Skip to main content
. 2022 Aug 31;9:960194. doi: 10.3389/fmolb.2022.960194

FIGURE 1.

FIGURE 1

tSNE embedding of the sequence space covered by the datasets used in this study. 2,000 random sequences from the OAS dataset are added for comparison, with a lower opacity. Groups of nearby points represent similar sequences which are different from the others. However, larger distances between groups should not be over-interpreted.