Machine Learning of System Biological Processes Bachelor-/Master thesis Contact: Prof. Dr.-Ing. G. Dartmann Prof. Dr.-Ing. A. Schmeink Motivation Use Case Methodology Sepsis is a life-threatening disease with high morbidity and mortality. Although novel therapeutics are urgently needed, the development of new drugs reveals a time and cost intensive worldwide challenge. The past few years have seen a profound development of machine learning techniques applied in diverse fields. This knowledge offers a new component in the drug design process, which may revolutionize the way we develop drugs. In addition to sepsis multiple medical applications are possible for this approach. We investigate a novel holistic approach for a machine learning driven development of sepsis therapeutics using Hybrid models Methods Hypbrid Petri Nets Machine Learning and Optimization System and control technology Machine Learning for model adaption Discrete and continuous optimization We use Hybrid Petri Nets to model the system biological process. In contrast to neural networks they offer the integration of expert knowledge. P. Vieting, R. C. de Lamare, L. Martin, G. Dartmann and A. Schmeink, An Adaptive Learning Approach to Parameter Estimation for Hybrid Petri Nets in Systems Biology, IEEE Statistical Signal Processing Workshop (SSP), 2018 Tasks Requirements Research Questions Students Modelling of a simple example use case Identification of training data for learning Development of a methodology to adapt a Petri net based on training data Information technology Computer Science Cooperation Partners University Hospital Aachen, OIM RWTH Aachen University, ICE & ISEK Trier University of Applied Sciences