A web-based artificial intelligence system for label-free virus classification and detection of cytopathic effects

Abstract Identifying viral replication within cells demands labor-intensive isolation methods, requiring specialized personnel and additional confirmatory tests. To facilitate this process, we developed an AI-powered automated system called AI Recognition of Viral CPE (AIRVIC), specifically designed...

Full description

Saved in:
Bibliographic Details
Main Authors: Zeynep Akkutay-Yoldar, Mehmet Türkay Yoldar, Yiğit Burak Akkaş, Sibel Şurak, Furkan Garip, Oğuzcan Turan, Bengisu Ekizoğlu, Osman Can Yüca, Aykut Özkul, Barış Ünver
Format: Article
Language:English
Published: Nature Portfolio 2025-02-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-89639-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849715768822857728
author Zeynep Akkutay-Yoldar
Mehmet Türkay Yoldar
Yiğit Burak Akkaş
Sibel Şurak
Furkan Garip
Oğuzcan Turan
Bengisu Ekizoğlu
Osman Can Yüca
Aykut Özkul
Barış Ünver
author_facet Zeynep Akkutay-Yoldar
Mehmet Türkay Yoldar
Yiğit Burak Akkaş
Sibel Şurak
Furkan Garip
Oğuzcan Turan
Bengisu Ekizoğlu
Osman Can Yüca
Aykut Özkul
Barış Ünver
author_sort Zeynep Akkutay-Yoldar
collection DOAJ
description Abstract Identifying viral replication within cells demands labor-intensive isolation methods, requiring specialized personnel and additional confirmatory tests. To facilitate this process, we developed an AI-powered automated system called AI Recognition of Viral CPE (AIRVIC), specifically designed to detect and classify label-free cytopathic effects (CPEs) induced by SARS-CoV-2, BAdV-1, BPIV3, BoAHV-1, and two strains of BoGHV-4 in Vero and MDBK cell lines. AIRVIC utilizes convolutional neural networks, with ResNet50 as the primary architecture, trained on 40,369 microscopy images at various magnifications. AIRVIC demonstrated strong CPE detection, achieving 100% accuracy for the BoGHV-4 DN-599 strain in MDBK cells, the highest among tested strains. In contrast, the BoGHV-4 MOVAR 33/63 strain in Vero cells showed a lower accuracy of 87.99%, the lowest among all models tested. For virus classification, a multi-class accuracy of 87.61% was achieved for bovine viruses in MDBK cells; however, it dropped to 63.44% when the virus was identified without specifying the cell line. To the best of our knowledge, this is the first research article published in English to utilize AI for distinguishing animal virus infections in cell culture. AIRVIC’s hierarchical structure highlights its adaptability to virological diagnostics, providing unbiased infectivity scoring and facilitating viral isolation and antiviral efficacy testing. Additionally, AIRVIC is accessible as a web-based platform, allowing global researchers to leverage its capabilities in viral diagnostics and beyond.
format Article
id doaj-art-004e3dbdbc404c2f8caab264f07071ae
institution DOAJ
issn 2045-2322
language English
publishDate 2025-02-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-004e3dbdbc404c2f8caab264f07071ae2025-08-20T03:13:12ZengNature PortfolioScientific Reports2045-23222025-02-0115111510.1038/s41598-025-89639-0A web-based artificial intelligence system for label-free virus classification and detection of cytopathic effectsZeynep Akkutay-Yoldar0Mehmet Türkay Yoldar1Yiğit Burak Akkaş2Sibel Şurak3Furkan Garip4Oğuzcan Turan5Bengisu Ekizoğlu6Osman Can Yüca7Aykut Özkul8Barış Ünver9Department of Virology, Faculty of Veterinary Medicine, Ankara UniversityTURK AI Artificial Intelligence Information and Software Systems, Bilkent CyberparkTURK AI Artificial Intelligence Information and Software Systems, Bilkent CyberparkGraduate School of Health Sciences, Ankara UniversityGraduate School of Health Sciences, Ankara UniversityTURK AI Artificial Intelligence Information and Software Systems, Bilkent CyberparkTURK AI Artificial Intelligence Information and Software Systems, Bilkent CyberparkTURK AI Artificial Intelligence Information and Software Systems, Bilkent CyberparkDepartment of Virology, Faculty of Veterinary Medicine, Ankara UniversityTURK AI Artificial Intelligence Information and Software Systems, Bilkent CyberparkAbstract Identifying viral replication within cells demands labor-intensive isolation methods, requiring specialized personnel and additional confirmatory tests. To facilitate this process, we developed an AI-powered automated system called AI Recognition of Viral CPE (AIRVIC), specifically designed to detect and classify label-free cytopathic effects (CPEs) induced by SARS-CoV-2, BAdV-1, BPIV3, BoAHV-1, and two strains of BoGHV-4 in Vero and MDBK cell lines. AIRVIC utilizes convolutional neural networks, with ResNet50 as the primary architecture, trained on 40,369 microscopy images at various magnifications. AIRVIC demonstrated strong CPE detection, achieving 100% accuracy for the BoGHV-4 DN-599 strain in MDBK cells, the highest among tested strains. In contrast, the BoGHV-4 MOVAR 33/63 strain in Vero cells showed a lower accuracy of 87.99%, the lowest among all models tested. For virus classification, a multi-class accuracy of 87.61% was achieved for bovine viruses in MDBK cells; however, it dropped to 63.44% when the virus was identified without specifying the cell line. To the best of our knowledge, this is the first research article published in English to utilize AI for distinguishing animal virus infections in cell culture. AIRVIC’s hierarchical structure highlights its adaptability to virological diagnostics, providing unbiased infectivity scoring and facilitating viral isolation and antiviral efficacy testing. Additionally, AIRVIC is accessible as a web-based platform, allowing global researchers to leverage its capabilities in viral diagnostics and beyond.https://doi.org/10.1038/s41598-025-89639-0BoAHV-1BoGHV-4BPIV3BAdV-1CPEDeep learning
spellingShingle Zeynep Akkutay-Yoldar
Mehmet Türkay Yoldar
Yiğit Burak Akkaş
Sibel Şurak
Furkan Garip
Oğuzcan Turan
Bengisu Ekizoğlu
Osman Can Yüca
Aykut Özkul
Barış Ünver
A web-based artificial intelligence system for label-free virus classification and detection of cytopathic effects
Scientific Reports
BoAHV-1
BoGHV-4
BPIV3
BAdV-1
CPE
Deep learning
title A web-based artificial intelligence system for label-free virus classification and detection of cytopathic effects
title_full A web-based artificial intelligence system for label-free virus classification and detection of cytopathic effects
title_fullStr A web-based artificial intelligence system for label-free virus classification and detection of cytopathic effects
title_full_unstemmed A web-based artificial intelligence system for label-free virus classification and detection of cytopathic effects
title_short A web-based artificial intelligence system for label-free virus classification and detection of cytopathic effects
title_sort web based artificial intelligence system for label free virus classification and detection of cytopathic effects
topic BoAHV-1
BoGHV-4
BPIV3
BAdV-1
CPE
Deep learning
url https://doi.org/10.1038/s41598-025-89639-0
work_keys_str_mv AT zeynepakkutayyoldar awebbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT mehmetturkayyoldar awebbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT yigitburakakkas awebbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT sibelsurak awebbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT furkangarip awebbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT oguzcanturan awebbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT bengisuekizoglu awebbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT osmancanyuca awebbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT aykutozkul awebbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT barısunver awebbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT zeynepakkutayyoldar webbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT mehmetturkayyoldar webbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT yigitburakakkas webbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT sibelsurak webbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT furkangarip webbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT oguzcanturan webbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT bengisuekizoglu webbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT osmancanyuca webbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT aykutozkul webbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects
AT barısunver webbasedartificialintelligencesystemforlabelfreevirusclassificationanddetectionofcytopathiceffects