A rapid, high-throughput, viral infectivity assay using automated brightfield microscopy with machine learning
SLAS Technology · 2023
DOI: 10.1016/j.slast.2023.07.003 ↗Kurz gefasst
Fachartikel in der Zeitschrift SLAS Technology, 2023. Verfasst von Rupert Dodkins und 10 weiteren Autor:innen. Beteiligte Einrichtung: ViQi Inc., Santa Barbara, CA, 93117, United States. Hauptthemen laut MEDLINE: Machine Learning, Microscopy, High-Throughput Screening Assays, Viruses. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 86 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: District of Columbia Developmental Center for AIDS Research, Concept Medical, National Science Foundation.
Abstract (Originalsprache)
Infectivity assays are essential for the development of viral vaccines, antiviral therapies, and the manufacture of biologicals. Traditionally, these assays take 2-7 days and require several manual processing steps after infection. We describe an automated viral infectivity assay (AVIATM), using convolutional neural networks (CNNs) and high-throughput brightfield microscopy on 96-well plates that can quantify infection phenotypes within hours, before they are manually visible, and without sample preparation. CNN models were trained on HIV, influenza A virus, coronavirus 229E, vaccinia viruses, poliovirus, and adenoviruses, which together span the four major categories of virus (DNA, RNA, enveloped, and non-enveloped). A sigmoidal function, fit between virus dilution curves and CNN predictions, results in sensitivity ranges comparable to or better than conventional plaque or TCID50 assays, and a precision of ∼10%, which is considerably better than conventional infectivity assays. Because this technology is based on sensitizing CNNs to specific phenotypes of infection, it has potential as a rapid, broad-spectrum tool for virus characterization, and potentially identification.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- ViQi Inc., Santa Barbara, CA, 93117, United States.
- Department of Biological Sciences North Carolina State University Raleigh, NC 27695, United States.
- College of Veterinary Medicine, Department of Population Health and Pathobiology, North Carolina State University, Raleigh, NC 27695, United States.
- Melbec Microbiology Ltd, Rossendale, Lancashire, BB4 4QJ, United Kingdom.
- ProBioGen AG, Goethestr. 54, 13086 Berlin, Germany.
- Department of Molecular Virology and Microbiology, Baylor College of Medicine, Houston, TX, United States.
Förderung
- District of Columbia Developmental Center for AIDS Research
- Concept Medical
- National Science Foundation
- National Science Foundation Directorate for Technology Innovation and Partnerships
Zitieren
APA
Dodkins, R., Delaney, J. R., Overton, T., Scholle, F., Frias-De-Diego, A., Crisci, E., Huq, N., Jordan, I., Kimata, J. T., Findley, T., & Goldberg, I. G. (2023). A rapid, high-throughput, viral infectivity assay using automated brightfield microscopy with machine learning. SLAS Technology. https://doi.org/10.1016/j.slast.2023.07.003
Vancouver
Dodkins R, Delaney JR, Overton T, Scholle F, Frias-De-Diego A, Crisci E, et al. A rapid, high-throughput, viral infectivity assay using automated brightfield microscopy with machine learning. SLAS Technology. 2023. doi:10.1016/j.slast.2023.07.003
BibTeX
@article{Dodkins2023,
author = {Dodkins, Rupert and Delaney, John R and Overton, Tess and Scholle, Frank and Frias-De-Diego, Alba and Crisci, Elisa and Huq, Nafisa and Jordan, Ingo and Kimata, Jason T and Findley, Teresa and Goldberg, Ilya G},
title = {A rapid, high-throughput, viral infectivity assay using automated brightfield microscopy with machine learning},
journal = {SLAS Technology},
year = {2023},
doi = {10.1016/j.slast.2023.07.003}
}
EUVIMED