Prediction and interpretation of the lipophilicity of small peptides

Peptide-based drug discovery has considerably expanded and solid in silico tools for the prediction of physico-chemical properties of peptides are urgently needed. In this work we tested some combinations of descriptors/algorithms to find the best model to predict $$\log D_{\text {oct}}$$logDoct of a series of peptides. To do that we evaluate the models statistical performances but also their skills in providing a reliable deconvolution of the balance of intermolecular forces governing the partitioning phenomenon. Results prove that a PLS model based on VolSurf+ descriptors is the best tool to predict $$\log D_{\text {oct}}$$logDoct of neutral and ionised peptides. The mechanistic interpretation also reveals that the inclusion in the chemical structure of a HBD group is more efficient in decreasing lipophilicity than the inclusion of a HBA group.