Skip to main content
. 2023 Feb 6;15:16. doi: 10.1186/s13321-023-00689-w

Fig. 3.

Fig. 3

Pairwise similarity distributions of (a) proteins and (b) compounds for “train vs. train”, “test vs. test”, and “train vs. test” samples in random-split, dissimilar-compound-split, and fully-dissimilar-split of the transferases dataset (shown in the logarithmic scale)