W1_Data_acquisition_from_ChEMBL

Information on compound structure, bioactivity and associated targets is organized in databases such as ChEMBL, PubChem, or DrugBank. In order to acquire data for a query target (default target: EGFR), the following steps are conducted:

1.Get bioactivity (IC50) & compound (SMILES) data from ChEMBL target ID
2.Filter out entries with missing values & duplicates
3.Filter for entries with IC50 in molar units
4.Convert bioactivity to unit nM and pIC50

Author:
Dominique Sydow, Michele Wichmann, Jaime Rodríguez-Guerra, Daria Goldmann, Gregory Landrum, and Andrea Volkamer