Risk Assessment of the Possible Intermediate Host Role of Pigs for Coronaviruses with a Deep Learning Predictor

Swine coronaviruses (CoVs) have been found to cause infection in humans, suggesting that Suiformes might be potential intermediate hosts CoV transmission from their natural humans. The present study aims establish convolutional neural network (CNN) models predict host adaptation of swine CoVs. Decomposing each ORF1ab and Spike sequence was performed with dinucleotide composition representation (DCR) other traits. relationship between CoVs different adaptive analyzed by unsupervised learning, CNN based on DCR were built the rationality verified phylogenetic analysis. Unsupervised learning showed there is a multiple According prediction models, acute diarrhea syndrome (SADS-CoV) porcine epidemic virus (PEDV) are adapted Chiroptera, transmissible gastroenteritis (TGEV) Carnivora, hemagglutinating encephalomyelitis (PHEV) Primate, Rodent, Lagomorpha, deltacoronavirus (PDCoV) Artiodactyla, Carnivora. In summary, trait has confirmed representative for genome, DCR-based deep model works well assess mammals. human mammalian provides novel approach risk humans mammals