PREDICTION OF SUPERCRITICAL CARBON-DIOXIDE SOLUBILITY OF ORGANIC-COMPOUNDS FROM MOLECULAR-STRUCTURE

A diverse data set of 58 compounds taken from the literature was used to create models for the prediction of the solubility of organic compo unds in supercritical carbon dioxide. Descriptors encoding information about the topological, geometric, and electronic properties of each c ompound in the data set were calculated from the molecular structures. A multiple linear regression model containing seven descriptors was g enerated. Several new descriptors, which were not present in the origi nal pool, were calculated. One of the new descriptors was used to crea te the final seven descriptor linear model, which had a better root me an square (rms) error than the original model. The seven descriptors t hat appeared in the final model were used to make a neural network mod el which had a significantly better rms error than the linear model.