Mikhail Eltsov

This paper optimizes adhesion methods for cryo-electron tomography of vitreous sections, increasing throughput to match thin film methods and enabling high-resolution imaging of molecular complexes.

This paper introduces Template Learning, a deep learning method for particle picking in cryo-ET that reduces reliance on annotated datasets by simulating training data.

The paper uses cryo-CLEM to visualize and analyze the ultrastructural organization of mitotic chromosomes, identifying non-histone macromolecular densities and surface particle clusters.