Classification and specific primer design for accurate detection of SARS-CoV-2 using deep learning
| Autor: | Lopez-Rincon, Alejandro, Tonda, Alberto, Mendoza-Maldonado, Lucero, Mulders, Daphne G J C, Molenkamp, Richard, Perez-Romero, Carmina A, Claassen, Eric, Garssen, Johan, Kraneveld, Aletta D, Afd Pharmacology, Pharmacology |
|---|---|
| Přispěvatelé: | Virology, Utrecht University [Utrecht], Mathématiques et Informatique Appliquées (MIA-Paris), Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-AgroParisTech-Université Paris-Saclay, Nuevo Hospital Civil de Guadalajara 'Dr. Juan I. Menchaca', Erasmus University Medical Center [Rotterdam] (Erasmus MC), Universidad Central de Queretaro (UNICEQ), Vrije Universiteit Amsterdam [Amsterdam] (VU), Danone Nutricia Research [Utrecht], Afd Pharmacology, Pharmacology, Athena Institute, APH - Global Health |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
0301 basic medicine
Computer science Classification and taxonomy Science Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) Genomics Computational biology Machine learning computer.software_genre medicine.disease_cause Convolutional neural network Genome Polymerase Chain Reaction Virus Article Set (abstract data type) 03 medical and health sciences 0302 clinical medicine Deep Learning SDG 17 - Partnerships for the Goals [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] SDG 3 - Good Health and Well-being Limit of Detection medicine 030212 general & internal medicine General Coronavirus DNA Primers Multidisciplinary business.industry SARS-CoV-2 Deep learning 030104 developmental biology Viral infection Specific primers [SDV.MP.VIR]Life Sciences [q-bio]/Microbiology and Parasitology/Virology Medicine Artificial intelligence Primer (molecular biology) [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM] business computer Classifier (UML) |
| Zdroj: | Scientific Reports, 11(1):947. Nature Publishing Group Scientific Reports Lopez-Rincon, A, Tonda, A, Mendoza-Maldonado, L, Mulders, D G J C, Molenkamp, R, Perez-Romero, C A, Claassen, E, Garssen, J & Kraneveld, A D 2021, ' Classification and specific primer design for accurate detection of SARS-CoV-2 using deep learning ', Scientific Reports, vol. 11, no. 1, 947 . https://doi.org/10.1038/s41598-020-80363-5 Scientific Reports, Nature Publishing Group, 2021, 11, pp.947. ⟨10.1038/s41598-020-80363-5⟩ Scientific Reports, 11(1), 1. NLM (Medline) Scientific Reports, Vol 11, Iss 1, Pp 1-11 (2021) |
| ISSN: | 2045-2322 |
| DOI: | 10.1038/s41598-020-80363-5 |
| Popis: | In this paper, deep learning is coupled with explainable artificial intelligence techniques for the discovery of representative genomic sequences in SARS-CoV-2. A convolutional neural network classifier is first trained on 553 sequences from available repositories, separating the genome of different virus strains from the Coronavirus family with considerable accuracy. The network’s behavior is then analyzed, to discover sequences used by the model to identify SARS-CoV-2, ultimately uncovering sequences exclusive to it. The discovered sequences are first validated on samples from other repositories, and proven able to separate SARS-CoV-2 from different virus strains with near-perfect accuracy. Next, one of the sequences is selected to generate a primer set, and tested against other state-of-the-art primer sets on existing datasets, obtaining competitive results. Finally, the primer is synthesized and tested on patient samples (n=6 previously tested positive), delivering a sensibility similar to routine diagnostic methods, and 100% specificity. In this paper, deep learning is coupled with explainable artificial intelligence techniques for the discovery of representative genomic sequences in SARS-CoV-2. A convolutional neural network classifier is first trained on 553 sequences from NGDC, separating the genome of different virus strains from the Coronavirus family with accuracy 98.73%. The network’s behavior is then analyzed, to discover sequences used by the model to identify SARS-CoV-2, ultimately uncovering sequences exclusive to it. The discovered sequences are validated on samples from NCBI and GISAID, and proven able to separate SARS-CoV-2 from different virus strains with near-perfect accuracy. Next, one of the sequences is selected to generate a primer set, and tested against other state-of-the-art primer sets, obtaining competitive results. Finally, the primer is synthesized and tested on patient samples (n=6 previously tested positive), delivering a sensibility similar to routine diagnostic methods, and 100% specificity. The proposed methodology has a substantial added value over existing methods, as it is able to both identify promising primer sets for a virus from a limited amount of data, and deliver effective results in a minimal amount of time. Considering the possibility of future pandemics, these characteristics are invaluable to promptly create specific detection methods for diagnostics. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|