Fig. 5From: Organizing the bacterial annotation space with amino acid sequence embeddingsK-means clustering of unannotated Bacillus sequences embedded using a Protvec model trained with unannotated Bacillus sequences. Embedded sequences were grouped into 12 clusters and visualized using t-SNE. The 100 sequences closest to the centroid of each cluster are shown in separate colors and the centroid of each cluster is shown in blackBack to article page