EpicCapo: epitope prediction using combined information of amino acid pairwise contact potentials and HLA-peptide contact site information

Saethang, Thammakorn; Hirose, Osamu; Kimkong, Ingorn; Vu, Tran Anh; Dang, Xuan Tho; Nguyen, Lan Anh; Le, Tu Kien T.; Kubo, Mamoru; Yamada, Yoichi; Satou, Kenji

doi:10.1186/1471-2105-13-313

Cited by 10 publications

(9 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A number of methods have been proposed for the identification of T-cell epitopes based on the binding ability of the predictor peptide to MHC molecules (45,46). As reported previously, multiple HLA class I-restricted CTL epitopes of HTNV-NP have been identified using overlapping peptides map screen methods in HFRS patients, one of which was the peptide FA9 restricted by HLA-A*02 (21).…”

Section: Discussionmentioning

confidence: 95%

Structure and Function of HLA-A*02-Restricted Hantaan Virus Cytotoxic T-Cell Epitope That Mediates Effective Protective Responses in HLA-A2.1/Kb Transgenic Mice

Cheng

Yuan

et al. 2016

Front. Immunol.

View full text Add to dashboard Cite

Hantavirus infections cause severe emerging diseases in humans and are associated with high mortality rates; therefore, they have become a global public health concern. Our previous study showed that the CD8+ T-cell epitope aa129–aa137 (FVVPILLKA, FA9) of the Hantaan virus (HTNV) nucleoprotein (NP), restricted by human leukocyte antigen (HLA)-A*02, induced specific CD8+ T-cell responses that controlled HTNV infection in humans. However, the in vivo immunogenicity of peptide FA9 and the effect of FA9-specific CD8+ T-cell immunity remain unclear. Here, based on a detailed structural analysis of the peptide FA9/HLA-A*0201 complex and functional investigations using HLA-A2.1/Kb transgenic (Tg) mice, we found that the overall structure of the peptide FA9/HLA-A*0201 complex displayed a typical MHC class I fold with Val2 and Ala9 as primary anchor residues and Val3 and Leu7 as secondary anchor residues that allow peptide FA9 to bind tightly with an HLA-A*0201 molecule. Residues in the middle portion of peptide FA9 extruding out of the binding groove may be the sites that allow for recognition by T-cell receptors. Immunization with peptide FA9 in HLA-A2.1/Kb Tg mice induced FA9-specific cytotoxic T-cell responses characterized by the induction of high expression levels of interferon-γ, tumor necrosis factor-α, granzyme B, and CD107a. In an HTNV challenge trial, significant reductions in the levels of both the antigens and the HTNV RNA loads were observed in the liver, spleen, and kidneys of Tg mice pre-vaccinated with peptide FA9. Thus, our findings highlight the ability of HTNV epitope-specific CD8+ T-cell immunity to control HTNV and support the possibility that the HTNV-NP FA9 peptide, naturally processed in vivo in an HLA-A*02-restriction manner, may be a good candidate for the development HTNV peptide vaccines.

show abstract

Section: Discussionmentioning

confidence: 95%

Structure and Function of HLA-A*02-Restricted Hantaan Virus Cytotoxic T-Cell Epitope That Mediates Effective Protective Responses in HLA-A2.1/Kb Transgenic Mice

Cheng

Yuan

et al. 2016

Front. Immunol.

View full text Add to dashboard Cite

show abstract

“…As more experimental data became available, statistical methods have been developed using positional scoring matrixes that utilize amino acid occurrence frequencies at each position [ 5 , 6 ]. Recently, more sophisticated machine learning methods [ 7 – 9 ] have generated the most successful results by training large amount of experimental data derived from public databases, such as the Immune Epitope Database [ 10 ]. Allele-specific machine learning methods generally achieve more accurate predictions as more data are learned for each HLA-I allele.…”

Section: Introductionmentioning

confidence: 99%

Deep convolutional neural networks for pan-specific peptide-MHC class I binding prediction

Han

Kim

2017

BMC Bioinformatics

View full text Add to dashboard Cite

BackgroundComputational scanning of peptide candidates that bind to a specific major histocompatibility complex (MHC) can speed up the peptide-based vaccine development process and therefore various methods are being actively developed. Recently, machine-learning-based methods have generated successful results by training large amounts of experimental data. However, many machine learning-based methods are generally less sensitive in recognizing locally-clustered interactions, which can synergistically stabilize peptide binding. Deep convolutional neural network (DCNN) is a deep learning method inspired by visual recognition process of animal brain and it is known to be able to capture meaningful local patterns from 2D images. Once the peptide-MHC interactions can be encoded into image-like array(ILA) data, DCNN can be employed to build a predictive model for peptide-MHC binding prediction. In this study, we demonstrated that DCNN is able to not only reliably predict peptide-MHC binding, but also sensitively detect locally-clustered interactions.ResultsNonapeptide-HLA-A and -B binding data were encoded into ILA data. A DCNN, as a pan-specific prediction model, was trained on the ILA data. The DCNN showed higher performance than other prediction tools for the latest benchmark datasets, which consist of 43 datasets for 15 HLA-A alleles and 25 datasets for 10 HLA-B alleles. In particular, the DCNN outperformed other tools for alleles belonging to the HLA-A3 supertype. The F1 scores of the DCNN were 0.86, 0.94, and 0.67 for HLA-A*31:01, HLA-A*03:01, and HLA-A*68:01 alleles, respectively, which were significantly higher than those of other tools. We found that the DCNN was able to recognize locally-clustered interactions that could synergistically stabilize peptide binding. We developed ConvMHC, a web server to provide user-friendly web interfaces for peptide-MHC class I binding predictions using the DCNN. ConvMHC web server can be accessible via http://jumong.kaist.ac.kr:8080/convmhc.ConclusionsWe developed a novel method for peptide-HLA-I binding predictions using DCNN trained on ILA data that encode peptide binding data and demonstrated the reliable performance of the DCNN in nonapeptide binding predictions through the independent evaluation on the latest IEDB benchmark datasets. Our approaches can be applied to characterize locally-clustered patterns in molecular interactions, such as protein/DNA, protein/RNA, and drug/protein interactions.Electronic supplementary materialThe online version of this article (10.1186/s12859-017-1997-x) contains supplementary material, which is available to authorized users.

show abstract

“…Most tools rely on small neural networks (NN) or variations of position-specific weight matrices (PSSM), to calculate the probability of a peptide matching a consensus motif or model. NetMHC tools (such as netMHC, netMHCII, netMHCpan, netMHCIIpan and others) have been under constant development and have consistently performed well throughout the last decade, (Peters, Nielsen, and Sette 2020;Mei et al 2019;Saethang et al 2012;Bhattacharya et al 2017) . Several tools are restricted in terms of which allotypes are available for prediction, in particular for MHC class II.…”

mentioning

confidence: 99%

COVID-19 Vaccine Candidates: Prediction and Validation of 174 SARS-CoV-2 Epitopes

Prachař

Justesen²,

Steen-Jensen³

et al. 2020

Preprint

View full text Add to dashboard Cite

The recent outbreak of SARS-CoV-2 (2019-nCoV) virus has highlighted the need for fast and efficacious vaccine development. Stimulation of a proper immune response that leads to protection is highly dependent on presentation of epitopes to circulating T-cells via the HLA complex. SARS-CoV-2 is a large RNA virus and testing of all overlapping peptides in vitro to deconvolute an immune response is not feasible. Therefore HLA-binding prediction tools are often used to narrow down the number of peptides to test. We tested 19 epitope-HLA-binding prediction tools, and using an in vitro peptide MHC stability assay, we assessed 777 peptides that were predicted to be good binders across 11 MHC allotypes. In this investigation of potential SARS-CoV-2 epitopes we found that current prediction tools vary in performance when assessing binding stability, and they are highly dependent on the MHC allotype in question. Designing a COVID-19 vaccine where only a few epitope targets are included is therefore a very challenging task. Here, we present 174 SARS-CoV-2 epitopes with high prediction binding scores, validated to bind stably to 11 HLA allotypes. Our findings may contribute to the design of an efficacious vaccine against COVID-19.

show abstract

EpicCapo: epitope prediction using combined information of amino acid pairwise contact potentials and HLA-peptide contact site information

Cited by 10 publications

References 55 publications

Structure and Function of HLA-A*02-Restricted Hantaan Virus Cytotoxic T-Cell Epitope That Mediates Effective Protective Responses in HLA-A2.1/Kb Transgenic Mice

Structure and Function of HLA-A*02-Restricted Hantaan Virus Cytotoxic T-Cell Epitope That Mediates Effective Protective Responses in HLA-A2.1/Kb Transgenic Mice

Deep convolutional neural networks for pan-specific peptide-MHC class I binding prediction

COVID-19 Vaccine Candidates: Prediction and Validation of 174 SARS-CoV-2 Epitopes

Contact Info

Product

Resources

About