Single particle imaging with x-ray-free electron lasers enables unique insights into the inner structure of nanometer-sized biological particles such as viruses. In order to reconstruct their 3D composition, a large number of 2D diffraction patterns must be acquired. AI-based isolation of single hits from among the hundreds of thousands of acquisitions made throughout the course […]
In this project we develop semantic segmentation methods for accurate delineation of cell membranes in cryoET data. Not only do these segmentations enable the analysis of the spatial configuration of membranes, for example in chloroplasts, they also facilitate downstream analysis like determining the distribution of membrane proteins on their surface.