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

Classification using viral sequencing techniques is mainly based on alignment methods such as FASTA [13] and BLAST [14] . These methods rely on the 35 assumption that DNA sequences share common features, and their order prevails among different sequences [15, 16] . However, these methods suffer from the necessity of needing base sequences for the detection [17] . Nevertheless, it is necessary to develop innovative improved diagnostic tools that target the genome to improve the identification of pathogenic variants, as sometimes several tests, 40 are needed to have an accurate diagnosis. As an alternative deep learning methods have been suggested for classification of DNA sequences, as these methods 3 . CC-BY-NC 4.0 International license author/funder. It is made available under a The copyright holder for this preprint (which was not peer-reviewed) is the . https://doi.org/10.1101/2020.03.13.990242 doi: bioRxiv preprint In particular, for the case of viruses, Next Generation Sequencing (NGS) genomic samples might not be identified by BLAST, as there are no reference sequences valid for all genomes, as viruses have high mutation frequency [20] .