EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Identification of Host Gene Transcripts by Machine Learning and Their Application to Predict Outcome in Ebola Virus Disease

Jocelyn G Pérez iD, Natasha Y Rickett iD, Stephan Günther iD, Romy Kerber iD, Lisa F P Ng, Tom Fletcher iD, Tracy MacGill iD, Todd Myers, Robert Orr, Miles W Carroll, Neil Blake, Julian A Hiscox iD

The Journal of Infectious Diseases · 2026

DOI: 10.1093/infdis/jiag308 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of Infectious Diseases, 2026. Verfasst von Jocelyn G Pérez und 11 weiteren Autor:innen. Beteiligte Einrichtung: School of Biodiversity, One Health and Veterinary Medicine, College of Medical, Veterinary and Life Sciences, University of Glasgow, Glasgow, United …. Hauptthemen laut MEDLINE: Hemorrhagic Fever, Ebola, Machine Learning, Ebolavirus. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fondo Nacional de Desarrollo Científico, Tecnológico y de Innovación Tecnológica, Consejo Nacional de Ciencia, Tecnología e Innovación, US Food and Drug Administration.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

In humans, Ebola virus disease (EVD) has a high mortality rate. While viral load is a known prognostic factor, it is not effective in predicting outcomes across all patients. Exploring host transcriptomic signatures may provide additional predictive value.

Methods

Here, the transcript abundance of 4 candidate host genes (VCAM1, TUBG1, MS4A4A, ISG15) was quantified by reverse transcription quantitative polymerase chain reaction (RT-qPCR) in blood samples from hospitalized patients with Ebola virus (EBOV) collected during the 2013–2016 West African outbreak. Samples were taken for diagnostic purposes during the acute phase of infection. Associations between target gene expression, viral load, and outcome (survival/death) were assessed, and machine learning models were trained and tested to predict patient outcome.

Results

EBOV cycle threshold (Ct) values were significantly higher in hospitalized survivors compared to fatalities. During the acute phase, the transcript abundance of VCAM1 and MS4A4A was higher in fatal cases, while TUBG1 expression was elevated in survivors; ISG15 expression did not differ by outcome. In support vector machine models, EBOV Ct alone classified patient outcomes with 86.9% accuracy, while MS4A4A alone reached 82.6%. Combining EBOV Ct with MS4A4A improved prediction to 91.3%. The best-performing model, integrating EBOV Ct, ISG15, and MS4A4A, achieved 100% accuracy in the test set.

Discussion

Host gene expression markers, particularly MS4A4A, in combination with viral load, improved outcome prediction in EVD beyond viral load alone in ambiguous cases with mid-range Ct values. These findings highlight the utility of host transcript-based assays to inform clinical management and for benchmarking the effectiveness of medical countermeasures during outbreaks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Hemorrhagic Fever, EbolaMachine LearningEbolavirusHumansViral LoadFemalePrognosisDisease OutbreaksMalePredictive Learning ModelsAdultGene Expression ProfilingTranscriptomeAfrica, Western

Stichwörter der Autor:innen

EBOVEVDEbola virusEbola virus diseasemachine learningmedical countermeasuretranscriptome

Autor:innen und Institutionen

  • School of Biodiversity, One Health and Veterinary Medicine, College of Medical, Veterinary and Life Sciences, University of Glasgow, Glasgow, United Kingdom.
  • Medical Research Council-University of Glasgow Centre for Virus Research, Glasgow, United Kingdom.
  • Institute of Infection, Veterinary and Ecological Science, Faculty of Health and Life Science, University of Liverpool, Liverpool, United Kingdom.
  • Bernhard Nocht Institute for Tropical Medicine, Hamburg, Germany.
  • A*STAR Infectious Diseases Labs, Singapore.
  • Liverpool School of Tropical Medicine, Liverpool, United Kingdom.

ORCID-Profile: Jocelyn G Pérez, Natasha Y Rickett, Stephan Günther, Romy Kerber, Tom Fletcher, Tracy MacGill, Julian A Hiscox

Förderung

  • Fondo Nacional de Desarrollo Científico, Tecnológico y de Innovación Tecnológica
  • Consejo Nacional de Ciencia, Tecnología e Innovación
  • US Food and Drug Administration
  • Pandemic Institute

Zitieren

APA

Pérez, J. G., Rickett, N. Y., Günther, S., Kerber, R., Ng, L. F. P., Fletcher, T., MacGill, T., Myers, T., Orr, R., Carroll, M. W., Blake, N., & Hiscox, J. A. (2026). Identification of Host Gene Transcripts by Machine Learning and Their Application to Predict Outcome in Ebola Virus Disease. The Journal of Infectious Diseases. https://doi.org/10.1093/infdis/jiag308

Vancouver

Pérez JG, Rickett NY, Günther S, Kerber R, Ng LFP, Fletcher T, et al. Identification of Host Gene Transcripts by Machine Learning and Their Application to Predict Outcome in Ebola Virus Disease. The Journal of Infectious Diseases. 2026. doi:10.1093/infdis/jiag308

BibTeX
@article{Prez2026,
  author = {Pérez, Jocelyn G and Rickett, Natasha Y and Günther, Stephan and Kerber, Romy and Ng, Lisa F P and Fletcher, Tom and MacGill, Tracy and Myers, Todd and Orr, Robert and Carroll, Miles W and Blake, Neil and Hiscox, Julian A},
  title = {Identification of Host Gene Transcripts by Machine Learning and Their Application to Predict Outcome in Ebola Virus Disease},
  journal = {The Journal of Infectious Diseases},
  year = {2026},
  doi = {10.1093/infdis/jiag308}
}
Kostenlos starten →