Vorpal: A novel RNA virus feature-extraction algorithm demonstrated through interpretable genotype-to-phenotype linear models

Phillip Davis; John Bagnoli; David Yarmosh; Alan Shteyman; Lance Presser; Sharon Altmann; Shelton Bradrick; Joseph A. Russell

to estimate the probability of future events. Certain observations seen in the models thus far may 441 themselves be predictive of the respective phenotype before it is observed, rather than an effect 442 of it already having occurred. The primary example of this is the predictor identified in the 443 Orthocoronavirinae model. As described in the Methods section, certain assumptions were built 444 into labeling for the human-pathogen phenotype that incorporated theories about the zoonotic 445 provenance of SARS and Middle East Respiratory Syndrome-related (MERS) from civets and 446 camels respectively. Observing human-pathogen predictors occurring in SARS and MERS 447 viruses from non-human hosts could suggest the ability to predict the potential of a virus as a 448