Accurate Identification of SARS-CoV-2 from Viral Genome Sequences using Deep Learning

Alejandro Lopez-Rincon; Alberto Tonda; Lucero Mendoza-Maldonado; Eric Claassen; Johan Garssen; Aletta D. Kraneveld

As of March 6 th of 2020, the new SARS-CoV-2 has 98,192 confirmed cases 20 across 88 countries, with 17,481 cases outside of China [7] . In addition, SARS-CoV-2 has an estimated mortality rate of 3-4%, and it is spreading faster than SARS-CoV and MERS-CoV [8] . SARS-CoV-2 assays can yield false positives if they are not targeted specifically to SARS-CoV-2, as the virus is closely related to other Coronavirus organisms. In addition, SARS-CoV-2 may present 25 with other respiratory infections, which make it even more difficult to identify [9, 10] . Thus, it is fundamental to improve existing diagnostic tools to contain the spread. For example, diagnostic tools combining computed tomography (CT) scans with deep learning have been proposed, achieving an improved detection accuracy of 82.9% [11] . Another solution for identifying SARS-CoV-2 30 is additional sequencing of the viral complementary DNA (cDNA). We can use sequencing data with cDNA, resulting from the PCR of the original viral RNA; e,g, Real-Time PCR amplicons ( Fig. 1 ) to identify the SARS-CoV-2 [12] .