This challenge data includes 101,017 data points in total. Challenge participants are expected to use the training data to build a prediction model that can predict the solubility class in the test set. The predictors can be generated from embedding the SMILES and/or collected from public resources, such as https://ecbd.eu/.
An example predictor matrix generated using SMILES is shown in the example_predictors.csv. 

Solubility labels are provided for 70% of the data. The rest 30% of the data points are equally spilt for the public leaderboard and final evaluation. All splitings are conducted using stratified random sampling with the solubility category as the stratification factor.

## Files

*   **train.csv** - the training set
*   **test.csv** - the test set
*   **submission_template.csv** - a sample submission file in the correct format
*   **example_predictors** - an example predictors metrics generated from SMILES id, Note! Challenge participants are NOT REQUIRED to use this file.

## Columns

*   `Id` - ID column of the compoud
*   `smiles` - [Simplified Molecular Input Line Entry System](https://dev.drugbank.com/guides/terms/smiles)
*   `sol_category` Solubility categories from the experiments.