Transfer learning improves pMHC kinetic stability and immunogenicity predictions.

The cellular immune response comprises several processes, with the most notable ones being the binding of the peptide to the Major Histocompability Complex (MHC), the peptide-MHC (pMHC) presentation to the surface of the cell, and the recognition of the pMHC by the T-Cell Receptor. Identifying the most potent peptide targets for MHC binding, presentation and T-cell recognition is vital for developing peptide-based vaccines and T-cell-based immunotherapies. Data-driven tools that predict each of these steps have been developed, and the availability of mass spectrometry (MS) datasets has facilitated the development of accurate Machine Learning (ML) methods for class-I pMHC binding prediction. However, the accuracy of ML-based tools for pMHC kinetic stability prediction and peptide immunogenicity prediction is uncertain, as stability and immunogenicity datasets are not abundant. Here, we use transfer learning techniques to improve stability and immunogenicity predictions, by taking advantage of a large number of binding affinity and MS datasets. The resulting models, TLStab and TLImm, exhibit comparable or better performance than state-of-the-art approaches on different stability and immunogenicity test sets respectively. Our approach demonstrates the promise of learning from the task of peptide binding to improve predictions on downstream tasks. The source code of TLStab and TLImm is publicly available at https://github.com/KavrakiLab/TL-MHC.

Comprehensive characterization of IFNγ signaling in acute myeloid leukemia reveals prognostic and therapeutic strategies.

Interferon gamma (IFNγ) is a critical cytokine known for its diverse roles in immune regulation, inflammation, and tumor surveillance. However, while IFNγ levels were elevated in sera of most newly diagnosed acute myeloid leukemia (AML) patients, its complex interplay in AML remains insufficiently understood. We aim to characterize these complex interactions through comprehensive bulk and single-cell approaches in bone marrow of newly diagnosed AML patients. We identify monocytic AML as having a unique microenvironment characterized by IFNγ producing T and NK cells, high IFNγ signaling, and immunosuppressive features. IFNγ signaling score strongly correlates with venetoclax resistance in primary AML patient cells. Additionally, IFNγ treatment of primary AML patient cells increased venetoclax resistance. Lastly, a parsimonious 47-gene IFNγ score demonstrates robust prognostic value. In summary, our findings suggest that inhibiting IFNγ is a potential treatment strategy to overcoming venetoclax resistance and immune evasion in AML patients.

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.

EnGens: a computational framework for generation and analysis of representative protein conformational ensembles.

Proteins are dynamic macromolecules that perform vital functions in cells. A protein structure determines its function, but this structure is not static, as proteins change their conformation to achieve various functions. Understanding the conformational landscapes of proteins is essential to understand their mechanism of action. Sets of carefully chosen conformations can summarize such complex landscapes and provide better insights into protein function than single conformations. We refer to these sets as representative conformational ensembles. Recent advances in computational methods have led to an increase in the number of available structural datasets spanning conformational landscapes. However, extracting representative conformational ensembles from such datasets is not an easy task and many methods have been developed to tackle it. Our new approach, EnGens (short for ensemble generation), collects these methods into a unified framework for generating and analyzing representative protein conformational ensembles. In this work, we: (1) provide an overview of existing methods and tools for representative protein structural ensemble generation and analysis; (2) unify existing approaches in an open-source Python package, and a portable Docker image, providing interactive visualizations within a Jupyter Notebook pipeline; (3) test our pipeline on a few canonical examples from the literature. Representative ensembles produced by EnGens can be used for many downstream tasks such as protein-ligand ensemble docking, Markov state modeling of protein dynamics and analysis of the effect of single-point mutations.

CrossDome: an interactive R package to predict cross-reactivity risk using immunopeptidomics databases.

T-cell-based immunotherapies hold tremendous potential in the fight against cancer, thanks to their capacity to specifically targeting diseased cells. Nevertheless, this potential has been tempered with safety concerns regarding the possible recognition of unknown off-targets displayed by healthy cells. In a notorious example, engineered T-cells specific to MAGEA3 (EVDPIGHLY) also recognized a TITIN-derived peptide (ESDPIVAQY) expressed by cardiac cells, inducing lethal damage in melanoma patients. Such off-target toxicity has been related to T-cell cross-reactivity induced by molecular mimicry. In this context, there is growing interest in developing the means to avoid off-target toxicity, and to provide safer immunotherapy products. To this end, we present CrossDome, a multi-omics suite to predict the off-target toxicity risk of T-cell-based immunotherapies. Our suite provides two alternative protocols, i) a peptide-centered prediction, or ii) a TCR-centered prediction. As proof-of-principle, we evaluate our approach using 16 well-known cross-reactivity cases involving cancer-associated antigens. With CrossDome, the TITIN-derived peptide was predicted at the 99+ percentile rank among 36,000 scored candidates (p-value < 0.001). In addition, off-targets for all the 16 known cases were predicted within the top ranges of relatedness score on a Monte Carlo simulation with over 5 million putative peptide pairs, allowing us to determine a cut-off p-value for off-target toxicity risk. We also implemented a penalty system based on TCR hotspots, named contact map (CM). This TCR-centered approach improved upon the peptide-centered prediction on the MAGEA3-TITIN screening (e.g., from 27th to 6th, out of 36,000 ranked peptides). Next, we used an extended dataset of experimentally-determined cross-reactive peptides to evaluate alternative CrossDome protocols. The level of enrichment of validated cases among top 50 best-scored peptides was 63% for the peptide-centered protocol, and up to 82% for the TCR-centered protocol. Finally, we performed functional characterization of top ranking candidates, by integrating expression data, HLA binding, and immunogenicity predictions. CrossDome was designed as an R package for easy integration with antigen discovery pipelines, and an interactive web interface for users without coding experience. CrossDome is under active development, and it is available at https://github.com/AntunesLab/crossdome.

Single-Cell Profiling of CD8+ T Cells in Acute Myeloid Leukemia Reveals a Continuous Spectrum of Differentiation and Clonal Hyperexpansion.

Comprehensive investigation of CD8+ T cells in acute myeloid leukemia (AML) is essential for developing immunotherapeutic strategies beyond immune checkpoint blockade. Herein, we performed single-cell RNA profiling of CD8+ T cells from 3 healthy bone marrow donors and 23 newly diagnosed (NewlyDx) and 8 relapsed/refractory (RelRef) patients with AML. Cells coexpressing canonical exhaustion markers formed a cluster constituting <1% of all CD8+ T cells. We identified two effector CD8+ T-cell subsets characterized by distinct cytokine and metabolic profiles that were differentially enriched in NewlyDx and RelRef patients. We refined a 25-gene CD8-derived signature correlating with therapy resistance, including genes associated with activation, chemoresistance, and terminal differentiation. Pseudotemporal trajectory analysis supported enrichment of a terminally differentiated state in CD8+ T cells with high CD8-derived signature expression at relapse or refractory disease. Higher expression of the 25-gene CD8 AML signature correlated with poorer outcomes in previously untreated patients with AML, suggesting that the bona fide state of CD8+ T cells and their degree of differentiation are clinically relevant. Immune clonotype tracking revealed more phenotypic transitions in CD8 clonotypes in NewlyDx than in RelRef patients. Furthermore, CD8+ T cells from RelRef patients had a higher degree of clonal hyperexpansion associated with terminal differentiation and higher CD8-derived signature expression. Clonotype-derived antigen prediction revealed that most previously unreported clonotypes were patient-specific, suggesting significant heterogeneity in AML immunogenicity. Thus, immunologic reconstitution in AML is likely to be most successful at earlier disease stages when CD8+ T cells are less differentiated and have greater capacity for clonotype transitions.

Individual Epitope-Specific CD8+ T Cell Immune Responses Are Shaped Differently during Chronic Viral Infection.

A hallmark in chronic viral infections are exhausted antigen-specific CD8+ T cell responses and the inability of the immune system to eliminate the virus. Currently, there is limited information on the variability of epitope-specific T cell exhaustion within one immune response and the relevance to the T cell receptor (TCR) repertoire. The aim of this study was a comprehensive analysis and comparison of three lymphocytic choriomeningitis virus (LCMV) epitope-specific CD8+ T cell responses (NP396, GP33 and NP205) in a chronic setting with immune intervention, e.g., immune checkpoint inhibitor (ICI) therapy, in regard to the TCR repertoire. These responses, though measured within the same mice, were individual and independent from each other. The massively exhausted NP396-specific CD8+ T cells revealed a significantly reduced TCR repertoire diversity, whereas less-exhausted GP33-specific CD8+ T cell responses were rather unaffected by chronicity in regard to their TCR repertoire diversity. NP205-specific CD8+ T cell responses showed a very special TCR repertoire with a prominent public motif of TCR clonotypes that was present in all NP205-specific responses, which separated this from NP396- and GP33-specific responses. Additionally, we showed that TCR repertoire shifts induced by ICI therapy are heterogeneous on the epitope level, by revealing profound effects in NP396-, less severe and opposed effects in NP205-, and minor effects in GP33-specific responses. Overall, our data revealed individual epitope-specific responses within one viral response that are differently affected by exhaustion and ICI therapy. These individual shapings of epitope-specific T cell responses and their TCR repertoires in an LCMV mouse model indicates important implications for focusing on epitope-specific responses in future evaluations for therapeutic approaches, e.g., for chronic hepatitis virus infections in humans.

EnGens: a computational framework for generation and analysis of representative protein conformational ensembles.

Proteins are dynamic macromolecules that perform vital functions in cells. A protein structure determines its function, but this structure is not static, as proteins change their conformation to achieve various functions. Understanding the conformational landscapes of proteins is essential to understand their mechanism of action. Sets of carefully chosen conformations can summarize such complex landscapes and provide better insights into protein function than single conformations. We refer to these sets as representative conformational ensembles. Recent advances in computational methods have led to an increase in number of available structural datasets spanning conformational landscapes. However, extracting representative conformational ensembles from such datasets is not an easy task and many methods have been developed to tackle it. Our new approach, EnGens (short for ensemble generation), collects these methods into a unified framework for generating and analyzing protein conformational ensembles. In this work we: (1) provide an overview of existing methods and tools for protein structural ensemble generation and analysis; (2) unify existing approaches in an open-source Python package, and a portable Docker image, providing interactive visualizations within a Jupyter Notebook pipeline; (3) test our pipeline on a few canonical examples found in the literature. Representative ensembles produced by EnGens can be used for many downstream tasks such as protein-ligand ensemble docking, Markov state modeling of protein dynamics and analysis of the effect of single-point mutations.

Single-Cell Profiling of CD8+ T Cells in Acute Myeloid Leukemia Reveals a Continuous Spectrum of Differentiation and Clonal Hyperexpansion.

Comprehensive investigation of CD8+ T cells in acute myeloid leukemia (AML) is essential for developing immunotherapeutic strategies beyond immune checkpoint blockade. Herein, we performed single-cell RNA profiling of CD8+ T cells from 3 healthy bone marrow donors and 23 newly diagnosed (NewlyDx) and 8 relapsed/refractory (RelRef) AML patients. Cells co-expressing canonical exhaustion markers formed a cluster constituting <1% of all CD8+ T cells. We identified two effector CD8+ T cell subsets characterized by distinct cytokine and metabolic profiles that were differentially enriched in NewlyDx and RelRef patients. We refined a 25-gene CD8-derived signature correlating with therapy resistance, including genes associated with activation, chemoresistance, and terminal differentiation. Pseudotemporal trajectory analysis supported enrichment of a terminally differentiated state in CD8+ T cells with high CD8-derived signature expression at relapse or refractory disease. Higher expression of the 25-gene CD8 AML signature correlated with poorer outcomes in previously untreated AML patients, suggesting that the bona fide state of CD8+ T cells and their degree of differentiation are clinically relevant. Immune clonotype tracking revealed more phenotypic transitions in CD8 clonotypes in NewlyDx than in RelRef patients. Furthermore, CD8+ T cells from RelRef patients had a higher degree of clonal hyperexpansion associated with terminal differentiation and higher CD8-derived signature expression. Clonotype-derived antigen prediction revealed that most previously unreported clonotypes were patient-specific, suggesting significant heterogeneity in AML immunogenicity. Thus, immunologic reconstitution in AML is likely to be most successful at earlier disease stages when CD8+ T cells are less differentiated and have greater capacity for clonotype transitions.

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.

Vestigial-like 1 (VGLL1): An ancient co-transcriptional activator linking wing, placenta, and tumor development.

Vestigial-like 1 (VGLL1) is a recently discovered driver of proliferation and invasion that is expressed in many aggressive human malignancies and is strongly associated with poor prognosis. The VGLL1 gene encodes for a co-transcriptional activator that shows intriguing structural similarity to key activators in the hippo pathway, providing important clues to its functional role. VGLL1 binds to TEAD transcription factors in an analogous fashion to YAP1 but appears to activate a distinct set of downstream gene targets. In mammals, VGLL1 expression is found almost exclusively in placental trophoblasts, cells that share many hallmarks of cancer. Due to its role as a driver of tumor progression, VGLL1 has become a target of interest for potential anticancer therapies. In this review, we discuss VGLL1 from an evolutionary perspective, contrast its role in placental and tumor development, summarize the current knowledge of how signaling pathways can modulate VGLL1 function, and discuss potential approaches for targeting VGLL1 therapeutically.

Immunologic Predictors for Clinical Responses during Immune Checkpoint Blockade in Patients with Myelodysplastic Syndromes.

PURPOSE: The aim of this study is to determine immune-related biomarkers to predict effective antitumor immunity in myelodysplastic syndrome (MDS) during immunotherapy (IMT, αCTLA-4, and/or αPD-1 antibodies) and/or hypomethylating agent (HMA). EXPERIMENTAL DESIGN: Peripheral blood samples from 55 patients with MDS were assessed for immune subsets, T-cell receptor (TCR) repertoire, mutations in 295 acute myeloid leukemia (AML)/MDS-related genes, and immune-related gene expression profiling before and after the first treatment. RESULTS: Clinical responders treated with IMT ± HMA but not HMA alone showed a significant expansion of central memory (CM) CD8+ T cells, diverse TCRß repertoire pretreatment with increased clonality and emergence of novel clones after the initial treatment, and a higher mutation burden pretreatment with subsequent reduction posttreatment. Autophagy, TGFß, and Th1 differentiation pathways were the most downregulated in nonresponders after treatment, while upregulated in responders. Finally, CTLA-4 but not PD-1 blockade attributed to favorable changes in immune landscape. CONCLUSIONS: Analysis of tumor-immune landscape in MDS during immunotherapy provides clinical response biomarkers.

Computational and atomistic studies applied to the understanding of the structural and behavioral features of the immune checkpoint HLA-G molecule and gene.

We took advantage of the increasingly evolving approaches for in silico studies concerning protein structures, protein molecular dynamics (MD), protein-protein and protein-DNA docking to evaluate: (i) the structure and MD characteristics of the HLA-G well-recognized isoforms, (ii) the impact of missense mutations at HLA-G receptor genes (LILRB1/2), and (iii) the differential binding of the hypoxia-inducible factor 1 (HIF1) to hypoxia-responsive elements (HRE) at the HLA-G gene. Besides reviewing these topics, they were revisited including the following novel results: (i) the HLA-G6 isoforms were unstable docked or not with ß2-microglobulin or peptide, (ii) missense mutations at LILRB1/2 genes, exchanging amino acids at the intracellular domain, particularly those located within and around the ITIM motifs, may impact the HLA-G binding strength, and (iii) HREs motifs at the HLA-G promoter or exon 2 regions exhibiting a guanine at their third position present a higher affinity for HIF1 when compared to an adenine at the same position. These data shed some light into the functional aspects of HLA-G, particularly how polymorphisms may influence the role of the molecule. Computational and atomistic studies have provided alternative tools for experimental physical methodologies, which are time-consuming, expensive, demanding large quantities of purified proteins, and exhibit low output.

Charge-based interactions through peptide position 4 drive diversity of antigen presentation by human leukocyte antigen class I molecules.

Human leukocyte antigen class I (HLA-I) molecules bind and present peptides at the cell surface to facilitate the induction of appropriate CD8+ T cell-mediated immune responses to pathogen- and self-derived proteins. The HLA-I peptide-binding cleft contains dominant anchor sites in the B and F pockets that interact primarily with amino acids at peptide position 2 and the C-terminus, respectively. Nonpocket peptide-HLA interactions also contribute to peptide binding and stability, but these secondary interactions are thought to be unique to individual HLA allotypes or to specific peptide antigens. Here, we show that two positively charged residues located near the top of peptide-binding cleft facilitate interactions with negatively charged residues at position 4 of presented peptides, which occur at elevated frequencies across most HLA-I allotypes. Loss of these interactions was shown to impair HLA-I/peptide binding and complex stability, as demonstrated by both in vitro and in silico experiments. Furthermore, mutation of these Arginine-65 (R65) and/or Lysine-66 (K66) residues in HLA-A*02:01 and A*24:02 significantly reduced HLA-I cell surface expression while also reducing the diversity of the presented peptide repertoire by up to 5-fold. The impact of the R65 mutation demonstrates that nonpocket HLA-I/peptide interactions can constitute anchor motifs that exert an unexpectedly broad influence on HLA-I-mediated antigen presentation. These findings provide fundamental insights into peptide antigen binding that could broadly inform epitope discovery in the context of viral vaccine development and cancer immunotherapy.

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.

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.

Current progress and open challenges for applying deep learning across the biosciences.

Deep Learning (DL) has recently enabled unprecedented advances in one of the grand challenges in computational biology: the half-century-old problem of protein structure prediction. In this paper we discuss recent advances, limitations, and future perspectives of DL on five broad areas: protein structure prediction, protein function prediction, genome engineering, systems biology and data integration, and phylogenetic inference. We discuss each application area and cover the main bottlenecks of DL approaches, such as training data, problem scope, and the ability to leverage existing DL architectures in new contexts. To conclude, we provide a summary of the subject-specific and general challenges for DL across the biosciences.