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.

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.

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.

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.

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.

Hepatitis E Virus (HEV)-Specific T Cell Receptor Cross-Recognition: Implications for Immunotherapy.

T cell immunotherapy is a concept developed for the treatment of cancer and infectious diseases, based on cytotoxic T lymphocytes to target tumor- or pathogen-specific antigens. Antigen-specificity of the T cell receptors (TCRs) is an important selection criterion in the developmental design of immunotherapy. However, off-target specificity is a possible autoimmunity concern if the engineered antigen-specific T cells are cross-reacting to self-peptides in-vivo. In our recent work, we identified several hepatitis E virus (HEV)-specific TCRs as potential candidates to be developed into T cell therapy to treat chronic hepatitis E. One of the identified TCRs, targeting a HLA-A2-restricted epitope at the RNA-dependent RNA polymerase (HEV-1527: LLWNTVWNM), possessed a unique multiple glycine motif in the TCR-ß CDR3, which might be a factor inducing cross-reactivity. The aim of our study was to explore if this TCR could cross-recognize self-peptides to underlay autoimmunity. Indeed, we found that this HEV-1527-specific TCR could also cross-recognize an apoptosis-related epitope, Nonmuscle Myosin Heavy Chain 9 (MYH9-478: QLFNHTMFI). While this TCR had dual specificities to both viral epitope and a self-antigen by double Dextramer binding, it was selectively functional against HEV-1527 but not activated against MYH9-478. The consecutive glycine motif in ß chain may be the reason promoting TCR binding promiscuity to recognize a secondary target, thereby facilitating cross-recognition. In conclusion, candidate TCRs for immunotherapy development should be screened for autoimmune potential, especially when the TCRs exhibit unique sequence pattern.

DockTope: a Web-based tool for automated pMHC-I modelling.

The immune system is constantly challenged, being required to protect the organism against a wide variety of infectious pathogens and, at the same time, to avoid autoimmune disorders. One of the most important molecules involved in these events is the Major Histocompatibility Complex class I (MHC-I), responsible for binding and presenting small peptides from the intracellular environment to CD8(+) T cells. The study of peptide:MHC-I (pMHC-I) molecules at a structural level is crucial to understand the molecular mechanisms underlying immunologic responses. Unfortunately, there are few pMHC-I structures in the Protein Data Bank (PDB) (especially considering the total number of complexes that could be formed combining different peptides), and pMHC-I modelling tools are scarce. Here, we present DockTope, a free and reliable web-based tool for pMHC-I modelling, based on crystal structures from the PDB. DockTope is fully automated and allows any researcher to construct a pMHC-I complex in an efficient way. We have reproduced a dataset of 135 non-redundant pMHC-I structures from the PDB (Cα RMSD below 1 Å). Modelling of pMHC-I complexes is remarkably important, contributing to the knowledge of important events such as cross-reactivity, autoimmunity, cancer therapy, transplantation and rational vaccine design.

CrossTope: a curate repository of 3D structures of immunogenic peptide: MHC complexes.

The CrossTope is a highly curate repository of three-dimensional structures of peptide:major histocompatibility complex (MHC) class I complexes (pMHC-I). The complexes hosted by this databank were obtained in protein databases and by large-scale in silico construction of pMHC-I structures, using a new approach developed by our group. At this moment, the database contains 182 'non-redundant' pMHC-I complexes from two human and two murine alleles. A web server provides interface for database query. The user can download (i) structure coordinate files and (ii) topological and charges distribution maps images from the T-cell receptor-interacting surface of pMHC-I complexes. The retrieved structures and maps can be used to cluster similar epitopes in cross-reactivity approaches, to analyse viral escape mutations in a structural level or even to improve the immunogenicity of tumour antigens. Database URL: http://www.crosstope.com.br.

Immunogenic epitopes of Hantaviruses' N protein are restricted to conserved regions.

The Bunyaviridae virus family is composed by five genera, of which the Hantavirus genus is one of the most important representatives. Occasionally, these viruses can be transmitted to humans, giving rise to severe diseases that present high mortality rates. We analyzed the amino acid sequences of the nucleocapsid (N) proteins of 34 different hantaviruses to investigate the potential mechanisms involved in immunogenicity against hantaviruses. Immunogenic epitopes described in the literature through experimental analyses for Sin Nombre (SNV), Puumala (PUUV), and Hantaan (HTNV) viruses' species were retrieved. We identified and characterized the regions believed to be responsible for the induction of immune response in hosts. We found that N protein epitopes described in the literature for PUUV, SNV and HTNV viruses are all located in highly conserved regions of the protein. The high conservation of these regions suggests that a cross-reactive immune response among different hantaviruses can be induced.