EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Alignment-Free Machine Learning Serotype Classification of the Dengue Virus

Vladimir Gajdov iD, Isidora Prosic iD, Mihaela Kavran iD, Filip Bosilkov iD, Tamas Petrovic iD, Jelena Konstantinov iD, Gospava Lazic iD

Viruses · 2026

DOI: 10.3390/v18030280 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Viruses, 2026. Verfasst von Vladimir Gajdov und 6 weiteren Autor:innen. Beteiligte Einrichtung: Scientific Veterinary Institute "Novi Sad", 21000 Novi Sad, Serbia. Hauptthemen laut MEDLINE: Dengue Virus, Machine Learning, Serotyping, Serogroup. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science Fund of the Republic of Serbia, Ministry of Science, Technological Development and Innovation of the Republic of Serbia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dengue virus (DENV) serotyping is essential for epidemiological surveillance, clinical risk assessment, and vaccine evaluation, as the four dengue serotypes differ in pathogenicity, immune interactions, and population dynamics. Existing subtyping methods largely rely on sequence alignment and phylogenetic inference, which can be computationally intensive and unreliable for short, fragmented, or error-prone sequences commonly generated in diagnostic and surveillance settings. There is a need for fast, alignment-free serotyping approaches that maintain high accuracy across heterogeneous sequence lengths while remaining scalable, transparent, and suitable for real-world diagnostic inputs. We demonstrate that compact 3-mer composition features are sufficient for highly accurate dengue virus serotyping when coupled with a lineage-aware Random Forest classification framework. Using 64 normalized 3-mer frequency features per sequence with ambiguity masking and enforcing strict cluster-aware validation at both 99% and 95% nucleotide identity thresholds, our approach achieved near-perfect accuracy and macro-F1 scores on held-out internal test sets. To further ensure independence, external validation datasets were filtered to remove exact sequence matches and any sequences sharing ≥99% or ≥95% nucleotide identity with internal data. On these strictly independent external datasets, the model maintained 100% accuracy and macro-F1 performance, confirming robust generalization beyond database redundancy. Robustness analyses showed stable performance under contiguous sequence truncation down to 300 bp and in the presence of ambiguous nucleotides, indicating resilience to realistic diagnostic inputs. These results demonstrate that a lightweight, alignment-free, machine learning approach can rival alignment-dependent methods while maintaining strict lineage-aware evaluation controls. The proposed framework combines high predictive accuracy, probabilistic reliability, computational efficiency, and reproducible validation design, making it well suited for large-scale genomic surveillance, rapid pre-screening, and diagnostic decision-support applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Dengue VirusMachine LearningSerotypingSerogroupPhylogenyClassification AlgorithmsHumansRandom ForestDengue

Stichwörter der Autor:innen

k-mer compositionsubtypingvector-borne diseasesviral classification

Autor:innen und Institutionen

  • Scientific Veterinary Institute "Novi Sad", 21000 Novi Sad, Serbia.
  • Faculty of Veterinary Medicine, University of Belgrade, 11000 Belgrade, Serbia.
  • Faculty of Agriculture, University of Novi Sad, 21000 Novi Sad, Serbia.
  • Faculty of Computer Science & Engineering, St Cyril and Methodius University, 1000 Skopje, North Macedonia.

ORCID-Profile: Vladimir Gajdov, Isidora Prosic, Mihaela Kavran, Filip Bosilkov, Tamas Petrovic, Jelena Konstantinov, Gospava Lazic

Förderung

  • Science Fund of the Republic of Serbia
  • Ministry of Science, Technological Development and Innovation of the Republic of Serbia

Zitieren

APA

Gajdov, V., Prosic, I., Kavran, M., Bosilkov, F., Petrovic, T., Konstantinov, J., & Lazic, G. (2026). Alignment-Free Machine Learning Serotype Classification of the Dengue Virus. Viruses. https://doi.org/10.3390/v18030280

Vancouver

Gajdov V, Prosic I, Kavran M, Bosilkov F, Petrovic T, Konstantinov J, et al. Alignment-Free Machine Learning Serotype Classification of the Dengue Virus. Viruses. 2026. doi:10.3390/v18030280

BibTeX
@article{Gajdov2026,
  author = {Gajdov, Vladimir and Prosic, Isidora and Kavran, Mihaela and Bosilkov, Filip and Petrovic, Tamas and Konstantinov, Jelena and Lazic, Gospava},
  title = {Alignment-Free Machine Learning Serotype Classification of the Dengue Virus},
  journal = {Viruses},
  year = {2026},
  doi = {10.3390/v18030280}
}
Kostenlos starten →