In the research area Data Science, we focus on the development and application of data-driven methods for solving biological, medical, and technical problems. In close cooperation with our partners from research and industry, we develop algorithms for preprocessing and analyzing data using statistical methods and machine learning, as well as visualizing and interpreting the results. For example, within the project LeiVMed Online we develop a platform for benchmarking and visualizing data of treatments of patients in hospitals and developing prediction models for the outcome of treatments.
In many of our projects, we see the need for customized data processing pipelines due to the heterogeneity and complexity of data structures in real world processes and systems. We use applied statistics as well as numerous machine learning approaches, including black box methods (deep neural nets, random forests, gradient boosted trees, etc.) and white box methods (symbolic regression by genetic programming). We build our knowledge discovery pipelines on a variety of different frameworks, especially python scikit-learn, tensorflow, pytorch, MATLAB, and HeuristicLab.
|2021||Stefan Anlauf, Andreas Haghofer, Karl Dirnberger, Stephan M. Winkler:||Data-Based Prediction of Microbial Contamination in Herbs and Identification of Optimal Harvest Parameters||International Journal of Food Engineering (IJFE), DeGruyter|
|2019||Renate Haselgrübler, Peter Lanzerstorfer, Clemens Röhrl, Flora Stübl, Jonas Schurr, Bettina Schwarzinger, Clemens Schwarzinger, Mario Brameshuber, Stefan Wieser, Stephan M. Winkler, and Julian Weghuber:||Hypolipidemic effects of herbal extracts by reduction of adipocyte differentiation, intracellular neutral lipid content, lipolysis, fatty acid exchange and lipid droplet motility||Scientific Reports||View Article|
|2018||Stephan M. Winkler:||Evolutionary Computation and Symbolic Regression in Scientific Modeling||, Johannes Kepler University Linz, Computer Science, Habilitation Thesis|
|2016||Daniela Borgmann, Sandra Mayr, Helene Polin, Susanne Schaller, Viktoria Dorfer, Christian Gabriel, Stephan Winkler, and Jaroslaw Jacak:||Single Molecule Florescence Microscopy and Machine Learning for Rhesus D Antigen Classification||Scientific Reports 6||View Article|
Following the introduction of highly potent immunosuppressive regimens in combination with induction therapy, a significant reduction of acute rejection episodes and an improvement in short term graft survival have been achieved. However, a small number of transplanted organs continue to be lost following an acute rejection (AREJ) episode, but long-term graft function and survival following this kind of immunological injury poses even greater problems to patient management.
Two principal histologic forms of acute rejection are distinguished: a) acute cellular rejection (T-cell mediated) and b) acute anti-body mediated rejection. Cellular rejection with CD8+ and CD4+ T lymphocytes plays a central role and accounts for the larger fraction of acute rejection episodes. Lymphocyte infiltrates in the kidney are the hallmark of T-cell mediated rejection. T cells require at least two signals: The first is delivered when the T cell receptor (TCR) binds to the MHC-allopeptide complex on APCs. The second signal termed “costimulation” involves ligation of specific molecules on the surface of T cells to molecules on APCs, e.g. CD28 binds CD80 and CD86 molecules on APCs fostering the cellular immune response. In this regard, the nature of the lymphoid cells that infiltrate the transplanted kidney is of special interest. Little is known about the molecular nature of these infiltrates, particularly as it relates to the T-cell receptor (TCR) repertoire.
Prof.(FH) DI Dr. Stephan M. Winkler
Susanne Schaller, MMSc
Prof.(FH) DI Dr. Stephan M. Winkler
2017 - present
University of Applied Sciences, Upper Austria, Hagenberg Campus
Medical University of Vienna