The optimization of aqueous solubility is an important step along the route to bringinga new therapeutic to market. We describe the development of an empirical computational modelto rank the pH-dependent aqueous solubility of drug candidates. The model consists of threecore components to describe aqueous solubility. The first is a multivariate QSAR model for theprediction of the intrinsic solubility of the neutral solute. The second facet of the approach is theconsideration of ionization using a predicted pKa and the Henderson-Hasselbalch equation.The third aspect of the model is a novel method for assessing the effects of crystal packing onsolubility through a series of short molecular dynamics simulations of an actual or hypotheticalsmall molecule crystal structure at escalating temperatures. The model also includes a MonteCarlo error function that considers the variability of each of the underlying components of themodel to estimate the 90% confidence interval of estimation.