In many branches of science and industry today institutions gather more data than they can digest. This simple fact is the driving force behind a new hybrid research field called data mining or knowledge discovery in databases (KDD). Data mining combines techniques from statistics, databases, computer graphics, and artificial intelligence to increase the digestive capacities of more traditional data analysis tools and the humans using them.

A promising sector for applying data mining is the pharmaceutical sector. The development of new drugs is a very data-intensive process and can potentially be sped up importantly by incorporating data mining techniques into it. Unfortunately, the data mining tasks considered here are very complex and often beyond the reach of current data mining technology.

This text reports on two things: first, the authors' recent data mining research (more specifically on relational data mining) that has advanced the state of the art of current data mining technology to the extent that the above described tasks could be performed; and second, their current project to start up a spin-off company of the K.U.Leuven that will develop software for the pharmaceutical sector based on these research results, thereby consolidating them.