EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Evaluation of Different Machine Learning Approaches to Predict Antigenic Distance Among Newcastle Disease Virus (NDV) Strains

Giovanni Franzo iD, Alice Fusaro, Chantal J Snoeck iD, Aleksandar Dodovski iD, Steven Van Borm iD, Mieke Steensels iD, Vasiliki Christodoulou iD, Iuliana Onita, Raluca Burlacu, Azucena Sánchez Sánchez, Ilya A Chvala iD, Mia Kim Torchetti und 11 weitere

Viruses · 14.04.2025 · 17 (4) · 567

DOI: 10.3390/v17040567 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Viruses, online erschienen am 14.04.2025. Verfasst von Giovanni Franzo und 22 weiteren Autor:innen. Beteiligte Einrichtung: Department of Animal Medicine, Production and Health (MAPS), Padua University, 35020 Legnaro, Italy. Hauptthemen laut MEDLINE: Newcastle disease virus, Machine Learning, Antigens, Viral. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Development of Smart Innovation through Research in Agriculture (DeSIRa) program), European Commission, Italian Ministry of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Newcastle disease virus (NDV) continues to present a significant challenge for vaccination due to its rapid evolution and the emergence of new variants. Although molecular and sequence data are now quickly and inexpensively produced, genetic distance rarely serves as a good proxy for cross-protection, while experimental studies to assess antigenic differences are time consuming and resource intensive. In response to these challenges, this study explores and compares several machine learning (ML) methods to predict the antigenic distance between NDV strains as determined by hemagglutination-inhibition (HI) assays. By analyzing F and HN gene sequences alongside corresponding amino acid features, we developed predictive models aimed at estimating antigenic distances. Among the models evaluated, the random forest (RF) approach outperformed traditional linear models, achieving a predictive accuracy with an R2 value of 0.723 compared to only 0.051 for linear models based on genetic distance alone. This significant improvement demonstrates the usefulness of applying flexible ML approaches as a rapid and reliable tool for vaccine selection, minimizing the need for labor-intensive experimental trials. Moreover, the flexibility of this ML framework holds promise for application to other infectious diseases in both animals and humans, particularly in scenarios where rapid response and ethical constraints limit conventional experimental approaches.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Newcastle disease virusMachine LearningAntigens, ViralAnimalsNewcastle DiseaseHemagglutination Inhibition TestsChickensHN ProteinAntigenic Variation

Stichwörter der Autor:innen

NDVantigenic cartographycross-protectionhemagglutination inhibitionmachine learningsequencing

Substanzen

Antigens, ViralHN Protein

Autor:innen und Institutionen

  • Department of Animal Medicine, Production and Health (MAPS), Padua University, 35020 Legnaro, Italy.
  • Division of Comparative Biomedical Sciences (DSBIO), Istituto Zooprofilattico Sperimentale delle Venezie, Viale dell'Università 10, 35020 Legnaro, Italy.
  • Clinical and Applied Virology Group, Department of Infection and Immunity, Luxembourg Institute of Health, 29, Rue Henri Koch, Esch-sur-Alzette, L-4354 Luxembourg, Luxembourg.
  • Faculty of Veterinary Medicine-Skopje, Ss. Cyril and Methodius University in Skopje, Lazar Pop Trajkov 5-7, 1000 Skopje, North Macedonia.
  • Avian Virology and Immunology, Sciensano, Rue Groeselenberg 99, 1180 Ukkel, Belgium.
  • Section Veterinary Services (1417), Laboratory for Animal Health Virology, 79, Athalassa Avenue, Aglantzia, Nicosia 2109, Cyprus.

ORCID-Profile: Giovanni Franzo, Chantal J Snoeck, Aleksandar Dodovski, Steven Van Borm, Mieke Steensels, Vasiliki Christodoulou, Ilya A Chvala, Ismaila Shittu, Mayowa Olabode, Isabella Monne, Mattia Cecchinato, Alessio Bortolami

Förderung

  • Development of Smart Innovation through Research in Agriculture (DeSIRa) program)
  • European Commission
  • Italian Ministry of Health

Zitieren

APA

Franzo, G., Fusaro, A., Snoeck, C. J., Dodovski, A., Van Borm, S., Steensels, M., Christodoulou, V., Onita, I., Burlacu, R., Sánchez, A. S., Chvala, I. A., Torchetti, M. K., Shittu, I., Olabode, M., Pastori, A., Schivo, A., Salomoni, A., Maniero, S., Zambon, I., …, & Bortolami, A. (2025). Evaluation of Different Machine Learning Approaches to Predict Antigenic Distance Among Newcastle Disease Virus (NDV) Strains. Viruses, 17(4), 567. https://doi.org/10.3390/v17040567

Vancouver

Franzo G, Fusaro A, Snoeck CJ, Dodovski A, Van Borm S, Steensels M, et al. Evaluation of Different Machine Learning Approaches to Predict Antigenic Distance Among Newcastle Disease Virus (NDV) Strains. Viruses. 2025;17(4):567. doi:10.3390/v17040567

BibTeX
@article{Franzo2025,
  author = {Franzo, Giovanni and Fusaro, Alice and Snoeck, Chantal J and Dodovski, Aleksandar and Van Borm, Steven and Steensels, Mieke and Christodoulou, Vasiliki and Onita, Iuliana and Burlacu, Raluca and Sánchez, Azucena Sánchez and Chvala, Ilya A and Torchetti, Mia Kim and Shittu, Ismaila and Olabode, Mayowa and Pastori, Ambra and Schivo, Alessia and Salomoni, Angela and Maniero, Silvia and Zambon, Ilaria and Bonfante, Francesco and Monne, Isabella and Cecchinato, Mattia and Bortolami, Alessio},
  title = {Evaluation of Different Machine Learning Approaches to Predict Antigenic Distance Among Newcastle Disease Virus (NDV) Strains},
  journal = {Viruses},
  year = {2025},
  volume = {17},
  number = {4},
  pages = {567},
  doi = {10.3390/v17040567}
}
Kostenlos starten →