2026Li Atomic

Citation

Li, T. and Huang, S.-Y. 2026. Deep learning–based postprocessing and model building for cryo-electron microscopy maps. Current Opinion in Structural Biology. 96, (2026), 103196.

Abstract

Cryo-electron microscopy (cryo-EM) has emerged as one of the most powerful techniques for determining the structures of biological macromolecules. The ultimate goal of cryo-EM is to determine the atomic structure of target molecules, where map postprocessing and atomic-model building are two crucial final steps of the cryo-EM pipeline. With the fast development of artificial intelligence, deep learning has been implemented in various stages of cryo-EM. Here, we present a comprehensive overview of recent advances in map postprocessing and model building for cryo-EM maps with focuses on deep learning–based methods. We also discuss the advantages and limitations of current approaches as well as challenges that are left for future research.

Links

https://www.sciencedirect.com/science/article/pii/S0959440X25002143