Prediction of drug solubility from structure.

By W. L. Jorgensen, E. Duffy. 2002

738 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Computational Methods in Drug Discovery (2014, methodology): “Comprehensive software packages have been developed such as QikProp, which can be used to predict an array of ADMET-related properties such as solubility, membrane permeability, partition coefficients, bloodbrain barrier penetration, plasma protein binding, and the formation of metabolites (Jorgense”
Contribution of solid-state properties to the aqueous solubility of drugs. (2006, background): “Several of these models provide comparable outcomes, with an average prediction error of about 0.7–0.8 log units for a chemically diverse set of drugs (Bergström et al., 2004; Jorgensen and Duffy, 2002).”
Calculation of molecular lipophilicity: state of the art and comparison of methods on more than 96000 compounds (2009, methodology): “4 Å probe radius.(114) The recent parameters of QikProp were optimized using 500 drugs and related heterocyclic compounds and the model calculated an R(2) of 0.”
In silico prediction of aqueous solubility (2006, background): “Jorgensen and Duffy [37] have suggested that the average uncertainty in measured aqueous solubility values is probably no better than 0.”