Deep Transfer Learning Approach for Automatic Recognition of Drug Toxicity and Inhibition of SARS-CoV-2

Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) causes COVID-19 and is responsible for the ongoing pandemic. Screening of potential antiviral drugs against SARS-CoV-2 depend on in vitro experiments, which are based on the quantification of the virus titer. Here, we used virus-induced cy...

Full description

Bibliographic Details
Main Authors:	Julia Werner, Raphael M. Kronberg, Pawel Stachura, Philipp N. Ostermann, Lisa Müller, Heiner Schaal, Sanil Bhatia, Jakob N. Kather, Arndt Borkhardt, Aleksandra A. Pandyra, Karl S. Lang, Philipp A. Lang
Format:	Article
Language:	English
Published:	MDPI AG 2021-04-01
Series:	Viruses
Subjects:	SARS-CoV-2 deep transfer learning deep learning drug screening emetine chloroquine
Online Access:	https://www.mdpi.com/1999-4915/13/4/610

id	doaj-c9156f2121e14890942acc6d555a2bf0
record_format	Article
spelling	doaj-c9156f2121e14890942acc6d555a2bf02021-04-02T23:04:31ZengMDPI AGViruses1999-49152021-04-011361061010.3390/v13040610Deep Transfer Learning Approach for Automatic Recognition of Drug Toxicity and Inhibition of SARS-CoV-2Julia Werner0Raphael M. Kronberg1Pawel Stachura2Philipp N. Ostermann3Lisa Müller4Heiner Schaal5Sanil Bhatia6Jakob N. Kather7Arndt Borkhardt8Aleksandra A. Pandyra9Karl S. Lang10Philipp A. Lang11Department of Molecular Medicine II, Medical Faculty, Heinrich-Heine-University, 40225 Düsseldorf, GermanyDepartment of Molecular Medicine II, Medical Faculty, Heinrich-Heine-University, 40225 Düsseldorf, GermanyDepartment of Molecular Medicine II, Medical Faculty, Heinrich-Heine-University, 40225 Düsseldorf, GermanyInstitute of Virology, Medical Faculty, Heinrich-Heine-University, 40225 Düsseldorf, GermanyInstitute of Virology, Medical Faculty, Heinrich-Heine-University, 40225 Düsseldorf, GermanyInstitute of Virology, Medical Faculty, Heinrich-Heine-University, 40225 Düsseldorf, GermanyDepartment of Pediatric Oncology, Hematology and Clinical Immunology, Medical Faculty, Center of Child and Adolescent Health, Heinrich-Heine-University 40225 Düsseldorf, GermanyDepartment of Medicine III, University Hospital RWTH Aachen, 52074 Aachen, GermanyDepartment of Pediatric Oncology, Hematology and Clinical Immunology, Medical Faculty, Center of Child and Adolescent Health, Heinrich-Heine-University 40225 Düsseldorf, GermanyDepartment of Pediatric Oncology, Hematology and Clinical Immunology, Medical Faculty, Center of Child and Adolescent Health, Heinrich-Heine-University 40225 Düsseldorf, GermanyInstitute of Immunology, Medical Faculty, University of Duisburg-Essen 45147 Essen, GermanyDepartment of Molecular Medicine II, Medical Faculty, Heinrich-Heine-University, 40225 Düsseldorf, GermanySevere acute respiratory syndrome coronavirus-2 (SARS-CoV-2) causes COVID-19 and is responsible for the ongoing pandemic. Screening of potential antiviral drugs against SARS-CoV-2 depend on in vitro experiments, which are based on the quantification of the virus titer. Here, we used virus-induced cytopathic effects (CPE) in brightfield microscopy of SARS-CoV-2-infected monolayers to quantify the virus titer. Images were classified using deep transfer learning (DTL) that fine-tune the last layers of a pre-trained Resnet18 (ImageNet). To exclude toxic concentrations of potential drugs, the network was expanded to include a toxic score (TOX) that detected cell death (CPETOXnet). With this analytic tool, the inhibitory effects of chloroquine, hydroxychloroquine, remdesivir, and emetine were validated. Taken together we developed a simple method and provided open access implementation to quantify SARS-CoV-2 titers and drug toxicity in experimental settings, which may be adaptable to assays with other viruses. The quantification of virus titers from brightfield images could accelerate the experimental approach for antiviral testing.https://www.mdpi.com/1999-4915/13/4/610SARS-CoV-2deep transfer learningdeep learningdrug screeningemetinechloroquine
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Julia Werner Raphael M. Kronberg Pawel Stachura Philipp N. Ostermann Lisa Müller Heiner Schaal Sanil Bhatia Jakob N. Kather Arndt Borkhardt Aleksandra A. Pandyra Karl S. Lang Philipp A. Lang
spellingShingle	Julia Werner Raphael M. Kronberg Pawel Stachura Philipp N. Ostermann Lisa Müller Heiner Schaal Sanil Bhatia Jakob N. Kather Arndt Borkhardt Aleksandra A. Pandyra Karl S. Lang Philipp A. Lang Deep Transfer Learning Approach for Automatic Recognition of Drug Toxicity and Inhibition of SARS-CoV-2 Viruses SARS-CoV-2 deep transfer learning deep learning drug screening emetine chloroquine
author_facet	Julia Werner Raphael M. Kronberg Pawel Stachura Philipp N. Ostermann Lisa Müller Heiner Schaal Sanil Bhatia Jakob N. Kather Arndt Borkhardt Aleksandra A. Pandyra Karl S. Lang Philipp A. Lang
author_sort	Julia Werner
title	Deep Transfer Learning Approach for Automatic Recognition of Drug Toxicity and Inhibition of SARS-CoV-2
title_short	Deep Transfer Learning Approach for Automatic Recognition of Drug Toxicity and Inhibition of SARS-CoV-2
title_full	Deep Transfer Learning Approach for Automatic Recognition of Drug Toxicity and Inhibition of SARS-CoV-2
title_fullStr	Deep Transfer Learning Approach for Automatic Recognition of Drug Toxicity and Inhibition of SARS-CoV-2
title_full_unstemmed	Deep Transfer Learning Approach for Automatic Recognition of Drug Toxicity and Inhibition of SARS-CoV-2
title_sort	deep transfer learning approach for automatic recognition of drug toxicity and inhibition of sars-cov-2
publisher	MDPI AG
series	Viruses
issn	1999-4915
publishDate	2021-04-01
description	Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) causes COVID-19 and is responsible for the ongoing pandemic. Screening of potential antiviral drugs against SARS-CoV-2 depend on in vitro experiments, which are based on the quantification of the virus titer. Here, we used virus-induced cytopathic effects (CPE) in brightfield microscopy of SARS-CoV-2-infected monolayers to quantify the virus titer. Images were classified using deep transfer learning (DTL) that fine-tune the last layers of a pre-trained Resnet18 (ImageNet). To exclude toxic concentrations of potential drugs, the network was expanded to include a toxic score (TOX) that detected cell death (CPETOXnet). With this analytic tool, the inhibitory effects of chloroquine, hydroxychloroquine, remdesivir, and emetine were validated. Taken together we developed a simple method and provided open access implementation to quantify SARS-CoV-2 titers and drug toxicity in experimental settings, which may be adaptable to assays with other viruses. The quantification of virus titers from brightfield images could accelerate the experimental approach for antiviral testing.
topic	SARS-CoV-2 deep transfer learning deep learning drug screening emetine chloroquine
url	https://www.mdpi.com/1999-4915/13/4/610
work_keys_str_mv	AT juliawerner deeptransferlearningapproachforautomaticrecognitionofdrugtoxicityandinhibitionofsarscov2 AT raphaelmkronberg deeptransferlearningapproachforautomaticrecognitionofdrugtoxicityandinhibitionofsarscov2 AT pawelstachura deeptransferlearningapproachforautomaticrecognitionofdrugtoxicityandinhibitionofsarscov2 AT philippnostermann deeptransferlearningapproachforautomaticrecognitionofdrugtoxicityandinhibitionofsarscov2 AT lisamuller deeptransferlearningapproachforautomaticrecognitionofdrugtoxicityandinhibitionofsarscov2 AT heinerschaal deeptransferlearningapproachforautomaticrecognitionofdrugtoxicityandinhibitionofsarscov2 AT sanilbhatia deeptransferlearningapproachforautomaticrecognitionofdrugtoxicityandinhibitionofsarscov2 AT jakobnkather deeptransferlearningapproachforautomaticrecognitionofdrugtoxicityandinhibitionofsarscov2 AT arndtborkhardt deeptransferlearningapproachforautomaticrecognitionofdrugtoxicityandinhibitionofsarscov2 AT aleksandraapandyra deeptransferlearningapproachforautomaticrecognitionofdrugtoxicityandinhibitionofsarscov2 AT karlslang deeptransferlearningapproachforautomaticrecognitionofdrugtoxicityandinhibitionofsarscov2 AT philippalang deeptransferlearningapproachforautomaticrecognitionofdrugtoxicityandinhibitionofsarscov2
_version_	1721544549493374976

Deep Transfer Learning Approach for Automatic Recognition of Drug Toxicity and Inhibition of SARS-CoV-2

Similar Items