ERC Starting Grant for research project of emergenCITY scientist Michael Muma

emergenCITY scientist Dr. Michael Muma’s project “ScReeningData” receives a Starting Grant from the European Research Council (ERC) and is funded with 1.5 million Euros as an excellent and innovative basic and frontier research. The project will develop methods to discover relevant information in complex biomedical data using computational learning.

The discovery of valuable medical information from biobanks is fundamental to the development of new personalized medicine. The project “Scalable Learning for Reproducibility in High-Dimensional Biomedical Signal Processing: A Robust Data Science Framework (ScReeningData)” provides researchers from biomedical disciplines with methods and reproducible insights for their research. The highlight: A quality control is already built in.

Reproducibility of results and statistical robustness of methods are mathematically quantified and proven in the “ScReeningData” project. This is important because hypotheses derived from biomedical data must be tested in elaborate experiments and clinical trials. Without statistical guarantees of reproducibility, valuable time is spent investigating relationships that may not actually exist. A high rate of new, reproducible discoveries, on the other hand, accelerates and improves, for example, the development of individualized diagnostics and therapies for diseases such as cancer, diabetes or heart failure.

Complex calculations possible in just a few days

The “ScReeningData” methods can distinguish reproducible biomarkers from random patterns. They are also robust to outliers in the data. In addition, they are scalable to very complex problems, such as the analysis of genetic data. Calculations that today take many years even with the most modern high-performance computers will be possible in a few days in the future. “ScReeningData” enables the systematic exploration of large biobanks.

The underlying computational learning concept of “ScReeningData”, which Michael Muma and his research team recently developed, is called “Terminating-Knockoff (T-Knock)”. The idea is similar to a placebo-controlled trial in drug research. It involves systematically running randomized controlled experiments on a computer and modeling them mathematically. Biomarkers are declared reproducible discoveries only if they sufficiently outperform computer-generated placebo markers (“knockoffs”). The speed advantage over existing methods comes from the fact that learning is stopped early (termination) when knockoffs are selected.

Michael Muma studied and received his PhD at the TU Darmstadt. Since 2017, he is a Postdoctoral Research Fellow, Lecturer and Young Investigator (Athene Young Investigator) in the Department of Signal Processing at the Department of Electrical Engineering and Information Technology (etit) at TU Darmstadt. He also conducts research in the LOEWE center emergenCITY. His work and publications have received numerous awards, including the Early Career Award of the European Association For Signal Processing (EURASIP).

ERC Starting Grants are awarded by the European Research Council to scientists from all disciplines up to seven years after their doctorate. In this way, the European Union promotes outstanding research and, at the same time, young scientists: The Starting Grant is aimed at researchers who already have excellent work to their credit and now want to expand independent research or establish their own working group at the beginning of their career.