A versatile automated pipeline for quantifying virus infectivity by label-free light microscopy and artificial intelligence.

Autor: Petkidis A; Department of Molecular Life Sciences, University of Zürich, Winterthurerstrasse 190, 8057, Zürich, Switzerland.; Life Science Zurich Graduate School, ETH and University of Zürich, 8057, Zurich, Switzerland., Andriasyan V; Department of Molecular Life Sciences, University of Zürich, Winterthurerstrasse 190, 8057, Zürich, Switzerland., Murer L; Department of Molecular Life Sciences, University of Zürich, Winterthurerstrasse 190, 8057, Zürich, Switzerland.; Roche Diagnostics, Forrenstrasse 2, 6343, Rotkreuz, Switzerland., Volle R; Department of Molecular Life Sciences, University of Zürich, Winterthurerstrasse 190, 8057, Zürich, Switzerland., Greber UF; Department of Molecular Life Sciences, University of Zürich, Winterthurerstrasse 190, 8057, Zürich, Switzerland. urs.greber@mls.uzh.ch.
Jazyk: angličtina
Zdroj: Nature communications [Nat Commun] 2024 Jun 15; Vol. 15 (1), pp. 5112. Date of Electronic Publication: 2024 Jun 15.
DOI: 10.1038/s41467-024-49444-1
Abstrakt: Virus infectivity is traditionally determined by endpoint titration in cell cultures, and requires complex processing steps and human annotation. Here we developed an artificial intelligence (AI)-powered automated framework for ready detection of virus-induced cytopathic effect (DVICE). DVICE uses the convolutional neural network EfficientNet-B0 and transmitted light microscopy images of infected cell cultures, including coronavirus, influenza virus, rhinovirus, herpes simplex virus, vaccinia virus, and adenovirus. DVICE robustly measures virus-induced cytopathic effects (CPE), as shown by class activation mapping. Leave-one-out cross-validation in different cell types demonstrates high accuracy for different viruses, including SARS-CoV-2 in human saliva. Strikingly, DVICE exhibits virus class specificity, as shown with adenovirus, herpesvirus, rhinovirus, vaccinia virus, and SARS-CoV-2. In sum, DVICE provides unbiased infectivity scores of infectious agents causing CPE, and can be adapted to laboratory diagnostics, drug screening, serum neutralization or clinical samples.
(© 2024. The Author(s).)
Databáze: MEDLINE