Challenge of Drug Solubility Prediction

AP ratio of aromatic to total number of heavy atoms 

COSMO-RS conductor-like screening model for realistic solvation 

Molecular Drug Properties. Measurement and Prediction. R. Mannhold (Ed.) Copyright 2008 Wiley-VCH Verlag GmbH Co. KGaA, Weinheim ISBN 978-3-527-31755-4 

Successful drugs with solubilities lower than 10 or lO molL, or in logarithmic units log Sw below -5 or -6, are rarely found, and so this may be viewed as a lower bound for promising drug candidates. On the other hand, almost all drugs have solubilities lower than O.lmolL , i.e. log Sw -1. Thus, the range of -6 log Sw -1 may be considered as the drug solubility window. 

---

I J 7 Challenge of Drug SolubilitY Prediction and as H-bond interactions ... 

In order to better understand some of the nuances associated with the construction and evaluation of predictive models, it is useful to consider actual examples. In this chapter, we will examine a number of datasets containing measured values for aqueous solubility and use these datasets to build and evaluate predictive models. Solubility in water or buffer is an important parameter in drug discovery [13]. Poorly soluble compounds tend to have poor pharmacokinetics and can precipitate or cause other problems in assays. As such, the prediction of aqueous solubility has been an area of high interest in the pharmaceutical industry. Over the last 15 years, numerous papers have been published on methods for predicting aqueous solubility [2, 3, 14]. Although many papers have been published and commercial software for predicting aqueous solubility has been released, reliable solubility prediction remains a challenge. 

---