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

These prior analyses relied upon alignment-based methods to identify relationships 265 between COVID-19 and other coronaviruses with nucleotide and amino acid sequence 266 similarities. When analyzing the conserved replicase domains of ORF1ab for 267 coronavirus species classification, nearly 94% of amino acid residues were identical to 268 SARS-CoV, yet overall genome similarity was only around 70%, confirming that 269 COVID-19 was genetically different [63] . Within the RdRp region, it was found that 270 another bat coronavirus, RaTG13, was the closest relative to COVID-19 and formed a 271 distinct lineage from other bat SARS-like coronaviruses [39, 41] . Other groups found 272 that two bat SARS-like coronaviruses, bat-SL-CoVZC45 and bat-SL-CoVZXC21, were 273 also closely related to COVID-19 [12, [34] [35] [36] [37] [38] . There is a consensus that these three bat 274 viruses are most similar to COVID-19, however, whether or not COVID-19 arose from a 275 recombination event is still unknown [39] [40] [41] . 276 Regardless of the stance on recombination, current consensus holds that the 277 hypothesis of COVID-19 originating from bats is highly likely. Bats have been identified 278 as a reservoir of mammalian viruses and cross-species transmission to other mammals, 279 including humans [4, 7, 8, 10, 13, [64] [65] [66] . Prior to intermediary cross-species infection, the 280 coronaviruses SARS-CoV and MERS-CoV were also thought to have originated in 281 bats [24, 25, 35, 68, 69] . Many novel SARS-like coronaviruses have been discovered in 282 bats across China, and even in European, African and other Asian countries [35, [70] [71] [72] [73] [74] [75] [76] . 283 With widespread geographic coverage, SARS-like coronaviruses have likely been present 284 in bats for a long period of time and novel strains of these coronaviruses can arise 285 through recombination [4] . Whether or not COVID-19 was transmitted directly from 286 bats, or from intermediary hosts, is still unknown, and will require identification of 287 COVID-19 in species other than humans, notably from the wet market and surrounding 288 area it is thought to have originated from [30] . While bats have been reported to have 289 been sold at the Huanan market, at this time, it is still unknown if there were 290 intermediary hosts involved prior to transmission to humans [27, 31, 34, 40, 77] . Snakes The copyright holder for this preprint (which was not peer-reviewed) is the . https://doi.org/10.1101/2020.02.03.932350 doi: bioRxiv preprint codon usage bias studies between viruses and their hosts [40] , however, this claim has 293 been disputed [78] . China CDC released information about environmental sampling in 294 the market and indicated that 33 of 585 samples had evidence of COVID-19, with 31 of 295 these positive samples taken from the location where wildlife booths were concentrated, 296 suggesting possible wildlife origin [79, 80] . Detection of SARS-CoV in Himalyan palm 297 civets and horseshoe bats identified 29 nucleotide sequences that helped trace the origins 298 of SARS-CoV isolates in humans to these intermediary species [13, 24, 39, 76] . Sampling 299 additional animals at the market and wildlife in the surrounding area may help elucidate 300 whether intermediary species were involved or not, as was possible with the SARS-CoV. 301 Viral outbreaks like COVID-19 demand timely analysis of genomic sequences to machine learning-based alignment-free method successfully us