Fig. 1
From: Unsupervised explainable AI for molecular evolutionary study of forty thousand SARS-CoV-2 genomes
BLSOMs for 1 ~ 6-mers. BLSOMs were constructed for mono- to hexa-nucleotide compositions in 40,450 genome sequences. The total number of nodes was set to 1/20 of the total number of viral genomes. Grid points that include sequences from more than one clade are indicated in black, and those containing sequences from a single clade are indicated in a clade-specific color: G (
), GH (
), GR (
), L (
), S (
) and V (
). Grid points that include no sequences were left in blank (white). Sequences of the O clade (other and unclassified clades) were included in the BLSOM calculation but excluded from the final display; i.e., if a sequence belonging to the O clade is mixed with sequences belonging to a main clade, the node is colored according to the main clade