Lorenz Lamm

BaSiCPy improves illumination correction in microscopy images by addressing foreground correlations and enabling automated processing.

MemBrain v2 couples a generalist U-Net cryo-ET membrane segmenter, a mesh-based picker reaching 91% F1 for photosystem II from one annotated membrane, and geodesic particle statistics.

Automated cryogenic plasma-focused ion beam milling and cryo-electron tomography of Chlamydomonas reinhardtii yield 1,829 annotated cellular tomograms and sub-nanometer in situ structures of six macromolecular complexes.

The paper uses cryo-electron tomography to visualize mitochondrial respiratory complexes in Chlamydomonas reinhardtii, revealing their organization into distinct membrane domains and a respirasome structure with cytochrome c binding.

This study uses cryo-ET and AI-based methods to analyze thylakoid membrane organization in spinach chloroplasts, revealing similarities to green algae despite differences in 3D architecture.

Surforama enables interactive visualization and analysis of membrane proteins in cryo-ET data by rendering local densities on segmented surfaces and exporting results for further analysis.

This paper introduces a Mean Shift loss function for more accurate protein localization in cryo-electron tomography using scoremap-guided clustering and random point sampling.

This paper introduces synthetic datasets for cryo-electron tomography to train deep learning algorithms by simulating cellular structures and geometries.

MemBrain detects membrane proteins in cryo-ET data using a deep learning pipeline, achieving high accuracy with minimal labels and generalizing across different cell types and imaging methods.

This paper introduces DeepFinder, a deep learning method that improves macromolecule identification in 3D cellular cryo-ET data by localizing multiple species with high accuracy.