Skip to main content
. 2022 Mar 7;14:10. doi: 10.1186/s13321-022-00590-y

Fig. 5.

Fig. 5

Cumulative histogram of the largest Tanimoto Similarity Coefficient for 200,000 molecules within the MolData dataset. More than 92% of the molecules have other similar molecules to them within the dataset with Tanimoto Coefficient of higher than 0.5, and more than 44% of the molecules for Coefficient of 0.7