Table 3 Summary of datasets
From: A unified approach to inferring chemical compounds with the desired aqueous solubility
\(\mathcal {C}\) | \( |\mathcal {C}| \) | \( \underline{y},~\overline{y} \) | |D| |
|---|---|---|---|
Protac | 21 | \(-6.64,\,-3.18\) | 83 |
Wassvik | 26 | \(-8.49,\,-2.48\) | 94 |
Alex Manfred | 72 | \(-0.833,\,0.65\) | 163 |
Goodman | 87 | \(-6.74,\,-1.06\) | 130 |
D5 | 91 | \(-5.88,\,0.58\) | 118 |
Duffy | 98 | \(-10.32,\,-2.48\) | 139 |
Boobier | 99 | \(-8.8,\,1.7\) | 133 |
Dearden | 118 | \(-6.24,\,-0.57\) | 142 |
Ran | 129 | \(-10.8,\,2.06\) | 157 |
Llinas | 132 | \(-8.75,\,-1.18\) | 167 |
Bergstrom | 163 | \(-7.59,\,0.55\) | 154 |
Grigorev | 362 | \(-7.85,\,0.38\) | 173 |
Jain | 456 | \(-12.95,\,1.58\) | 223 |
Lovric | 805 | \(-8.75,\,1.149\) | 323 |
Huuskonen | 827 | \( -11.62,\,1.58\) | 310 |
David | 826 | \( -10.41,\,1.58\) | 263 |
Water set wide | 845 | \(-12.79,\,1.58\) | 320 |
Daniel | 915 | \(-10.43,\,6.4\) | 372 |
Esol | 1054 | \(-11.6,\,1.58\) | 338 |
Aqua | 1238 | \(-11.62,\,1.58\) | 364 |
Tang | 1221 | \(-1162,\,1.58\) | 364 |
Wang | 1414 | \(-9.33,\,1.58\) | 405 |
Phys | 1812 | \(-12.06,\,1.58\) | 469 |
Training set | 5315 | \(-13.17,\,2.89\) | 675 |
Ochem | 6006 | \(-12.1,\,1.58\) | 668 |
Cui | 6678 | \(-18.21,\,1.7\) | 766 |
Aqsol | 8230 | \(-13.17,\,2.13\) | 965 |
Charles N. Lowe | *9150 | \(-13.17,\,2.41\) | 835 |
Ademola | 10343 | \(-13.17,\,2.14\) | 949 |