Novel methods for predicting logP, pKa, and logD values have been developed using data sets (592 moleculesfor logP and 1029 for pKa) containing a wide range of molecular structures. An equation with three molecularproperties (polarizability and partial atomic charges on nitrogen and oxygen) correlates highly with logP (r2= 0.89). The pKas are estimated for both acids and bases using a novel tree structured fingerprint describingthe ionizing centers. The new models have been compared with existing models and also experimentalmeasurements on test sets of common organic compounds and pharmaceutical molecules.