In this paper we propose new methods of chemical structure classification based on the integration of graph database mining from data mining and graph kernel functions from machine learning. In our method, we first identify a set of general graph patterns in chemical structure data. These patterns are then used to augment a graph kernel function that calculates the pairwise similarity between molecules. The obtained similarity matrix is used as input to classify chemical compounds via a kernel machines such as the support vector machine (SVM). Our results indicate that the use of a pattern-based approach to graph similarity yields performance profiles comparable to, and sometimes exceeding that of the existing state-of-the-art approaches. In addition, the identification of highly discriminative patterns for activity classification provides evidence that our methods can make generalizations about a compound's function given its chemical structure. While we evaluated our methods on molecular structures, these methods are designed to operate on general graph data and hence could easily be applied to other domains in bioinformatics.

He organized several international and national meetings and symposia (IBRO meeting, Glia conferences etc.). His projects were funded by the EU, DFG, DAAD,national foundations and several industrial companies. He received several awards among them the MerckleForschungspreis 2001, the price of the Society of Steroid Biochemistry in 2002, and the RWTH Teaching Award in 2007. He is a member of the Editorial board of several peer-review journals such as the Annals of Anatomy and Current Neuropharmacology, and published several special issues in the Journal of Biochemistry and Molecular Biology. To this day, he published more than 190 peer reviewed articles with more than 3500 citations.