Figure 1

Characterization of the training dataset (Dataset 1). (A) Phylogenetic characterization estimated based on maximum likelihood, and showing all the Coronaviruses genus. The tree was generated with IQ-TREE 1.5.5²¹ available at http://www.iqtree.org and visualized with FigTree 1.4.4²² available at http://tree.bio.ed.ac.uk/software/figtree/; (B) Two Dimensional PCA reduction with prototypes according to the different Coronaviruses genus; and (C) Two Dimensional PCA reduction with prototypes according to the different primary host. The different colours in (B) and (C) represents each group of genus or host class using the training data set (Dataset 1). For some hosts or even between the genus, we can observe some clouds of points concentrated, while in other conditions, as in bats, the samples are scattered in different positions of the graph.