Viral Immunogenicity Prediction by Machine Learning Methods
International Journal of Molecular Sciences · 03.03.2024 · 25 (5) · 2949
DOI: 10.3390/ijms25052949 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Molecular Sciences, online erschienen am 03.03.2024. Verfasst von Nikolet Doneva und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Pharmacy, Medical University-Sofia, 1000 Sofia, Bulgaria. Hauptthemen laut MEDLINE: Algorithms, Vaccines. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Science and Education for Smart Growth Operational Program,, Bulgarian National Roadmap for Research Infrastructure (2017-2024), Science and Education for Smart Growth Operational Program.
Abstract (Originalsprache)
Since viruses are one of the main causes of infectious illnesses, prophylaxis is essential for efficient disease control. Vaccines play a pivotal role in mitigating the transmission of various viral infections and fortifying our defenses against them. The initial step in modern vaccine design and development involves the identification of potential vaccine targets through computational techniques. Here, using datasets of 1588 known viral immunogens and 468 viral non-immunogens, we apply machine learning algorithms to develop models for the prediction of protective immunogens of viral origin. The datasets are split into training and test sets in a 4:1 ratio. The protein structures are encoded by E-descriptors and transformed into uniform vectors by the auto- and cross-covariance methods. The most relevant descriptors are selected by the gain/ratio technique. The models generated by Random Forest, Multilayer Perceptron, and XGBoost algorithms demonstrate superior predictive performance on the test sets, surpassing predictions made by VaxiJen 2.0—an established gold standard in viral immunogenicity prediction. The key attributes determining immunogenicity in viral proteins are specific fingerprints in hydrophobicity and steric properties.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Faculty of Pharmacy, Medical University-Sofia, 1000 Sofia, Bulgaria.
ORCID-Profile: Nikolet Doneva, Ivan Dimitrov
Förderung
- The Science and Education for Smart Growth Operational Program,
- Bulgarian National Roadmap for Research Infrastructure (2017-2024)
- Science and Education for Smart Growth Operational Program
Zitieren
APA
Doneva, N., & Dimitrov, I. (2024). Viral Immunogenicity Prediction by Machine Learning Methods. International Journal of Molecular Sciences, 25(5), 2949. https://doi.org/10.3390/ijms25052949
Vancouver
Doneva N, Dimitrov I. Viral Immunogenicity Prediction by Machine Learning Methods. International Journal of Molecular Sciences. 2024;25(5):2949. doi:10.3390/ijms25052949
BibTeX
@article{Doneva2024,
author = {Doneva, Nikolet and Dimitrov, Ivan},
title = {Viral Immunogenicity Prediction by Machine Learning Methods},
journal = {International Journal of Molecular Sciences},
year = {2024},
volume = {25},
number = {5},
pages = {2949},
doi = {10.3390/ijms25052949}
}
EUVIMED