Microscopy deep learning predicts virus infections and reveals mechanics of lytic-infected cells
Summary: Imaging across scales reveals disease mechanisms in organisms, tissues, and cells. Yet, particular infection phenotypes, such as virus-induced cell lysis, have remained difficult to study. Here, we developed imaging modalities and deep learning procedures to identify herpesvirus and adenovi...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-06-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004221005113 |
| _version_ | 1819156147637059584 |
|---|---|
| author | Vardan Andriasyan Artur Yakimovich Anthony Petkidis Fanny Georgi Robert Witte Daniel Puntener Urs F. Greber |
| author_facet | Vardan Andriasyan Artur Yakimovich Anthony Petkidis Fanny Georgi Robert Witte Daniel Puntener Urs F. Greber |
| author_sort | Vardan Andriasyan |
| collection | DOAJ |
| description | Summary: Imaging across scales reveals disease mechanisms in organisms, tissues, and cells. Yet, particular infection phenotypes, such as virus-induced cell lysis, have remained difficult to study. Here, we developed imaging modalities and deep learning procedures to identify herpesvirus and adenovirus (AdV) infected cells without virus-specific stainings. Fluorescence microscopy of vital DNA-dyes and live-cell imaging revealed learnable virus-specific nuclear patterns transferable to related viruses of the same family. Deep learning predicted two major AdV infection outcomes, non-lytic (nonspreading) and lytic (spreading) infections, up to about 20 hr prior to cell lysis. Using these predictive algorithms, lytic and non-lytic nuclei had the same levels of green fluorescent protein (GFP)-tagged virion proteins but lytic nuclei enriched the virion proteins faster, and collapsed more extensively upon laser-rupture than non-lytic nuclei, revealing impaired mechanical properties of lytic nuclei. Our algorithms may be used to infer infection phenotypes of emerging viruses, enhance single cell biology, and facilitate differential diagnosis of non-lytic and lytic infections. |
| first_indexed | 2024-12-22T15:48:15Z |
| format | Article |
| id | doaj.art-2642241825d0412abb91c66c05245b80 |
| institution | Directory Open Access Journal |
| issn | 2589-0042 |
| language | English |
| last_indexed | 2024-12-22T15:48:15Z |
| publishDate | 2021-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | iScience |
| spelling | doaj.art-2642241825d0412abb91c66c05245b802022-12-21T18:20:58ZengElsevieriScience2589-00422021-06-01246102543Microscopy deep learning predicts virus infections and reveals mechanics of lytic-infected cellsVardan Andriasyan0Artur Yakimovich1Anthony Petkidis2Fanny Georgi3Robert Witte4Daniel Puntener5Urs F. Greber6Department of Molecular Life Sciences, University of Zürich, Zürich 8057, SwitzerlandDepartment of Molecular Life Sciences, University of Zürich, Zürich 8057, Switzerland; University College London, London WC1E 6BT, UK; Artificial Intelligence for Life Sciences CIC, London N8 7FJ, UKDepartment of Molecular Life Sciences, University of Zürich, Zürich 8057, SwitzerlandDepartment of Molecular Life Sciences, University of Zürich, Zürich 8057, SwitzerlandDepartment of Molecular Life Sciences, University of Zürich, Zürich 8057, SwitzerlandDepartment of Molecular Life Sciences, University of Zürich, Zürich 8057, Switzerland; Roche Diagnostics International Ltd, Rotkreuz 6343, SwitzerlandDepartment of Molecular Life Sciences, University of Zürich, Zürich 8057, Switzerland; Corresponding authorSummary: Imaging across scales reveals disease mechanisms in organisms, tissues, and cells. Yet, particular infection phenotypes, such as virus-induced cell lysis, have remained difficult to study. Here, we developed imaging modalities and deep learning procedures to identify herpesvirus and adenovirus (AdV) infected cells without virus-specific stainings. Fluorescence microscopy of vital DNA-dyes and live-cell imaging revealed learnable virus-specific nuclear patterns transferable to related viruses of the same family. Deep learning predicted two major AdV infection outcomes, non-lytic (nonspreading) and lytic (spreading) infections, up to about 20 hr prior to cell lysis. Using these predictive algorithms, lytic and non-lytic nuclei had the same levels of green fluorescent protein (GFP)-tagged virion proteins but lytic nuclei enriched the virion proteins faster, and collapsed more extensively upon laser-rupture than non-lytic nuclei, revealing impaired mechanical properties of lytic nuclei. Our algorithms may be used to infer infection phenotypes of emerging viruses, enhance single cell biology, and facilitate differential diagnosis of non-lytic and lytic infections.http://www.sciencedirect.com/science/article/pii/S2589004221005113VirologyMachine learning |
| spellingShingle | Vardan Andriasyan Artur Yakimovich Anthony Petkidis Fanny Georgi Robert Witte Daniel Puntener Urs F. Greber Microscopy deep learning predicts virus infections and reveals mechanics of lytic-infected cells iScience Virology Machine learning |
| title | Microscopy deep learning predicts virus infections and reveals mechanics of lytic-infected cells |
| title_full | Microscopy deep learning predicts virus infections and reveals mechanics of lytic-infected cells |
| title_fullStr | Microscopy deep learning predicts virus infections and reveals mechanics of lytic-infected cells |
| title_full_unstemmed | Microscopy deep learning predicts virus infections and reveals mechanics of lytic-infected cells |
| title_short | Microscopy deep learning predicts virus infections and reveals mechanics of lytic-infected cells |
| title_sort | microscopy deep learning predicts virus infections and reveals mechanics of lytic infected cells |
| topic | Virology Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2589004221005113 |
| work_keys_str_mv | AT vardanandriasyan microscopydeeplearningpredictsvirusinfectionsandrevealsmechanicsoflyticinfectedcells AT arturyakimovich microscopydeeplearningpredictsvirusinfectionsandrevealsmechanicsoflyticinfectedcells AT anthonypetkidis microscopydeeplearningpredictsvirusinfectionsandrevealsmechanicsoflyticinfectedcells AT fannygeorgi microscopydeeplearningpredictsvirusinfectionsandrevealsmechanicsoflyticinfectedcells AT robertwitte microscopydeeplearningpredictsvirusinfectionsandrevealsmechanicsoflyticinfectedcells AT danielpuntener microscopydeeplearningpredictsvirusinfectionsandrevealsmechanicsoflyticinfectedcells AT ursfgreber microscopydeeplearningpredictsvirusinfectionsandrevealsmechanicsoflyticinfectedcells |