Niklas Gebauer is a doctoral researcher at the Machine Learning group of Prof. Dr. Klaus-Robert Müller at Technische Universität Berlin. He is a member of the BIFOLD graduate school and part of BASLEARN, the Berlin based joint lab of BASF and TU Berlin for machine learning. His work focuses on generative deep neural networks for molecular structures. He recieved his Master's and Bachelor's degrees in Computer Science from TU Berlin.
Research project: “Generating Molecular Structures with Deep Neural Networks”
The exploration and identification of novel molecules and materials with certain desired chemical properties is crucial for various fields such as drug discovery, renewable energies, catalysis, or nanotechnologies. However, the space of all possible compounds is extremely vast and the calculation of stable molecular structures and their properties is computationally expensive, making an exhaustive search impossible. Machine learning can help to overcome these challenges in two ways. First, deep learning models have proven to yield accurate predictions of quantum-chemical properties at a fraction of the time that classical simulation methods need. Second, generative models can learn to sample novel, promising candidate molecules with desired properties given a training set of known molecules. In my project I focus on the latter by developing deep neural network models for the generation of 3d molecular structures. The goal is to build a framework for the guided exploration of chemical compound space in order to drive advancements in real-world applications.
- Machine learning (ML) for quantum chemistry
- Generative modelling for atomistic systems
- Geometric deep learning
- Member of BASLEARN - Berlin based Joint Lab for Machine Learning
- Member of the BIFOLD Graduate School
Kristof T. Schütt, Stefaan S.P. Hessmann, Niklas W.A. Gebauer, Jonas Lederer, Michael Gastegger
Niklas W. A. Gebauer, Michael Gastegger, Stefaan S. P. Hessmann, Klaus-Robert Müller, Kristof T. Schütt