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

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

  • Viruses. 2021 Apr 2;13(4):610. doi: 10.3390/v13040610.
Julia Werner 1,  Raphael M Kronberg 1 2,  Pawel Stachura 1,  Philipp N Ostermann 3,  Lisa Müller 3,  Heiner Schaal 3,  Sanil Bhatia 4,  Jakob N Kather 5,  Arndt Borkhardt 4,  Aleksandra A Pandyra 4,  Karl S Lang 6,  Philipp A Lang 1
Affiliations

Affiliations

  • 1 Department of Molecular Medicine II, Medical Faculty, Heinrich-Heine-University, 40225 Düsseldorf, Germany.
  • 2 Mathematical Modelling of Biological Systems, Heinrich-Heine-University, 40225 Düsseldorf, Germany.
  • 3 Institute of Virology, Medical Faculty, Heinrich-Heine-University, 40225 Düsseldorf, Germany.
  • 4 Department of Pediatric Oncology, Hematology and Clinical Immunology, Medical Faculty, Center of Child and Adolescent Health, Heinrich-Heine-University, 40225 Düsseldorf, Germany.
  • 5 Department of Medicine III, University Hospital RWTH Aachen, 52074 Aachen, Germany.
  • 6 Institute of Immunology, Medical Faculty, University of Duisburg-Essen, 45147 Essen, Germany.
PMID: 33918368 DOI: 10.3390/v13040610
Abstract

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.

Keywords

SARS-CoV-2; chloroquine; deep learning; deep transfer learning; drug screening; emetine; hydroxychloroquine; remdesivir.

Figures
Products