Improving cryo-EM maps by resolution-dependent and heterogeneity-aware deep learning
Cryo-electron microscopy (cryo-EM) has emerged as a leading technology for determining the structures of biological macromolecules. However, map quality issues such as noise and loss of contrast hinder accurate map interpretation. Traditional and deep learning-based post-processing methods offer improvements but face limitations particularly in handling map heterogeneity. Here, we present a generalist Mamba-based deep learning model for improving cryo-EM maps, named EMReady2. EMReady2 introduces a fast Mamba-based dual-branch UNet architecture to jointly capture local and global features. In addition, EMReady2 also uses a local resolution-guided learning strategy to address map heterogeneity, and significantly extends the training set. These advances render EMReady2 applicable to a broader range of cryo-EM maps, including those containing nucleic acids, medium-resolution maps, and cryo-electron tomography (cryo-ET) maps, while substantially reducing computational cost. EMReady2 is extensively evaluated on 136 diverse maps at 2.0-10.0 [A] resolutions, and compared with existing map post-processing methods. It is shown that EMReady2 exhibits state-of-the-art performance in both map quality and map interpretability improvement. EMReady2 is freely available at https://github.com/huang-laboratory/EMReady2/.