**Molecular Properties Datasets**

ZINC is a widely utilized public access database and tool set, playing a crucial role in various applications including virtual screening, ligand discovery, pharmacophore screens, benchmarking, and force field development. The **MolProp250KLeadlike** dataset consists of 250,000 leadlike compounds randomly selected from ZINC25.

The ZINC22 is published in https://pubs.acs.org/doi/10.1021/acs.jcim.2c01253 and the dataset is downloaded from https://cartblanche22.docking.org \

To **maintain consistency** with other benchmarks in the Polaris Hub, a thorough data curation process is carried out to ensure the accuracy of molecular presentations.
Therefore, the raw data from the data resource is not used here. 

See more curation details in [03_ZINC22_250K_leadlike_curation.ipynb](https://github.com/polaris-hub/polaris-recipes/blob/mvp/02_MolProp/03_ZINC22_250K_leadlike_benchmark.ipynb)