I am a mathematician who is currently pursuing a doctoral degree at the Mathematical Institute and the Department of Statistics of the University of Oxford. Within the Mathematical Institute, I am a member of the well-known Center for Doctoral Training in Industrially Focused Mathematical Modelling (InFoMM CDT). During my undergraduate degree, I mainly focussed on pure mathematics and its rigorous methodology. Since then, I have additionally become interested in the applied and data-driven side of the mathematical sciences. I have developed a particular focus on mathematical data science, programming, graphs and networks, deep learning, artificial intelligence and advanced statistical machine learning. In my current DPhil (= PhD) project at the University of Oxford I am collaborating with the research company Lhasa Limited to investigate novel graph-based machine learning techniques and their applications in chemistry and computational drug discovery.

Molecular machine learning techniques have recently shown great promise for important computational drug discovery tasks such as molecular property prediction and activity cliff prediction. The success of such methods, however, crucially depends on the way in which molecular compounds are transformed into informative feature vectors that can be fed into a machine learning pipeline. This is referred to as the problem of molecular representation. In my DPhil project, I am investigating the potential of modern graph-based molecular representation techniques to outperform classical molecular representations such as structural fingerprints and physicochemical descriptor vectors. I am particularly interested in developing novel self-supervised learning strategies for graph neural networks operating on molecular graphs in order to identify and remove hidden performance barriers of state-of-the-art molecular representation methods. The gained insights can be used to design new tailored deep learning architectures for important computational drug discovery tasks such as molecular property prediction and activity cliff prediction.