Title: Graph representation learning for single-cell genomics

Abstract: Single-cell RNA sequencing measures gene expression at an unprecedented resolution and scale and allows the analysis of cellular phenotypes which was not possible before. In this context, graphs occur as a natural representation of the system —both as gene-centric and cell-centric. Taking the inference of cell types or gene interactions as examples, graph representation learning has a wide applicability to both cell and gene graphs. Graph Neural Networks (GNNs) lie at the core of graph representation learning. This talk will introduce the fundamentals of GNNs and show how they map to concepts used in single-cell biology. Selected applications will be discussed in more detail.

Bio: Leon Hetzel is a PhD student at the Technical University of Munich (TUM) under the joint supervision of Prof. Fabian Theis and Prof. Stephan Günnemann. Leon studied physics at the Universities of Bremen and Heidelberg and obtained his Master’s degree in Mathematical Sciences at the University of Oxford. Throughout his studies, he was supported by the German Academic Scholarship Foundation. Leon now works on generative models for single-cell perturbation and spatial transcriptomics, focusing on GNNs in particular.

Share this Event