Computational models that predict PK properties, such as those related to drug absorption, metabolism, distribution, and excretion, are critical to flagging drug candidates with poor PK profiles that emerge as hits in high-throughput screening campaigns. To support the development of reliable computational models to predict key PK properties, we collected, curated, and integrated a database of compounds tested in 13 major PK endpoints containing over 10,000 unique molecules. We built classification quantitative structure-activity relationship (QSAR) models for all but one endpoint (Cmax) following best practices of model development and validation. Those with acceptable external accuracy (CCR ≥ 0.60 and SE, PPV, SP, and NPV ≥ 0.50) include hepatic stability at 15, 30, and 60 minutes, hepatic half-life at the subcellular and tissue levels, renal clearance, blood brain barrier permeability, CNS activity, Caco-2 permeability, plasma protein binding, plasma half-life, microsomal intrinsic clearance, and oral bioavailability. As a case study to illustrate model utility, we employed all developed models to predict the PK properties of all compounds in DrugBank. We also predicted PK properties of molecules hitting popular drug targets among several organs SLC6A4 (brain), ADRB2 (heart and lungs), HMGCR (liver), and CaSR (kidneys) only. These analyses revealed that nearly all experimental, investigational, and withdrawn compounds included in DrugBank are hepatically stable at 60 minutes and under, exhibit CNS activity, and permeate the Caco-2 cell line (a measure of intestinal absorption). Furthermore, our results indicate that compounds targeting different organs have distinct predicted PK profiles. This observation suggests that desired PK properties depend on compound’s indication. All models described in this paper have been integrated and made publicly available via the novel predictor of pharmacokinetic properties (PhaKinPro) web portal that can be accessed at https://phakinpro.mml.unc.edu/.