Table 1. Comparison of the Diversity of Different Data Sets, Showing the Range of Values Observed in the Data Setsa.
data set | N | log S | atoms | AromAtom | rings |
---|---|---|---|---|---|
ours | 17,149 | –17.5 to 1.7 | 1–273 | 0–64 | 0–33 |
Delaney50 | 1100 | –11.6 to 1.6 | 4–119 | 0–28 | 0–8 |
Tang18 | 1310 | –11.6 to 1.6 | 5–94 | 0–23 | 0–7 |
Cui38 | 9979 | –18.2 to 1.7 | 1–216 | 0–60 | 0–16 |
Boobier51 | 100 | –8.8 to 2.0 | 10–67 | 0–20 | 0–7 |
Huuskonen52 | 1011 | –11.6 to 1.6 | 5–94 | 0–23 | 0–7 |
Sol. Challenge 153 | 114 | –7.7 to −1.1 | 13–76 | 0–19 | 1–5 |
Sol. Challenge 2 SET139 | 100 | –6.8 to −1.2 | 15–196 | 0–26 | 1–7 |
Sol. Challenge 2 SET239 | 32 | –10.4 to −1.2 | 21–123 | 0–30 | 1–8 |
water set wide54 | 900 | –12.8 to 1.6 | 4–80 | 0–26 | 0–6 |
water set narrow54 | 560 | –4.0 to 1.0 | 4–61 | 0–17 | 0–6 |
Hou SET155,56 | 21 | –8.1 to 0.4 | 18–57 | 0–18 | 0–4 |
Hou SET255,57 | 120 | –10.4 to 1.0 | 6–57 | 0–18 | 0–5 |
Wang58 | 1640 | –11.6 to 1.6 | 4–119 | 0–28 | 0–8 |
N, log S, atoms, AromAtom, and rings refer to the number of molecules, log solubility (mol/L), number of atoms, number of aromatic atoms, and number of rings, respectively.