues, (2) only subsets of an epitope’s residues being consistently accessible and (3) varying surface accessibility of residues of epitopes. Our data suggest B-cell epitope definitions can be refined by considering allele-specific solvent-accessibility, rather than aggregating HLA protein surface maps by HLA class or locus. To support studies on epitope analyses in organ transplantation, the calculation of donor-allele-specific solvent-accessible amino acid mismatches was implemented as a cloud-based web service.

SARS-Arena: Sequence and Structure-Guided Selection of Conserved Peptides from SARS-related Coronaviruses for Novel Vaccine Development

The pandemic caused by the SARS-CoV-2 virus, the agent responsible for the COVID-19 disease, has affected millions of people worldwide. There is constant search for new therapies to either prevent or mitigate the disease. Fortunately, we have observed the successful development of multiple vaccines. Most of them are focused on one viral envelope protein, the spike protein. However, such focused approaches may contribute for the rise of new variants, fueled by the constant selection pressure on envelope proteins, and the widespread dispersion of coronaviruses in nature. Therefore, it is important to examine other proteins, preferentially those that are less susceptible to selection pressure, such as the nucleocapsid (N) protein. Even though the N protein is less accessible to humoral response, peptides from its conserved regions can be presented by class I Human Leukocyte Antigen (HLA) molecules, eliciting an immune response mediated by T-cells. Given the increased number of protein sequences deposited in biological databases daily and the N protein conservation among viral strains, computational methods can be leveraged to discover potential new targets for SARS-CoV-2 and SARS-CoV-related viruses. Here we developed SARS-Arena, a user-friendly computational pipeline that can be used by practitioners of different levels of expertise for novel vaccine development. SARS-Arena combines sequence-based methods and structure-based analyses to (i) perform multiple sequence alignment (MSA) of SARS-CoV-related N protein sequences, (ii) recover candidate peptides of different lengths from conserved protein regions, and (iii) model the 3D structure of the conserved peptides in the context of different HLAs. We present two main Jupyter Notebook workflows that can help in the identification of new T-cell targets against SARS-CoV viruses. In fact, in a cross-reactive case study, our workflows identified a conserved N protein peptide (SPRWYFYYL) recognized by CD8⁺ T-cells in the context of HLA-B7⁺. SARS-Arena is available at https://github.com/KavrakiLab/SARS-Arena.

Binding Affinity Calculations of Gluten Peptides to HLA Risk Modifiers: DQ2.5 versus DQ7.5

Free energy perturbation (FEP) calculations can predict relative binding affinities of an antigen and its point mutants to the same human leukocyte antigen (HLA) with high accuracy (e.g., within 1.0 kcal/mol to experiment); however, a more challenging task is to compare binding affinities of wholly different antigens binding to completely different HLAs using FEP. Researchers have used a variety of different FEP schemes to compute and compare absolute binding affinities, with varied success. Here, we propose and assess a unifying scheme to compute the relative binding affinities of different antigens binding to completely different HLAs using absolute binding affinity FEP calculations. We apply our affinity calculation technique to HLA-antigen-T-cell receptor (TCR) systems relevant to celiac disease (CeD) by investigating binding affinity differences between HLA-DQ2.5 (enhanced CeD risk) and HLA-DQ7.5 (CeD protective) in the binary (HLA-gliadin) and ternary (HLA-gliadin-TCR) binding complexes for three gliadin derived epitopes: glia-α1, glia-α2, and glia-ω1. Based on FEP calculations with our carefully designed thermodynamic cycles, we demonstrate that HLA-DQ2.5 has higher binding affinity than HLA-DQ7.5 for gliadin and enhanced binding affinity with a common TCR, agreeing with known results that the HLA-DQ2.5 serotype exhibits increased risk for CeD. Our findings reveal that our proposed absolute binding affinity FEP method is appropriate for predicting HLA binding for disparate antigens with different genotypes. We also discuss atomic-level details of HLA genotypes interacting with gluten peptides and TCRs in regard to the pathogenesis of CeD.

3pHLA-score improves structure-based peptide-HLA binding affinity prediction

Binding of peptides to Human Leukocyte Antigen (HLA) receptors is a prerequisite for triggering immune response. Estimating peptide-HLA (pHLA) binding is crucial for peptide vaccine target identification and epitope discovery pipelines. Computational methods for binding affinity prediction can accelerate these pipelines. Currently, most of those computational methods rely exclusively on sequence-based data, which leads to inherent limitations. Recent studies have shown that structure-based data can address some of these limitations. In this work we propose a novel machine learning (ML) structure-based protocol to predict binding affinity of peptides to HLA receptors. For that, we engineer the input features for ML models by decoupling energy contributions at different residue positions in peptides, which leads to our novel per-peptide-position protocol. Using Rosetta's ref2015 scoring function as a baseline we use this protocol to develop 3pHLA-score. Our per-peptide-position protocol outperforms the standard training protocol and leads to an increase from 0.82 to 0.99 of the area under the precision-recall curve. 3pHLA-score outperforms widely used scoring functions (AutoDock4, Vina, Dope, Vinardo, FoldX, GradDock) in a structural virtual screening task. Overall, this work brings structure-based methods one step closer to epitope discovery pipelines and could help advance the development of cancer and viral vaccines.

Physicochemical Heuristics for Identifying High Fidelity, Near-Native Structural Models of Peptide/MHC Complexes

There is long-standing interest in accurately modeling the structural features of peptides bound and presented by class I MHC proteins. This interest has grown with the advent of rapid genome sequencing and the prospect of personalized, peptide-based cancer vaccines, as well as the development of molecular and cellular therapeutics based on T cell receptor recognition of peptide-MHC. However, while the speed and accessibility of peptide-MHC modeling has improved substantially over the years, improvements in accuracy have been modest. Accuracy is crucial in peptide-MHC modeling, as T cell receptors are highly sensitive to peptide conformation and capturing fine details is therefore necessary for useful models. Studying nonameric peptides presented by the common class I MHC protein HLA-A*02:01, here we addressed a key question common to modern modeling efforts: from a set of models (or decoys) generated through conformational sampling, which is best? We found that the common strategy of decoy selection by lowest energy can lead to substantial errors in predicted structures. We therefore adopted a data-driven approach and trained functions capable of predicting near native decoys with exceptionally high accuracy. Although our implementation is limited to nonamer/HLA-A*02:01 complexes, our results serve as an important proof of concept from which improvements can be made and, given the significance of HLA-A*02:01 and its preference for nonameric peptides, should have immediate utility in select immunotherapeutic and other efforts for which structural information would be advantageous.

PANDORA: A Fast, Anchor-Restrained Modelling Protocol for Peptide: MHC Complexes

Deeper understanding of T-cell-mediated adaptive immune responses is important for the design of cancer immunotherapies and antiviral vaccines against pandemic outbreaks. T-cells are activated when they recognize foreign peptides that are presented on the cell surface by Major Histocompatibility Complexes (MHC), forming peptide:MHC (pMHC) complexes. 3D structures of pMHC complexes provide fundamental insight into T-cell recognition mechanism and aids immunotherapy design. High MHC and peptide diversities necessitate efficient computational modelling to enable whole proteome structural analysis. We developed PANDORA, a generic modelling pipeline for pMHC class I and II (pMHC-I and pMHC-II), and present its performance on pMHC-I here. Given a query, PANDORA searches for structural templates in its extensive database and then applies anchor restraints to the modelling process. This restrained energy minimization ensures one of the fastest pMHC modelling pipelines so far. On a set of 835 pMHC-I complexes over 78 MHC types, PANDORA generated models with a median RMSD of 0.70 Å and achieved a 93% success rate in top 10 models. PANDORA performs competitively with three pMHC-I modelling state-of-the-art approaches and outperforms AlphaFold2 in terms of accuracy while being superior to it in speed. PANDORA is a modularized and user-configurable python package with easy installation. We envision PANDORA to fuel deep learning algorithms with large-scale high-quality 3D models to tackle long-standing immunology challenges.

Large-Scale Structure-Based Screening of Potential T Cell Cross-Reactivities Involving Peptide-Targets From BCG Vaccine and SARS-CoV-2

Although not being the first viral pandemic to affect humankind, we are now for the first time faced with a pandemic caused by a coronavirus. The Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) has been responsible for the COVID-19 pandemic, which caused more than 4.5 million deaths worldwide. Despite unprecedented efforts, with vaccines being developed in a record time, SARS-CoV-2 continues to spread worldwide with new variants arising in different countries. Such persistent spread is in part enabled by public resistance to vaccination in some countries, and limited access to vaccines in other countries. The limited vaccination coverage, the continued risk for resistant variants, and the existence of natural reservoirs for coronaviruses, highlight the importance of developing additional therapeutic strategies against SARS-CoV-2 and other coronaviruses. At the beginning of the pandemic it was suggested that countries with Bacillus Calmette-Guérin (BCG) vaccination programs could be associated with a reduced number and/or severity of COVID-19 cases. Preliminary studies have provided evidence for this relationship and further investigation is being conducted in ongoing clinical trials. The protection against SARS-CoV-2 induced by BCG vaccination may be mediated by cross-reactive T cell lymphocytes, which recognize peptides displayed by class I Human Leukocyte Antigens (HLA-I) on the surface of infected cells. In order to identify potential targets of T cell cross-reactivity, we implemented an in silico strategy combining sequence-based and structure-based methods to screen over 13,5 million possible cross-reactive peptide pairs from BCG and SARS-CoV-2. Our study produced (i) a list of immunogenic BCG-derived peptides that may prime T cell cross-reactivity against SARS-CoV-2, (ii) a large dataset of modeled peptide-HLA structures for the screened targets, and (iii) new computational methods for structure-based screenings that can be used by others in future studies. Our study expands the list of BCG peptides potentially involved in T cell cross-reactivity with SARS-CoV-2-derived peptides, and identifies multiple high-density "neighborhoods" of cross-reactive peptides which could be driving heterologous immunity induced by BCG vaccination, therefore providing insights for future vaccine development efforts.

Structural Prediction of Peptide-MHC Binding Modes

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

Dynamics-Based Peptide-MHC Binding Optimization by a Convolutional Variational Autoencoder: A Use-Case Model for CASTELO

An unsolved challenge in the development of antigen-specific immunotherapies is determining the optimal antigens to target. Comprehension of antigen-major histocompatibility complex (MHC) binding is paramount toward achieving this goal. Here, we apply CASTELO, a combined machine learning-molecular dynamics (ML-MD) approach, to identify per-residue antigen binding contributions and then design novel antigens of increased MHC-II binding affinity for a type 1 diabetes-implicated system. We build upon a small-molecule lead optimization algorithm by training a convolutional variational autoencoder (CVAE) on MD trajectories of 48 different systems across four antigens and four HLA serotypes. We develop several new machine learning metrics including a structure-based anchor residue classification model as well as cluster comparison scores. ML-MD predictions agree well with experimental binding results and free energy perturbation-predicted binding affinities. Moreover, ML-MD metrics are independent of traditional MD stability metrics such as contact area and root-mean-square fluctuations (RMSF), which do not reflect binding affinity data. Our work supports the role of structure-based deep learning techniques in antigen-specific immunotherapy design.

Toward Guided Mutagenesis: Gaussian Process Regression Predicts MHC Class II Antigen Mutant Binding

Antigen-specific immunotherapies (ASI) require successful loading and presentation of antigen peptides into the major histocompatibility complex (MHC) binding cleft. One route of ASI design is to mutate native antigens for either stronger or weaker binding interaction to MHC. Exploring all possible mutations is costly both experimentally and computationally. To reduce experimental and computational expense, here we investigate the minimal amount of prior data required to accurately predict the relative binding affinity of point mutations for peptide-MHC class II (pMHCII) binding. Using data from different residue subsets, we interpolate pMHCII mutant binding affinities by Gaussian process (GP) regression of residue volume and hydrophobicity. We apply GP regression to an experimental data set from the Immune Epitope Database, and theoretical data sets from NetMHCIIpan and Free Energy Perturbation calculations. We find that GP regression can predict binding affinities of nine neutral residues from a six-residue subset with an average R² coefficient of determination value of 0.62 ± 0.04 (±95% CI), average error of 0.09 ± 0.01 kcal/mol (±95% CI), and with an receiver operating characteristic (ROC) AUC value of 0.92 for binary classification of enhanced or diminished binding affinity. Similarly, metrics increase to an R² value of 0.69 ± 0.04, average error of 0.07 ± 0.01 kcal/mol, and an ROC AUC value of 0.94 for predicting seven neutral residues from an eight-residue subset. Our work finds that prediction is most accurate for neutral residues at anchor residue sites without register shift. This work holds relevance to predicting pMHCII binding and accelerating ASI design.

Rapid Assessment of T-Cell Receptor Specificity of the Immune Repertoire

Accurate assessment of TCR-antigen specificity at the whole immune repertoire level lies at the heart of improved cancer immunotherapy, but predictive models capable of high-throughput assessment of TCR-peptide pairs are lacking. Recent advances in deep sequencing and crystallography have enriched the data available for studying TCR-p-MHC systems. Here, we introduce a pairwise energy model, RACER, for rapid assessment of TCR-peptide affinity at the immune repertoire level. RACER applies supervised machine learning to efficiently and accurately resolve strong TCR-peptide binding pairs from weak ones. The trained parameters further enable a physical interpretation of interacting patterns encoded in each specific TCR-p-MHC system. When applied to simulate thymic selection of an MHC-restricted T-cell repertoire, RACER accurately estimates recognition rates for tumor-associated neoantigens and foreign peptides, thus demonstrating its utility in helping address the large computational challenge of reliably identifying the properties of tumor antigen-specific T-cells at the level of an individual patient's immune repertoire.

Glycoproteogenomics: Setting the Course for Next-generation Cancer Neoantigen Discovery for Cancer Vaccines

Molecular-assisted precision oncology gained tremendous ground with high-throughput next-generation sequencing (NGS), supported by robust bioinformatics. The quest for genomics-based cancer medicine set the foundations for improved patient stratification, while unveiling a wide array of neoantigens for immunotherapy. Upfront pre-clinical and clinical studies have successfully used tumor-specific peptides in vaccines with minimal off-target effects. However, the low mutational burden presented by many lesions challenges the generalization of these solutions, requiring the diversification of neoantigen sources. Oncoproteogenomics utilizing customized databases for protein annotation by mass spectrometry (MS) is a powerful tool toward this end. Expanding the concept toward exploring proteoforms originated from post-translational modifications (PTMs) will be decisive to improve molecular subtyping and provide potentially targetable functional nodes with increased cancer specificity. Walking through the path of systems biology, we highlight that alterations in protein glycosylation at the cell surface not only have functional impact on cancer progression and dissemination but also originate unique molecular fingerprints for targeted therapeutics. Moreover, we discuss the outstanding challenges required to accommodate glycoproteomics in oncoproteogenomics platforms. We envisage that such rationale may flag a rather neglected research field, generating novel paradigms for precision oncology and immunotherapy.

Markov state modeling reveals alternative unbinding pathways for peptide-MHC complexes

Peptide binding to major histocompatibility complexes (MHCs) is a central component of the immune system, and understanding the mechanism behind stable peptide-MHC binding will aid the development of immunotherapies. While MHC binding is mostly influenced by the identity of the so-called anchor positions of the peptide, secondary interactions from nonanchor positions are known to play a role in complex stability. However, current MHC-binding prediction methods lack an analysis of the major conformational states and might underestimate the impact of secondary interactions. In this work, we present an atomically detailed analysis of peptide-MHC binding that can reveal the contributions of any interaction toward stability. We propose a simulation framework that uses both umbrella sampling and adaptive sampling to generate a Markov state model (MSM) for a coronavirus-derived peptide (QFKDNVILL), bound to one of the most prevalent MHC receptors in humans (HLA-A24:02). While our model reaffirms the importance of the anchor positions of the peptide in establishing stable interactions, our model also reveals the underestimated importance of position 4 (p4), a nonanchor position. We confirmed our results by simulating the impact of specific peptide mutations and validated these predictions through competitive binding assays. By comparing the MSM of the wild-type system with those of the D4A and D4P mutations, our modeling reveals stark differences in unbinding pathways. The analysis presented here can be applied to any peptide-MHC complex of interest with a structural model as input, representing an important step toward comprehensive modeling of the MHC class I pathway.

Structural Modeling and Molecular Dynamics of the Immune Checkpoint Molecule HLA-G

HLA-G is considered to be an immune checkpoint molecule, a function that is closely linked to the structure and dynamics of the different HLA-G isoforms. Unfortunately, little is known about the structure and dynamics of these isoforms. For instance, there are only seven crystal structures of HLA-G molecules, being all related to a single isoform, and in some cases lacking important residues associated to the interaction with leukocyte receptors. In addition, they lack information on the dynamics of both membrane-bound HLA-G forms, and soluble forms. We took advantage of in silico strategies to disclose the dynamic behavior of selected HLA-G forms, including the membrane-bound HLA-G1 molecule, soluble HLA-G1 dimer, and HLA-G5 isoform. Both the membrane-bound HLA-G1 molecule and the soluble HLA-G1 dimer were quite stable. Residues involved in the interaction with ILT2 and ILT4 receptors (α3 domain) were very close to the lipid bilayer in the complete HLA-G1 molecule, which might limit accessibility. On the other hand, these residues can be completely exposed in the soluble HLA-G1 dimer, due to the free rotation of the disulfide bridge (Cys42/Cys42). In fact, we speculate that this free rotation of each protomer (i.e., the chains composing the dimer) could enable alternative binding modes for ILT2/ILT4 receptors, which in turn could be associated with greater affinity of the soluble HLA-G1 dimer. Structural analysis of the HLA-G5 isoform demonstrated higher stability for the complex containing the peptide and coupled β2-microglobulin, while structures lacking such domains were significantly unstable. This study reports for the first time structural conformations for the HLA-G5 isoform and the dynamic behavior of HLA-G1 molecules under simulated biological conditions. All modeled structures were made available through GitHub (https://github.com/KavrakiLab/), enabling their use as templates for modeling other alleles and isoforms, as well as for other computational analyses to investigate key molecular interactions.

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.

HLA-Arena: A Customizable Environment for the Structural Modeling and Analysis of Peptide-HLA Complexes for Cancer Immunotherapy

PURPOSE

HLA protein receptors play a key role in cellular immunity. They bind intracellular peptides and display them for recognition by T-cell lymphocytes. Because T-cell activation is partially driven by structural features of these peptide-HLA complexes, their structural modeling and analysis are becoming central components of cancer immunotherapy projects. Unfortunately, this kind of analysis is limited by the small number of experimentally determined structures of peptide-HLA complexes. Overcoming this limitation requires developing novel computational methods to model and analyze peptide-HLA structures.

METHODS

Here we describe a new platform for the structural modeling and analysis of peptide-HLA complexes, called HLA-Arena, which we have implemented using Jupyter Notebook and Docker. It is a customizable environment that facilitates the use of computational tools, such as APE-Gen and DINC, which we have previously applied to peptide-HLA complexes. By integrating other commonly used tools, such as MODELLER and MHCflurry, this environment includes support for diverse tasks in structural modeling, analysis, and visualization.

RESULTS

To illustrate the capabilities of HLA-Arena, we describe 3 example workflows applied to peptide-HLA complexes. Leveraging the strengths of our tools, DINC and APE-Gen, the first 2 workflows show how to perform geometry prediction for peptide-HLA complexes and structure-based binding prediction, respectively. The third workflow presents an example of large-scale virtual screening of peptides for multiple HLA alleles.

CONCLUSION

These workflows illustrate the potential benefits of HLA-Arena for the structural modeling and analysis of peptide-HLA complexes. Because HLA-Arena can easily be integrated within larger computational pipelines, we expect its potential impact to vastly increase. For instance, it could be used to conduct structural analyses for personalized cancer immunotherapy, neoantigen discovery, or vaccine development.

Uncovering the Tumor Antigen Landscape: What to Know about the Discovery Process

According to the latest available data, cancer is the second leading cause of death, highlighting the need for novel cancer therapeutic approaches. In this context, immunotherapy is emerging as a reliable first-line treatment for many cancers, particularly metastatic melanoma. Indeed, cancer immunotherapy has attracted great interest following the recent clinical approval of antibodies targeting immune checkpoint molecules, such as PD-1, PD-L1, and CTLA-4, that release the brakes of the immune system, thus reviving a field otherwise poorly explored. Cancer immunotherapy mainly relies on the generation and stimulation of cytotoxic CD8 T lymphocytes (CTLs) within the tumor microenvironment (TME), priming T cells and establishing efficient and durable anti-tumor immunity. Therefore, there is a clear need to define and identify immunogenic T cell epitopes to use in therapeutic cancer vaccines. Naturally presented antigens in the human leucocyte antigen-1 (HLA-I) complex on the tumor surface are the main protagonists in evocating a specific anti-tumor CD8+ T cell response. However, the methodologies for their identification have been a major bottleneck for their reliable characterization. Consequently, the field of antigen discovery has yet to improve. The current review is intended to define what are today known as tumor antigens, with a main focus on CTL antigenic peptides. We also review the techniques developed and employed to date for antigen discovery, exploring both the direct elution of HLA-I peptides and the in silico prediction of epitopes. Finally, the last part of the review analyses the future challenges and direction of the antigen discovery field.