Machine learning using intrinsic genomic signatures for rapid classification of novel pathogens: COVID-19 case study

Gurjit S. Randhawa; Maximillian P.M. Soltysiak; Hadi El Roz; Camila P.E. de Souza; Kathleen A. Hill; Lila Kari

With human-to-human transmission confirmed and concerns for possible 436 asymptomatic transmission, there is a strong need for continued intervention to prevent 437 the spread of the virus [33, 34, [61] [62] [63] . Due to the high amino acid similarities between 438 COVID-19 and SARS-CoV main protease essential for viral replication and processing, 439 anticoronaviral drugs targeting this protein and other potential drugs have been 440 identified using virtual docking to the protease for treatment of 441 COVID-19 [29, 44, 45, [91] [92] [93] [94] . The human ACE2 receptor has also been identified as the 442 potential receptor for COVID-19 and represents a potential target for treatment [42, 43] . 443 MLDSP-GUI is an ultra-fast, alignment-free method as is evidenced by the 444 time-performance of MLDSP-GUI for Test-1 to Test-6 given in Figure 7 . MLDSP-GUI 445 took just 10.55 seconds to compute a pairwise distance matrix (including reading 3273 complete genomes). All of the tests combined (Test-1 to Test-6) are doable in This study provides an alignment-free method based on intrinsic genomic signatures 456 that can deliver highly-accurate real-time taxonomic predictions of yet unclassified new 457 sequences, ab initio, using raw DNA sequence data alone and without the need for gene 458 or genome annotation. We use this method to provide evidence for the taxonomic correlation coefficient analyses. This study suggests that such alignment-free approaches 465 to comparative genomics can be used to complement alignment-based approaches when 466 timely taxonomic classification is of the essence, such as at critical periods during novel 467 viral outbreaks.