AZ(AstraZeneca)-hPPB

Dataset: Download it here.

Dataset description: 1,614 compounds with measured logarithm of the percentage unbound to human plasma protein, deposited by AstraZeneca in ChEMBL.

Dataset preprocessing

• Extract the raw dataset from ChEMBL 34 using assay ID CHEMBL3301365;
• Convert the unit from percentage bound to \(\log_{10}\)-based percentage unbound;

Reference

1. M. Wenlock and N. Tomkinson, Experimental in vitro DMPK and physicochemical data on a set of publicly disclosed compounds.