QSAR models for the human H(+)/peptide symporter, hPEPT1: affinity prediction using alignment-independent descriptors.

A data set comprising the major known chemical classes of hPEPT1 ligands was compiled from the literature. For these compounds, alignment-independent descriptors (VolSurf, GRIND/Almond, and MOE) were computed. Using hierarchical partial least-squares projection to latent structures (H-PLS), a one-component model with r2 = 0.77 and q2 = 0.75 was obtained. The model satisfied a set of rigorous validation criteria and performed well in the prediction of an external test set. Mechanistic interpretation of the model reveals polarity properties to be the dominant factors in determining hPEPT1 affinity, with hydrophobic interactions contributing to a lesser extent. The model is superior to previously reported models due to its combination of quality and speed. Accordingly, it is suitable for ligand-based virtual screening, such as QSAR-based database mining.