Skip to main content
. 2020 Dec 22;10(73):45189–45198. doi: 10.1039/d0ra07820d

General information about the three databases.

Database Number of molecules Exact molecular mass Number of atoms Number of chiral centers Number of rings Number of bridgehead atoms Number of heterocycles
CheML 2 899 276 373 ± 213 26.3 ± 15 0.23 ± 0.60 2.55 ± 1.02 0.023 ± 0.248 1.18 ± 0.93
eMolecules 26 394 586 331 ± 87.7 22.8 ± 6.46 0.0944 ± 0.489 2.63 ± 1.16 0.036 ± 0.319 1.35 ± 0.97
ZINC 30 000 000 321 ± 24.5 22.7 ± 2.0 1.399 ± 1.017 2.55 ± 0.90 0.076 ± 0.391 1.72 ± 0.95
CheML JT-VAE 1 399 265 323 ± 55 22.7 ± 3.9 0.0 ± 0.0 2.69 ± 0.93 0.024 ± 0.25 1.41 ± 0.89
CheML RNN 962 245 475 ± 336 33.8 ± 23.8 0.30 ± 0.66 2.37 ± 1.12 0.0176 ± 0.23 0.80 ± 0.84
CheML GrammarVAE 239 206 326 ± 59 22.7 ± 4.25 0.86 ± 0.90 2.63 ± 0.93 0.0238 ± 0.247 1.37 ± 0.92
CheML ChemVAE 99 273 333 ± 63 22.9 ± 4.6 0.81 ± 0.9 2.72 ± 1.01 0.0540 ± 0.37 1.48 ± 0.95
CheML MolCycleGAN 60 856 330 ± 61 23.0 ± 4.4 0.94 ± 1.00 2.75 ± 0.98 0.0400 ± 0.32 1.45 ± 0.96
CheML ORGAN 50 262 273 ± 58 18.6 ± 4.1 0.28 ± 0.57 2.20 ± 0.75 0.029 ± 0.26 0.77 ± 0.72
CheML ORGANIC 42 609 222 ± 60 15.8 ± 4.39 0.74 ± 0.82 1.39 ± 0.58 0.0022 ± 0.068 0.46 ± 0.55
CheML SSVAE 42 606 355 ± 70 24.9 ± 4.8 0.0 ± 0.0 2.89 ± 0.92 0.034 ± 0.26 1.18 ± 0.87
CheML CDN 2415 385 ± 413 26.8 ± 27.8 0.44 ± 0.74 2.70 ± 1.28 0.167 ± 0.7 1.35 ± 1.07
CheML CVAE 539 304 ± 19 22.3 ± 1.48 0.87 ± 1.26 2.19 ± 0.52 0.0074 ± 0.122 0.69 ± 0.69