Abstract

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 the National Genomics Data Center repository, separating the genome of different virus strains from the Coronavirus family with 98.73% 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 validated on samples from the National Center for Biotechnology Information and Global Initiative on Sharing All Influenza Data repositories, and are proven to be 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 sensitivity 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 automatically 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.

Highlights

  • In this paper, deep learning is coupled with explainable artificial intelligence techniques for the discovery of representative genomic sequences in SARS-CoV-2

  • The trained Convolutional Neural Networks (CNN) described in the “Methods” section obtained a mean accuracy of 98.73% in a 10-fold stratified cross-validation

  • For the in-silico analysis of specificity, we compared all the primers sets’ sequences with the National Center for Biotechnology Information (NCBI)-B and National Genomics Data Center (NGDC) dataset, and the results show that HKU-N-F, HKU-N-R, ChariteE-F, Charite-E-R and US-CDC-N2-F are not specific to SARS-CoV-2, as they bind to SARS-CoV, too

Read more

Summary

Introduction

Deep learning is coupled with explainable artificial intelligence techniques for the discovery of representative genomic sequences in SARS-CoV-2. In the specific case of SARS-CoV-2, RT-qPCR testing using primers in ORF1ab and N genes have been used to identified the infection in h­ umans[5] This method has come into question; Yang et al in a study from 866 respiratory specimens showed that for 0–7 days after onset of illness, the sputum samples had a negative rate of 11.1% in severe and 17.8% in mild cases, follow by 26.7% and 27.0% in nasal swabs and 40% and 38.7% for throat s­ wabs[6]. Diagnostic tools combining computed tomography (CT) scans with deep learning have been proposed, achieving an improved detection accuracy of 82.9%15 Another solution being used for studying SARS-CoV-2, is sequencing of the viral complementary DNA (cDNA). We can use this sequencing data with cDNA, resulting from the PCR of the original viral RNA; e.g. Real-Time PCR amplicons to identify the SARS-CoV-216

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call