Solid dispersion is an effective way to improve the dissolution and oral bioavailability of water-insoluble drugs. In order to obtain an effective solid dispersion formulation, researchers need to evaluate a series of important properties of the designed formulation, including in vitro dissolution and physical stability of solid dispersion. Here, we developed a formulation prediction platform of solid dispersion: PharmSD. Based on the advanced machine learning algorithm, several key properties related with solid dispersion could be rapidly evaluated just by clicking mouse.
In the pharmaceutical field, about 40% of the drugs are insoluble in water, which limits their absorption. To solve this problem, researchers have tried many methods, such as micronization, cyclodextrin inclusion, solid dispersion and so on. PharmES is an online platform that can be used to predict the changes of binding free energy and solubility of drugs and excipients in different environments. PharmES has the latest and most comprehensive data. By using the state-of-art machine learning methods, a series of high-precision and robust machine learning models are constructed. By applying these models, researchers can design better drug formulations.