1
|
Bukhari SNH, Ogudo KA. Hybrid Predictive Machine Learning Model for the Prediction of Immunodominant Peptides of Respiratory Syncytial Virus. Bioengineering (Basel) 2024; 11:791. [PMID: 39199749 PMCID: PMC11351268 DOI: 10.3390/bioengineering11080791] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2024] [Revised: 07/26/2024] [Accepted: 08/02/2024] [Indexed: 09/01/2024] Open
Abstract
Respiratory syncytial virus (RSV) is a common respiratory pathogen that infects the human lungs and respiratory tract, often causing symptoms similar to the common cold. Vaccination is the most effective strategy for managing viral outbreaks. Currently, extensive efforts are focused on developing a vaccine for RSV. Traditional vaccine design typically involves using an attenuated form of the pathogen to elicit an immune response. In contrast, peptide-based vaccines (PBVs) aim to identify and chemically synthesize specific immunodominant peptides (IPs), known as T-cell epitopes (TCEs), to induce a targeted immune response. Despite their potential for enhancing vaccine safety and immunogenicity, PBVs have received comparatively less attention. Identifying IPs for PBV design through conventional wet-lab experiments is challenging, costly, and time-consuming. Machine learning (ML) techniques offer a promising alternative, accurately predicting TCEs and significantly reducing the time and cost of vaccine development. This study proposes the development and evaluation of eight hybrid ML predictive models created through the permutations and combinations of two classification methods, two feature weighting techniques, and two feature selection algorithms, all aimed at predicting the TCEs of RSV. The models were trained using the experimentally determined TCEs and non-TCE sequences acquired from the Bacterial and Viral Bioinformatics Resource Center (BV-BRC) repository. The hybrid model composed of the XGBoost (XGB) classifier, chi-squared (ChST) weighting technique, and backward search (BST) as the optimal feature selection algorithm (ChST-BST-XGB) was identified as the best model, achieving an accuracy, sensitivity, specificity, F1 score, AUC, precision, and MCC of 97.10%, 0.98, 0.97, 0.98, 0.99, 0.99, and 0.96, respectively. Additionally, K-fold cross-validation (KFCV) was performed to ensure the model's reliability and an average accuracy of 97.21% was recorded for the ChST-BST-XGB model. The results indicate that the hybrid XGBoost model consistently outperforms other hybrid approaches. The epitopes predicted by the proposed model may serve as promising vaccine candidates for RSV, subject to in vitro and in vivo scientific assessments. This model can assist the scientific community in expediting the screening of active TCE candidates for RSV, ultimately saving time and resources in vaccine development.
Collapse
Affiliation(s)
- Syed Nisar Hussain Bukhari
- National Institute of Electronics and Information Technology (NIELIT), Ministry of Electronics and Information Technology (MeitY), Government of India, Srinagar 191132, India
| | - Kingsley A. Ogudo
- Department of Electrical & Electronics Engineering, Faculty of Engineering and the Built Environment, University of Johannesburg, Johannesburg 0524, South Africa;
| |
Collapse
|
2
|
Nuttens C, Moyersoen J, Curcio D, Aponte-Torres Z, Baay M, Vroling H, Gessner BD, Begier E. Differences Between RSV A and RSV B Subgroups and Implications for Pharmaceutical Preventive Measures. Infect Dis Ther 2024; 13:1725-1742. [PMID: 38971918 PMCID: PMC11266343 DOI: 10.1007/s40121-024-01012-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2023] [Accepted: 06/21/2024] [Indexed: 07/08/2024] Open
Abstract
INTRODUCTION Understanding the differences between respiratory syncytial virus (RSV) subgroups A and B provides insights for the development of prevention strategies and public health interventions. We aimed to describe the structural differences of RSV subgroups, their epidemiology, and genomic diversity. The associated immune response and differences in clinical severity were also investigated. METHODS A literature review from PubMed and Google Scholar (1985-2023) was performed and extended using snowballing from references in captured publications. RESULTS RSV has two major antigenic subgroups, A and B, defined by the G glycoprotein. The RSV F fusion glycoprotein in the prefusion conformation is a major target of virus neutralizing antibodies and differs in surface exposed regions between RSV A and RSV B. The subgroups co-circulate annually, but there is considerable debate as to whether clinical severity is impacted by the subgroup of the infecting RSV strain. Large variations between the studies reporting RSV subgroup impact on clinical severity were observed. A tendency for higher disease severity may be attributed to RSV A but no consensus could be reached as to whether infection by one of the subgroup caused more severe outcomes. RSV genotype diversity decreased over the last two decades, and ON and BA have become the sole lineages detected for RSV A and RSV B, since 2014. No studies with data obtained after 2014 reported a difference in disease severity between the two subgroups. RSV F is relatively well conserved and highly similar between RSV A and B, but changes in the amino acid sequence have been observed. Some of these changes led to differences in F antigenic sites compared to reference F sequences (e.g., RSV/A Long strain), which are more pronounced in antigenic sites of the prefusion conformation of RSV B. Initial results from the second season after vaccination suggest specific RSV B efficacy wanes more rapidly than RSV A for RSV PreF-based monovalent vaccines. CONCLUSIONS RSV A and RSV B both contribute substantially to the global RSV burden. Both RSV subgroups cause severe disease and none of the available evidence to date suggests any differences in clinical severity between the subgroups. Therefore, it is important to implement measures effective at preventing disease due to both RSV A and RSV B to ensure impactful public health interventions. Monitoring overtime will be needed to assess the impact of waning antibody levels on subgroup-specific efficacy.
Collapse
Affiliation(s)
| | | | | | | | - Marc Baay
- Epidemiology & Pharmacovigilance, P95, Louvain, Belgium
| | - Hilde Vroling
- Epidemiology & Pharmacovigilance, P95, Louvain, Belgium
| | | | - Elizabeth Begier
- Scientific Affairs, Older Adult RSV Vaccine Program, Global Medical Development Scientific and Clinical Affairs, Pfizer Vaccines, 9 Riverwalk, Citywest Business Campus, Dublin 24, Dublin, Ireland.
| |
Collapse
|
3
|
Guo H, Song Y, Li H, Hu H, Shi Y, Jiang J, Guo J, Cao L, Mao N, Zhang Y. A Mixture of T-Cell Epitope Peptides Derived from Human Respiratory Syncytial Virus F Protein Conferred Protection in DR1-TCR Tg Mice. Vaccines (Basel) 2024; 12:77. [PMID: 38250890 PMCID: PMC10820450 DOI: 10.3390/vaccines12010077] [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: 12/08/2023] [Revised: 01/04/2024] [Accepted: 01/10/2024] [Indexed: 01/23/2024] Open
Abstract
Human respiratory syncytial virus (HRSV) poses a significant disease burden on global health. To date, two vaccines that primarily induce humoral immunity to prevent HRSV infection have been approved, whereas vaccines that primarily induce T-cell immunity have not yet been well-represented. To address this gap, 25 predicted T-cell epitope peptides derived from the HRSV fusion protein with high human leukocyte antigen (HLA) binding potential were synthesized, and their ability to be recognized by PBMC from previously infected HRSV cases was assessed using an ELISpot assay. Finally, nine T-cell epitope peptides were selected, each of which was recognized by at least 20% of different donors' PBMC as potential vaccine candidates to prevent HRSV infection. The protective efficacy of F-9PV, a combination of nine peptides along with CpG-ODN and aluminum phosphate (Al) adjuvants, was validated in both HLA-humanized mice (DR1-TCR transgenic mice, Tg mice) and wild-type (WT) mice. The results show that F-9PV significantly enhanced protection against viral challenge as evidenced by reductions in viral load and pathological lesions in mice lungs. In addition, F-9PV elicits robust Th1-biased response, thereby mitigating the potential safety risk of Th2-induced respiratory disease during HRSV infection. Compared to WT mice, the F-9PV mice exhibited superior protection and immunogenicity in Tg mice, underscoring the specificity for human HLA. Overall, our results demonstrate that T-cell epitope peptides provide protection against HRSV infection in animal models even in the absence of neutralizing antibodies, indicating the feasibility of developing an HRSV T-cell epitope peptide-based vaccine.
Collapse
Affiliation(s)
- Hong Guo
- NHC Key Laboratory of Medical Virology and Viral Diseases, National Institute for Viral Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing 102206, China; (H.G.); (Y.S.); (H.L.); (H.H.); (Y.S.); (J.J.); (J.G.); (L.C.)
| | - Yang Song
- NHC Key Laboratory of Medical Virology and Viral Diseases, National Institute for Viral Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing 102206, China; (H.G.); (Y.S.); (H.L.); (H.H.); (Y.S.); (J.J.); (J.G.); (L.C.)
| | - Hai Li
- NHC Key Laboratory of Medical Virology and Viral Diseases, National Institute for Viral Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing 102206, China; (H.G.); (Y.S.); (H.L.); (H.H.); (Y.S.); (J.J.); (J.G.); (L.C.)
| | - Hongqiao Hu
- NHC Key Laboratory of Medical Virology and Viral Diseases, National Institute for Viral Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing 102206, China; (H.G.); (Y.S.); (H.L.); (H.H.); (Y.S.); (J.J.); (J.G.); (L.C.)
| | - Yuqing Shi
- NHC Key Laboratory of Medical Virology and Viral Diseases, National Institute for Viral Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing 102206, China; (H.G.); (Y.S.); (H.L.); (H.H.); (Y.S.); (J.J.); (J.G.); (L.C.)
| | - Jie Jiang
- NHC Key Laboratory of Medical Virology and Viral Diseases, National Institute for Viral Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing 102206, China; (H.G.); (Y.S.); (H.L.); (H.H.); (Y.S.); (J.J.); (J.G.); (L.C.)
| | - Jinyuan Guo
- NHC Key Laboratory of Medical Virology and Viral Diseases, National Institute for Viral Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing 102206, China; (H.G.); (Y.S.); (H.L.); (H.H.); (Y.S.); (J.J.); (J.G.); (L.C.)
| | - Lei Cao
- NHC Key Laboratory of Medical Virology and Viral Diseases, National Institute for Viral Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing 102206, China; (H.G.); (Y.S.); (H.L.); (H.H.); (Y.S.); (J.J.); (J.G.); (L.C.)
| | - Naiying Mao
- NHC Key Laboratory of Medical Virology and Viral Diseases, National Institute for Viral Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing 102206, China; (H.G.); (Y.S.); (H.L.); (H.H.); (Y.S.); (J.J.); (J.G.); (L.C.)
| | - Yan Zhang
- NHC Key Laboratory of Medical Virology and Viral Diseases, National Institute for Viral Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing 102206, China; (H.G.); (Y.S.); (H.L.); (H.H.); (Y.S.); (J.J.); (J.G.); (L.C.)
- National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases (NITFID), National Institute for Viral Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing 102206, China
| |
Collapse
|