Login |


Research at the Chair for Bioinformatics and Information Mining centers around methods from machine learning and data mining for the interactive knowledge extraction from large, heterogenuous data repositories. The following shows an overview of some of the ongoing research projects.

Information Mining: Foundations

Active Learning

In active learning the classifier selects examples to be classified by a human expert.


Data-mining of heterogeneous data with an ART-based (Adaptive Resonance Theory) neuronal network.

Fuzzy Rule Hierarchies

Hierarchies of rule models consist of different layers of simple rule models that describe the concept of the origin of the data in each layer according to a certain degree of detail.

Parallel Data Mining Unification

Towards an unifying formalism for generic parallelization model that is applicable to all data mining algorithms

Information Mining in Computational Life Science

Virtual High-Throughput Screening

Virtual High-Throughput Screening (vHTS) is very similar to traditional HTS in that hundreds and thousands (or even more) of chemical substances are tested with regard to their efficacy vis-à-vis protein targets.


MoFa, the Molecular Fragment Miner, is a program that finds automatically molecular substructures and discriminative fragments in a set of molecule descriptions given some user defined parameters.

Active Segmentation

The user-steered detection of cells in cell-images.



A modular data exploration platform, which enables data flows, or so-called “pipelines”, to be assembled visually.

Collaborative Research


The group coordinates the EU FP7 Open FET research project “BISON”. The target of the project is to develop an ICT paradigm, based on bisociation.