Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 52 min ago
Peer-reviewedCC BY-NC-NDNature Communications

EMReady2: improvement of cryo-EM and cryo-ET maps by local quality-aware deep learning with Mamba

  • Hong Cao1
  • Yueting Zhu2
  • Tao Li1
  • Ji Chen1
  • Jiahua He3,4
  • Xinggang Wang5
  • Sheng‐You Huang6
6 affiliations
  1. 1School of Physics, Huazhong University of Science and Technology, Wuhan, China
  2. 2School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China
  3. 3Department of Biochemistry and Biophysics, University of California San Francisco, San Francisco, CA, USA. [email protected]
  4. 4School of Physics, Huazhong University of Science and Technology, Wuhan, China. [email protected]
  5. 5School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China. [email protected]
  6. 6School of Physics, Huazhong University of Science and Technology, Wuhan, China. [email protected]
Open at sourcePDFDOICite

Abstract

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 EMReady2, an extension of our previous EMReady cryo-EM map improvement method. 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 local quality 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. EMReady2 is evaluated on 136 diverse maps at 2.0-10.0 Å resolutions, and compared with existing map post-processing methods. Our results demonstrate that EMReady2 exhibits state-of-the-art performance in both map quality and map interpretability improvement while much reducing the computational cost.

Related

  1. GLASS: a graph learning algorithm for screening splice-aware alignments of long-read RNA-seq data
    Jiahao Li, Zeming Tan, Guojun Li +1
    BMC GenomicsPeer-reviewedCC BY-NC-ND 4.0Molecular biology & gene regulationCrossref
  2. Geometric-aware deep learning for deciphering tissue structure from spatially resolved transcriptomics
    Xingyi Li, Xiangting Jia, Dongmin Zhao +8
    Communications BiologyPeer-reviewedCC BY-NC-ND 4.0Full text1 citedMolecular biology & gene regulationPMC
  3. Learning Task-Specific Antibody Representations via Function-Aware Masking
    Ayan Goel, Thomas A. Walton, Amirali Aghazadeh
    arXivPreprintCC BY 4.0Full textBiophysicsarXiv
  4. TransSurv: compatibility-aware transfer learning for target-cohort survival prediction
    Zheng Qu, Hongzhe Zhang, Katherine L Nathanson +3
    Briefings in BioinformaticsPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationPMC
  5. EvoGraph: synergizing evolutionary semantics and tail-aware graph contrastive learning for protein-protein interaction prediction.
    Yilou Zhang, Yuan Zhao, Jue Zhou +2
    Briefings in bioinformaticsPeer-reviewedCC BY-NCFull textMolecular biology & gene regulationEurope PMCPMC

Cite

BibTeXRIS
BibTeX
@article{cao2026emready2,
  title = {{EMReady2: improvement of cryo-EM and cryo-ET maps by local quality-aware deep learning with Mamba}},
  author = {Hong Cao and Yueting Zhu and Tao Li and Ji Chen and Jiahua He and Xinggang Wang and Sheng‐You Huang},
  journal = {Nature Communications},
  year = {2026},
  month = may,
  doi = {10.1038/s41467-026-71794-1},
  url = {https://doi.org/10.1038/s41467-026-71794-1},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - EMReady2: improvement of cryo-EM and cryo-ET maps by local quality-aware deep learning with Mamba
AU  - Hong Cao
AU  - Yueting Zhu
AU  - Tao Li
AU  - Ji Chen
AU  - Jiahua He
AU  - Xinggang Wang
AU  - Sheng‐You Huang
PY  - 2026
DA  - 2026/05/16
JO  - Nature Communications
DO  - 10.1038/s41467-026-71794-1
UR  - https://doi.org/10.1038/s41467-026-71794-1
AB  - 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 EMReady2, an extension of our previous EMReady cryo-EM map improvement method. 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 local quality 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. EMReady2 is evaluated on 136 diverse maps at 2.0-10.0 Å resolutions, and compared with existing map post-processing methods. Our results demonstrate that EMReady2 exhibits state-of-the-art performance in both map quality and map interpretability improvement while much reducing the computational cost.
SN  - 2041-1723
ER  -