Discovering knowledge hidden in a chemical database using a commercially available data mining tool

Describes DataMariner, a commercially available tool that is designed to facilitate the discovery of knowledge hidden in databases. The potential of the tool for scientific applications is illustrated via a case study. This is both the first application of this particular tool to a scientific domain and the first project to describe the application of data mining techniques to the analytical separation of a chemical mixture, known as an enantiomer pair, using Pirkle-type chiral stationary phases. DataMariner was successfully used to develop and validate rules for the domain of the case study. Although it is not easy to provide a justification for the rules by looking at them, the results suggest that they have a high degree of accuracy.