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

Additional mammalian mechanisms for inhibiting viral RNA have been highlighted for 424 retroviruses with the actions of zinc-finger antiviral protein (ZAP) [81] . ZAP targets 425 CG dinucleotide sequences, and in vertebrate host cells with the CG suppression in host 426 genomes, this can serve as a mechanism for the distinction of self vs non-self RNA and 427 inhibitory consequences [81] . Coronaviruses have A/U rich and C/G poor genomes, 428 which over time may have been, in part, a product of cytidine deamination and 429 selection against CG dinucleotides [88] [89] [90] . This is consistent with the fact that bats 430 serve as a reservoir for many coronaviruses and that bats have been observed to have 431 some of the largest and most diverse arrays of APOBEC genes in mammals [66, 67] . The 432 Spearman's rank correlation data and the patterns observed in the CGR images from 433 Figure 4 , of the coronavirus genomes, including COVID-19 identify patterns such as CG 434 underepresentation, also present in vertebrate and, importantly, bat host genomes.