Biogen-rPPB

Dataset: Download it here.

Dataset description: 168 compounds with measured logarithm of the percentage unbound to rat plasma protein, released by Biogen.

Dataset preprocessing

• Download the original dataset from here, which contains 168 compounds with available measurements;
• Use RDKit to transform the SMILES to their canonical forms (most SMILES are already canonical.);

Reference

1. C. Fang, Y. Wang, R. Grater, S. Kapadnis, C. Black, P. Trapa, and S. Sciabola, Prospective validation of machine learning algorithms for absorption, distribution, metabolism, and excretion prediction: An industrial perspective, Journal of Chemical Information and Modeling 63, 3263 (2023).