scholarly journals Artificial intelligence predicts the immunogenic landscape of SARS-CoV-2: toward universal blueprints for vaccine designs

2020 ◽  
Author(s):  
Brandon Malone ◽  
Boris Simovski ◽  
Clément Moliné ◽  
Jun Cheng ◽  
Marius Gheorghe ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Monte Carlo ◽  
T Cell ◽  
Monte Carlo Simulations ◽  
Human Population ◽  
T Cell Epitopes ◽  
Maximum Coverage ◽  
Hla Genotypes ◽  
Significant Homology ◽  
Global Population

Abstract This protocol predicts blueprints for vaccine design that contain a broad repertoire of T-cell epitopes optimized for the global population. The protocol first requires a screening of the SARS-CoV-2 proteome using immunogenicity predictors to generate comprehensive epitope maps. Then, these epitope maps are used as input to Monte Carlo simulations designed to identify statistically significant “epitope hotspot” regions in the virus that are most likely to be immunogenic. The epitope hotspots that share significant homology with proteins in the human proteome are removed to reduce the chance of inducing off-target autoimmune responses. Finally, a database of the actual HLA genotypes of citizens is used to develop a “digital twin” type simulation to model how effective different combinations of hotspots would work in a diverse human population. The approach identifies an optimal constellation of epitope hotspots that could provide maximum coverage in the human population.

scholarly journals Artificial intelligence predicts the immunogenic landscape of SARS-CoV-2 leading to universal blueprints for vaccine designs

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Brandon Malone ◽  
Boris Simovski ◽  
Clément Moliné ◽  
Jun Cheng ◽  
Marius Gheorghe ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Monte Carlo ◽  
Cell Surface ◽  
Antigen Presentation ◽  
Human Population ◽  
Host Immune System ◽  
T Cell Epitopes ◽  
Digital Twin ◽  
Novel Coronavirus ◽  
Global Population

AbstractThe global population is at present suffering from a pandemic of Coronavirus disease 2019 (COVID-19), caused by the novel coronavirus Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). The goal of this study was to use artificial intelligence (AI) to predict blueprints for designing universal vaccines against SARS-CoV-2, that contain a sufficiently broad repertoire of T-cell epitopes capable of providing coverage and protection across the global population. To help achieve these aims, we profiled the entire SARS-CoV-2 proteome across the most frequent 100 HLA-A, HLA-B and HLA-DR alleles in the human population, using host-infected cell surface antigen presentation and immunogenicity predictors from the NEC Immune Profiler suite of tools, and generated comprehensive epitope maps. We then used these epitope maps as input for a Monte Carlo simulation designed to identify statistically significant “epitope hotspot” regions in the virus that are most likely to be immunogenic across a broad spectrum of HLA types. We then removed epitope hotspots that shared significant homology with proteins in the human proteome to reduce the chance of inducing off-target autoimmune responses. We also analyzed the antigen presentation and immunogenic landscape of all the nonsynonymous mutations across 3,400 different sequences of the virus, to identify a trend whereby SARS-COV-2 mutations are predicted to have reduced potential to be presented by host-infected cells, and consequently detected by the host immune system. A sequence conservation analysis then removed epitope hotspots that occurred in less-conserved regions of the viral proteome. Finally, we used a database of the HLA haplotypes of approximately 22,000 individuals to develop a “digital twin” type simulation to model how effective different combinations of hotspots would work in a diverse human population; the approach identified an optimal constellation of epitope hotspots that could provide maximum coverage in the global population. By combining the antigen presentation to the infected-host cell surface and immunogenicity predictions of the NEC Immune Profiler with a robust Monte Carlo and digital twin simulation, we have profiled the entire SARS-CoV-2 proteome and identified a subset of epitope hotspots that could be harnessed in a vaccine formulation to provide a broad coverage across the global population.

scholarly journals Artificial intelligence predicts the immunogenic landscape of SARS-CoV-2: toward universal blueprints for vaccine designs

2020 ◽  
Author(s):  
Brandon Malone ◽  
Boris Simovski ◽  
Clément Moliné ◽  
Jun Cheng ◽  
Marius Gheorghe ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Monte Carlo ◽  
Cell Surface ◽  
Antigen Presentation ◽  
Human Population ◽  
Host Immune System ◽  
T Cell Epitopes ◽  
Digital Twin ◽  
Novel Coronavirus ◽  
Global Population

AbstractThe global population is at present suffering from a pandemic of Coronavirus disease 2019 (COVID-19), caused by the novel coronavirus Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). The goals of this study were to use artificial intelligence (AI) to predict blueprints for designing universal vaccines against SARS-CoV-2, that contain a sufficiently broad repertoire of T-cell epitopes capable of providing coverage and protection across the global population. To help achieve these aims, we profiled the entire SARS-CoV-2 proteome across the most frequent 100 HLA-A, HLA-B and HLA-DR alleles in the human population, using host-infected cell surface antigen presentation and immunogenicity predictors from the NEC Immune Profiler suite of tools, and generated comprehensive epitope maps. We then used these epitope maps as input for a Monte Carlo simulation designed to identify statistically significant “epitope hotspot” regions in the virus that are most likely to be immunogenic across a broad spectrum of HLA types. We then removed epitope hotspots that shared significant homology with proteins in the human proteome to reduce the chance of inducing off-target autoimmune responses. We also analyzed the antigen presentation and immunogenic landscape of all the nonsynonymous mutations across 3400 different sequences of the virus, to identify a trend whereby SARS-COV-2 mutations are predicted to have reduced potential to be presented by host-infected cells, and consequently detected by the host immune system. A sequence conservation analysis then removed epitope hotspots that occurred in less-conserved regions of the viral proteome. Finally, we used a database of the HLA genotypes of approximately 22 000 individuals to develop a “digital twin” type simulation to model how effective different combinations of hotspots would work in a diverse human population, and used the approach to identify an optimal constellation of epitopes hotspots that could provide maximum coverage in the global population. By combining the antigen presentation to the infected-host cell surface and immunogenicity predictions of the NEC Immune Profiler with a robust Monte Carlo and digital twin simulation, we have managed to profile the entire SARS-CoV-2 proteome and identify a subset of epitope hotspots that could be harnessed in a vaccine formulation to provide a broad coverage across the global population.

scholarly journals T-CoV: a comprehensive portal of HLA-peptide interactions affected by SARS-CoV-2 mutations

2021 ◽  
Author(s):  
Stepan Nersisyan ◽  
Anton Zhiyanov ◽  
Maxim Shkurnikov ◽  
Alexander Tonevitsky
Keyword(s):  
T Cell ◽  
Hla Class I ◽  
Binding Affinities ◽  
T Cell Epitopes ◽  
Hla Alleles ◽  
Cell Responses ◽  
Hla Genotypes ◽  
Peptide Interactions ◽  
The Uk ◽  
Hla Molecules

Rapidly appearing SARS-CoV-2 mutations can affect T cell epitopes, which can help the virus to evade either CD8 or CD4 T-cell responses. We developed T-cell COVID-19 Atlas (T-CoV, https://t-cov.hse.ru) - the comprehensive web portal, which allows one to analyze how SARS-CoV-2 mutations alter the presentation of viral peptides by HLA molecules. The data are presented for common virus variants and the most frequent HLA class I and class II alleles. Binding affinities of HLA molecules and viral peptides were assessed with accurate in silico methods. The obtained results highlight the importance of taking HLA alleles diversity into account: mutation-mediated alterations in HLA-peptide interactions were highly dependent on HLA alleles. For example, we found that the essential number of peptides tightly bound to HLA-B*07:02 in the reference Wuhan variant ceased to be tight binders for the Indian (Delta) and the UK (Alpha) variants. In summary, we believe that T-CoV will help researchers and clinicians to predict the susceptibility of individuals with different HLA genotypes to infection with variants of SARS-CoV-2 and/or forecast its severity.

scholarly journals MHC-restricted recognition of immunogenic T cell epitopes of pertussis toxin reveals determinants in man distinct from the ADP-ribosylase active site.

1988 ◽  
Vol 168 (5) ◽  
pp. 1855-1864 ◽  
Author(s):  
J R Oksenberg ◽  
A K Judd ◽  
C Ko ◽  
M Lim ◽  
R Fernandez ◽  
...  
Keyword(s):  
T Cell ◽  
Pertussis Vaccine ◽  
Pertussis Toxin ◽  
T Cell Epitopes ◽  
Cell Responses ◽  
Hla Dr ◽  
Hla Genotypes ◽  
Hla Dq ◽  
Wide Range ◽  
Critical Residues

The S1 subunit of Pertussis toxin (PT) is responsible for the reactogenicity and in part the immunogenicity of Bordetella pertussis vaccine. The critical residues associated with the immunomodulatory effects of PT were located around Glu140 in the S1 subunit. In man, T cell responses to PT are directed at S1 peptides distinct from Glu140. Two such epitopes, p64-75 and p151-161, are immunogenic in a panel of individuals covering a wide range of HLA genotypes. The response to PT peptides is HLA class II restricted. The response to p64-75 is blocked by an anti-HLA-DQ mAb, while that to p151-161 is blocked by an anti-HLA-DR mAb. These findings may allow for the development of a B. pertussis vaccine free from reactogenicity.

Immuno-Informatics Quest against COVID-19/SARS-COV-2: Determining Putative T-Cell Epitopes for Vaccine Prediction

2020 ◽  
Vol 20 ◽  
Author(s):  
Nahid Akhtar ◽  
Amit Joshi ◽  
Bhupender Singh ◽  
Vikas Kaushik
Keyword(s):  
Public Health ◽  
T Cell ◽  
Molecular Dynamic Simulation ◽  
Molecular Dynamic ◽  
Dynamic Simulation ◽  
T Cell Epitopes ◽  
Global Public Health ◽  
Population Coverage ◽  
Vaccine Candidates ◽  
Global Population

Background: Since, December 2019 a novel coronavirus, SARS-CoV-2 has caused global public health issue after being reported for the first time in Wuhan province of China. So far, there have been approximately 14.8 million confirmed cases and 0.614 million deaths due to the SARS-CoV-2 infection globally, and still numbers are increasing. Although, the virus has caused a global public health concern, no effective treatment has been developed. Objective: One of the strategies to combat the COVID-19 disease caused by SARS-CoV-2 is development of vaccines that can make humans immune to these infections. Considering this approach, in this study an attempt has been made to design epitope based vaccine for combatting COVID-19 disease by analyzing the complete proteome of the virus by using immuno-informatics tools. Methods: The protein sequence of the SARS-CoV-2 was retrieved and the individual proteins were checked for their allergic potential. Then, from non-allergen proteins antigenic epitopes were identified that could bind with MHCII molecules. The epitopes were modeled and docked to predict the interaction with MHCII molecules. The stability of the epitopeMHCII complex was further analyzed by performing molecular dynamic simulation study. The selected vaccine candidates were also analyzed for their global population coverage and conservancy among SARS related coronavirus species. Results: The study has predicted 5 peptide molecules that can act as potential candidate for epitope based vaccine development. Among the 5 selected epitopes, the peptide LRARSVSPK can be the most potent epitope because of its high geometric shape complementarity score, low ACE and very high response to it by the world population (81.81% global population coverage). Further, molecular dynamic simulation analysis indicated the formation of stable epitope-MHCII complex. The epitope LRARSVSPK was also found to be highly conserved among the SARS-CoV-2 isolated from different countries. Conclusion: The study has predicted T-cell epitopes that can elicit robust immune response in global human population and act as potential vaccine candidates. However, the ability of these epitopes to act as vaccine candidate needs to be validated in wet lab studies.

scholarly journals Identification of SARS-CoV-2 Nucleocapsid and Spike T-cell Epitopes for Assessing T-cell Immunity

2020 ◽  
pp. JVI.02002-20
Author(s):  
Eunok Lee ◽  
Kerrie Sandgren ◽  
Gabriel Duette ◽  
Vicki V. Stylianou ◽  
Rajiv Khanna ◽  
...  
Keyword(s):  
T Cell ◽  
Immune Responses ◽  
Cd8 T Cells ◽  
T Cell Immunity ◽  
T Cell Epitopes ◽  
Analysis Pipeline ◽  
Cell Immunity ◽  
Immunogenic Peptides ◽  
Human Coronaviruses ◽  
Global Population

Developing optimal T-cell response assays to severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2) is critical for measuring the duration of immunity to this disease and assessing the efficacy of vaccine candidates. These assays need to target conserved regions of SARS-CoV-2 global variants and avoid cross-reactivity to seasonal human coronaviruses. To contribute to this effort, we employed an in-silico immunoinformatics analysis pipeline to identify immunogenic peptides resulting from conserved and highly networked regions with topological importance from the SARS-CoV-2 nucleocapsid and spike proteins. A total of 57 highly networked T-cell epitopes that are conserved across geographic viral variants were identified from these viral proteins, with a binding potential to diverse HLA alleles and 80-100% global population coverage. Importantly, 18 of these T-cell epitope derived peptides had limited homology to seasonal human coronaviruses making them promising candidates for SARS-CoV-2 specific T-cell immunity assays. Moreover, two of the NC-derived peptides elicited effector/polyfunctional responses of CD8+ T-cells derived from SARS-CoV-2 convalescent patients.ImportanceThe development of specific and validated immunologic tools is critical for understanding the level and duration of the cellular response induced by SARS-CoV-2 infection and/or vaccines against this novel coronavirus disease. To contribute to this effort, we employed an immunoinformatics analysis pipeline to define 57 SARS-CoV-2 immunogenic peptides within topologically important regions of the nucleocapsid (NC) and spike (S) proteins that will be effective for detecting cellular immune responses in 80-100% of the global population. Our immunoinformatics analysis revealed that 18 of these peptides had limited homology to circulating seasonal human coronaviruses, and therefore are promising candidates for distinguishing SARS-CoV-2 specific immune responses from pre-existing coronavirus immunity. Importantly, CD8+ T-cells derived from SARS-CoV-2 survivors exhibited polyfunctional effector responses to two novel NC-derived peptides identified as HLA-binders. These studies provide a proof of concept that our immunoinformatics analysis pipeline identifies novel immunogens which can elicit polyfunctional SARS-CoV-2 specific T-cell responses.

scholarly journals Artificial Intelligence for Monte Carlo Simulation in Medical Physics

2021 ◽  
Vol 9 ◽  
Author(s):  
David Sarrut ◽  
Ane Etxebeste ◽  
Enrique Muñoz ◽  
Nils Krah ◽  
Jean Michel Létang
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Monte Carlo Simulations ◽  
Convolutional Neural Networks ◽  
Medical Physics ◽  
Nuclear Imaging ◽  
Computation Time ◽  
Distribution Estimation

Monte Carlo simulation of particle tracking in matter is the reference simulation method in the field of medical physics. It is heavily used in various applications such as 1) patient dose distribution estimation in different therapy modalities (radiotherapy, protontherapy or ion therapy) or for radio-protection investigations of ionizing radiation-based imaging systems (CT, nuclear imaging), 2) development of numerous imaging detectors, in X-ray imaging (conventional CT, dual-energy, multi-spectral, phase contrast … ), nuclear imaging (PET, SPECT, Compton Camera) or even advanced specific imaging methods such as proton/ion imaging, or prompt-gamma emission distribution estimation in hadrontherapy monitoring. Monte Carlo simulation is a key tool both in academic research labs as well as industrial research and development services. Because of the very nature of the Monte Carlo method, involving iterative and stochastic estimation of numerous probability density functions, the computation time is high. Despite the continuous and significant progress on computer hardware and the (relative) easiness of using code parallelisms, the computation time is still an issue for highly demanding and complex simulations. Hence, since decades, Variance Reduction Techniques have been proposed to accelerate the processes in a specific configuration. In this article, we review the recent use of Artificial Intelligence methods for Monte Carlo simulation in medical physics and their main associated challenges. In the first section, the main principles of some neural networks architectures such as Convolutional Neural Networks or Generative Adversarial Network are briefly described together with a literature review of their applications in the domain of medical physics Monte Carlo simulations. In particular, we will focus on dose estimation with convolutional neural networks, dose denoising from low statistics Monte Carlo simulations, detector modelling and event selection with neural networks, generative networks for source and phase space modelling. The expected interests of those approaches are discussed. In the second section, we focus on the current challenges that still arise in this promising field.

Sign in / Sign up

Export Citation Format

Share Document