ESOL (delaney) is a standard regression dataset containing structures and water solubility data for 1128 compounds. The dataset is widely used to validate machine learning models on estimating solubility directly from molecular structures (as encoded in SMILES strings).
Reference:
Delaney, John S. "ESOL: estimating aqueous solubility directly from molecular structure." Journal of chemical information and computer sciences 44.3 (2004): 1000-1005.
File descriptions
delaney-processed.csv
- the data set for training
test.csv
- the test set
Data fields
The delaney-processed data file contains a csv table, in which columns below are used:>
smiles
- SMILES representation of the molecular structure
measured log solubility in mols per litre
- Log-scale water solubility of the compound, used as label [log(mol/L)]
The test data file contains only one column, for which you are required to predict the solubility:
smiles
- SMILES representation of the molecular structure