1
|
Yang Y, Wei Z, Cia G, Song X, Pucci F, Rooman M, Xue F, Hou Q. MHCII-peptide presentation: an assessment of the state-of-the-art prediction methods. Front Immunol 2024; 15:1293706. [PMID: 38646540 PMCID: PMC11027168 DOI: 10.3389/fimmu.2024.1293706] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2023] [Accepted: 02/19/2024] [Indexed: 04/23/2024] Open
Abstract
Major histocompatibility complex Class II (MHCII) proteins initiate and regulate immune responses by presentation of antigenic peptides to CD4+ T-cells and self-restriction. The interactions between MHCII and peptides determine the specificity of the immune response and are crucial in immunotherapy and cancer vaccine design. With the ever-increasing amount of MHCII-peptide binding data available, many computational approaches have been developed for MHCII-peptide interaction prediction over the last decade. There is thus an urgent need to provide an up-to-date overview and assessment of these newly developed computational methods. To benchmark the prediction performance of these methods, we constructed an independent dataset containing binding and non-binding peptides to 20 human MHCII protein allotypes from the Immune Epitope Database, covering DP, DR and DQ alleles. After collecting 11 known predictors up to January 2022, we evaluated those available through a webserver or standalone packages on this independent dataset. The benchmarking results show that MixMHC2pred and NetMHCIIpan-4.1 achieve the best performance among all predictors. In general, newly developed methods perform better than older ones due to the rapid expansion of data on which they are trained and the development of deep learning algorithms. Our manuscript not only draws a full picture of the state-of-art of MHCII-peptide binding prediction, but also guides researchers in the choice among the different predictors. More importantly, it will inspire biomedical researchers in both academia and industry for the future developments in this field.
Collapse
Affiliation(s)
- Yaqing Yang
- Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan, China
- National Institute of Health Data Science of China, Shandong University, Jinan, China
| | - Zhonghui Wei
- Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan, China
- National Institute of Health Data Science of China, Shandong University, Jinan, China
| | - Gabriel Cia
- Computational Biology and Bioinformatics, Université Libre de Bruxelles, Brussels, Belgium
- Interuniversity Institute of Bioinformatics in Brussels, Brussels, Belgium
| | - Xixi Song
- Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan, China
- National Institute of Health Data Science of China, Shandong University, Jinan, China
| | - Fabrizio Pucci
- Computational Biology and Bioinformatics, Université Libre de Bruxelles, Brussels, Belgium
- Interuniversity Institute of Bioinformatics in Brussels, Brussels, Belgium
| | - Marianne Rooman
- Computational Biology and Bioinformatics, Université Libre de Bruxelles, Brussels, Belgium
- Interuniversity Institute of Bioinformatics in Brussels, Brussels, Belgium
| | - Fuzhong Xue
- Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan, China
- National Institute of Health Data Science of China, Shandong University, Jinan, China
| | - Qingzhen Hou
- Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan, China
- National Institute of Health Data Science of China, Shandong University, Jinan, China
| |
Collapse
|
2
|
A simple pan-specific RNN model for predicting HLA-II binding peptides. Mol Immunol 2021; 139:177-183. [PMID: 34555693 DOI: 10.1016/j.molimm.2021.09.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/27/2020] [Revised: 08/17/2021] [Accepted: 09/02/2021] [Indexed: 11/19/2022]
Abstract
The prediction of human leukocyte antigen (HLA) class II binding peptides plays important roles in understanding the mechanism of immune recognition and developing effective epitope-based vaccines. In this work, gated recurrent unit (GRU)-based recurrent neural network (RNN) was successfully employed to establish a pan-specific prediction model of HLA-II-binding peptides by using only the HLA and peptide sequence information. In comparison with the existing pan-specific models of HLA-II-binding peptides, the GRU-based RNN model covered a broad spectrum of HLA-II molecules including 50 HLA-DR, 47 HLA-DQ, and 19 HLA-DP molecules with peptide lengths varying from 8 to 43 mers. The results demonstrated strong discriminant capabilities of the GRU-based RNN model, of which the AUC values were 0.92, 0.88, and 0.88 for the training, validation, and test sets, respectively. Also, the GRU-based model showed state-of-the-art performances in predicting the binding peptides with the length ranging from 8-32 mers, which provides an efficient method for predicting HLA-II-binding peptides of longer lengths in comparison with the available methods. Overall, taking the advantages of the RNN architecture, the established pan-specific GRU model can be used for predicting accurately the HLA-II-binding peptides in a simple and direct manner.
Collapse
|
3
|
Kangueane P. From Anna University to America and to Agriculture. Bioinformation 2021; 17:29-36. [PMID: 34393415 PMCID: PMC8340703 DOI: 10.6026/97320630017029] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2020] [Accepted: 11/06/2020] [Indexed: 11/23/2022] Open
Abstract
Anna University (AU) is an awesome alma mater for attracting the attention of the invincible through awareness from education. It is a place with a plan for preparing a palace in a person's life. It is an avenue for America through adequate cGPA and Advanced GRE (AGRE) with good TOEFL score. The views,visions, modes and models of several faculty members shaped many technocrats, teachers, entrepreneurs, journalists, editors and even farmers. Technology is engineering with science. The foundation and facilities at AU is priceless. AU created the framework for Industrial Biotechnology, a truly inter disciplinary curriculum with an optimal blend of Engineering and Science (Biology especially Agriculture and Healthcare through Organic chemistry) in 1992 almost 28 years back. The place was positioned just perfect in the world for wonders to come true. The Raman auditorium (in reverence to the Nobel Laureate Sir CV Raman) reassured rational research with reasonable respect in many minds at the ACTECH (Alagappa College of Technology) under the administration of AU. The admiration, acknowledgement and accountability for the alma mater, the AU will always remain precious.
Collapse
|
4
|
Short Peptide Vaccine Design and Development: Promises and Challenges. GLOBAL VIROLOGY I - IDENTIFYING AND INVESTIGATING VIRAL DISEASES 2015. [PMCID: PMC7121995 DOI: 10.1007/978-1-4939-2410-3_1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
Abstract
Vaccine development for viral diseases is a challenge where subunit vaccines are often ineffective. Therefore, the need for alternative solutions is crucial. Thus, short peptide vaccine candidates promise effective answers under such circumstances. Short peptide vaccine candidates are linear T-cell epitopes (antigenic determinants that are recognized by the immune system) that specifically function by binding human leukocyte antigen (HLA) alleles of different ethnicities (including Black, Caucasian, Oriental, Hispanic, Pacific Islander, American Indian, Australian aboriginal, and mixed ethnicities). The population-specific allele-level HLA sequence data in the public IMGT/HLA database contains approximately 12542 nomenclature defined class I (9437) and class II (3105) HLA alleles as of March 2015 present in several ethnic populations. The bottleneck in short peptide vaccine design and development is HLA polymorphism on the one hand and viral diversity on the other hand. Hence, a crucial step in its design and development is HLA allele-specific binding of short antigen peptides. This is usually combinatorial and computationally labor intensive. Mathematical models utilizing structure-defined pockets are currently available for class I and class II HLA-peptide-binding peptides. Frameworks have been developed to design protocols to identify the most feasible short peptide cocktails as vaccine candidates with superantigen properties among known HLA supertypes. This approach is a promising solution to develop new viral vaccines given the current advancement in T-cell immuno-informatics, yet challenging in terms of prediction efficiency and protocol development.
Collapse
|
5
|
Oprea M, Antohe F. Reverse-vaccinology strategy for designing T-cell epitope candidates for Staphylococcus aureus endocarditis vaccine. Biologicals 2013; 41:148-53. [PMID: 23582120 DOI: 10.1016/j.biologicals.2013.03.001] [Citation(s) in RCA: 24] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/25/2012] [Revised: 03/12/2013] [Accepted: 03/15/2013] [Indexed: 11/30/2022] Open
Abstract
Staphylococcus aureus is an opportunistic pathogen causing various inflammatory diseases from skin and tissue local infections, to serious life threatening infections including endocarditis. Experimental models for endocarditis demonstrated that virulence factors of S. aureus, that are very important in infection of heart vegetations, are surface proteins which promote bacterial adherence. Until now, efforts to develop effective vaccines against S. aureus were unsuccessful, partly due to the fact that different vaccine formulations have targeted mainly B-cell immunity. Reverse vaccinology is applied here, in order to identify potential vaccine epitope candidates. The basic epitopes prediction strategy relied on detection of a common antigenic 9-mer epitope meant to be able to stimulate both the B-cell and T-cell mediated immunity. Ten surface exposed proteins were chosen for antigenicity testing. Using a web-based system, five T-cell epitopes corresponding to fibronectin binding protein A (FDFTLSNNV and YVDGYIETI), collagen adhesin (FSINYKTKI), serine-rich adhesin for platelets (LTFDSTNNT) and elastin binding protein (FAMDKSHPE) were selected as potential vaccine candidates. Epitopes sequences were found to be conserved among the different S. aureus genomes screened from NCBI GenBank. In vitro and in vivo immunological tests will be performed in order to validate the suitability of the epitopes for vaccine development.
Collapse
Affiliation(s)
- Mihaela Oprea
- Molecular Epidemiology Laboratory, Cantacuzino National Institute of Research-Development for Microbiology and Immunology, Splaiul Independentei Street, No. 103, 050096 Bucharest, Romania.
| | | |
Collapse
|
6
|
Zonneveld-Huijssoon E, Albani S, Prakken BJ, van Wijk F. Heat shock protein bystander antigens for peptide immunotherapy in autoimmune disease. Clin Exp Immunol 2013. [PMID: 23199319 DOI: 10.1111/j.1365-2249.2012.04627.x] [Citation(s) in RCA: 20] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/19/2022] Open
Abstract
Mucosal administration of an antigen eliciting bystander suppression at the site of inflammation results in effective antigen-specific immunotherapy for autoimmune diseases. Heat shock proteins are bystander antigens that are effective in peptide-specific immunotherapy in both experimental and human autoimmune disease. The efficacy of preventive peptide immunotherapy is increased by enhancing peptide-specific immune responses with proinflammatory agents. Combining peptide-specific immunotherapy with general suppression of inflammation may improve its therapeutic effect.
Collapse
Affiliation(s)
- E Zonneveld-Huijssoon
- Department of Pediatric Immunology, Centre for Cellular and Molecular Intervention, University Medical Centre Utrecht, Utrecht, the Netherlands
| | | | | | | |
Collapse
|
7
|
Saha I, Mazzocco G, Plewczynski D. Consensus classification of human leukocyte antigen class II proteins. Immunogenetics 2012; 65:97-105. [PMID: 23229472 PMCID: PMC3543608 DOI: 10.1007/s00251-012-0665-6] [Citation(s) in RCA: 11] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2012] [Accepted: 10/29/2012] [Indexed: 01/15/2023]
Abstract
Class II human leukocyte antigens (HLA II) are proteins involved in the human immunological adaptive response by binding and exposing some pre-processed, non-self peptides in the extracellular domain in order to make them recognizable by the CD4+ T lymphocytes. However, the understanding of HLA–peptide binding interaction is a crucial step for designing a peptide-based vaccine because the high rate of polymorphisms in HLA class II molecules creates a big challenge, even though the HLA II proteins can be grouped into supertypes, where members of different class bind a similar pool of peptides. Hence, first we performed the supertype classification of 27 HLA II proteins using their binding affinities and structural-based linear motifs to create a stable group of supertypes. For this purpose, a well-known clustering method was used, and then, a consensus was built to find the stable groups and to show the functional and structural correlation of HLA II proteins. Thus, the overlap of the binding events was measured, confirming a large promiscuity within the HLA II–peptide interactions. Moreover, a very low rate of locus-specific binding events was observed for the HLA-DP genetic locus, suggesting a different binding selectivity of these proteins with respect to HLA-DR and HLA-DQ proteins. Secondly, a predictor based on a support vector machine (SVM) classifier was designed to recognize HLA II-binding peptides. The efficiency of prediction was estimated using precision, recall (sensitivity), specificity, accuracy, F-measure, and area under the ROC curve values of random subsampled dataset in comparison with other supervised classifiers. Also the leave-one-out cross-validation was performed to establish the efficiency of the predictor. The availability of HLA II–peptide interaction dataset, HLA II-binding motifs, high-quality amino acid indices, peptide dataset for SVM training, and MATLAB code of the predictor is available at http://sysbio.icm.edu.pl/HLA.
Collapse
Affiliation(s)
- Indrajit Saha
- Interdisciplinary Centre for Mathematical and Computational Modeling, University of Warsaw, Warsaw, Poland
| | | | | |
Collapse
|
8
|
Mohanapriya A, Nandagond S, Shapshak P, Kangueane U, Kangueane P. A HLA-DRB supertype chart with potential overlapping peptide binding function. Bioinformation 2010; 4:300-9. [PMID: 20978603 PMCID: PMC2957767 DOI: 10.6026/97320630004300] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2009] [Revised: 12/07/2009] [Accepted: 01/16/2010] [Indexed: 11/23/2022] Open
Abstract
HLA-DRB alleles are class II alleles that are associated with CD4+ T-cell immune response. DRB alleles are polymorphic and currently there are about 622 named in the IMGT/HLA sequence database. Each allele binds short peptides with high sensitivity and specificity. However, it has been suggested that majority of HLA alleles can be covered within few HLA supertypes, where different members of a supertype bind similar peptides showing distinct repertoires. Definition of DRB supertypes using binding data is limited to few (about 29) known alleles (< 5% of all known DRB alleles). Hence, we describe a strategy using structurally defined virtual pockets to group all known DRB alleles with regard to their overlapping peptide binding specificity.
Collapse
Affiliation(s)
- Arumugam Mohanapriya
- Biomedical Informatics, Pondicherry 607 402, India
- VITU, Vellore, Tamil Nadu 632 014, India
| | | | - Paul Shapshak
- Division of Infectious Disease & International Health Department of Psychiatry & Behavioral Medicine USF Health Tampa Gen Hospital, 1 Tampa Gen Circle, Room G318, Tampa FL 33606
| | | | | |
Collapse
|