DeepEMhancer: a deep learning solution for cryo-EM volume post-processing

Cryo-EM maps are valuable sources of information for protein structure modeling. However, due to the loss of contrast at high frequencies, they generally need to be post-processed to improve their interpretability. Most popular approaches, based on B-factor correction, suffer from limitations. For instance, they ignore the heterogeneity in the map local quality that reconstructions tend to exhibit. Aiming to overcome these problems, we present DeepEMhancer, a deep learning approach designed to perform automatic post-processing of cryo-EM maps. Trained on a dataset of pairs of experimental maps and maps sharpened using their respective atomic models, DeepEMhancer has learned how to post-process experimental maps performing masking-like and sharpening-like operations in a single step. DeepEMhancer was evaluated on a testing set of 20 different experimental maps, showing its ability to obtain much cleaner and more detailed versions of the experimental maps. Additionally, we illustrated the benefits of DeepEMhancer on the structure of the SARS-CoV-2 RNA polymerase.

[1]  Genki Terashi,et al.  Protein Secondary Structure Detection in Intermediate Resolution Cryo-EM Maps Using Deep Learning , 2019, Nature Methods.

[2]  L. Guddat,et al.  Structure of the RNA-dependent RNA polymerase from COVID-19 virus , 2020, Science.

[3]  Jue Chen,et al.  ATP Binding Enables Substrate Release from Multidrug Resistance Protein 1 , 2018, Cell.

[4]  J. Vargas,et al.  Local computational methods to improve the interpretability and analysis of cryo-EM maps , 2020 .

[5]  Yanan Zhu,et al.  A deep convolutional neural network approach to single-particle recognition in cryo-electron microscopy , 2016, BMC Bioinformatics.

[6]  Michael Unser,et al.  CryoGAN: A New Reconstruction Paradigm for Single-Particle Cryo-EM via Deep Adversarial Learning , 2020, bioRxiv.

[7]  Erik Lindahl,et al.  New tools for automated high-resolution cryo-EM structure determination in RELION-3 , 2018, eLife.

[8]  R. Henderson,et al.  Optimal determination of particle orientation, absolute hand, and contrast loss in single-particle electron cryomicroscopy. , 2003, Journal of molecular biology.

[9]  C O S Sorzano,et al.  Re-examining the spectra of macromolecules. Current practice of spectral quasi B-factor flattening. , 2020, Journal of structural biology.

[10]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[11]  Thorsten Wagner,et al.  SPHIRE-crYOLO is a fast and accurate fully automated particle picker for cryo-EM , 2019, Communications Biology.

[12]  Dong Si,et al.  Deep Learning to Predict Protein Backbone Structure from High-Resolution Cryo-EM Density Maps , 2020, Scientific Reports.

[13]  Pablo Chacón,et al.  The structural basis of flagellin detection by NAIP5: A strategy to limit pathogen immune evasion , 2017, Science.

[14]  Wei Wang,et al.  Deep Learning for Single Image Super-Resolution: A Brief Review , 2018, IEEE Transactions on Multimedia.

[15]  Tian Xia,et al.  DeepPicker: a Deep Learning Approach for Fully Automated Particle Picking in Cryo-EM , 2016, Journal of structural biology.

[16]  Conrad C. Huang,et al.  UCSF Chimera—A visualization system for exploratory research and analysis , 2004, J. Comput. Chem..

[17]  Dong Si,et al.  Deep Learning for Validating and Estimating Resolution of Cryo-Electron Microscopy Density Maps , 2019, Molecules.

[18]  John D. Westbrook,et al.  EMDataBank unified data resource for 3DEM , 2013, Nucleic Acids Res..

[19]  Kaiming He,et al.  Group Normalization , 2018, ECCV.

[20]  Carsten Sachse,et al.  Model-based local density sharpening of cryo-EM maps , 2017, eLife.

[21]  Tuo-Hung Hou,et al.  SLIM: Simultaneous Logic-in-Memory Computing Exploiting Bilayer Analog OxRAM Devices , 2018, Scientific Reports.

[22]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[23]  Tristan Bepler,et al.  Reconstructing continuous distributions of 3D protein structure from cryo-EM images , 2019, ICLR.

[24]  Thomas C Terwilliger,et al.  Automated map sharpening by maximization of detail and connectivity , 2018, bioRxiv.

[25]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[26]  José María Carazo,et al.  Automatic local resolution-based sharpening of cryo-EM maps , 2018, bioRxiv.

[27]  E. Lindahl,et al.  Accelerated cryo-EM structure determination with parallelisation using GPUs in RELION-2 , 2016, bioRxiv.

[28]  Kevin Cowtan,et al.  research papers Acta Crystallographica Section D Biological , 2005 .

[29]  Marta Sawicka,et al.  Cryo-EM structures and functional characterization of murine Slc26a9 reveal mechanism of uncoupled chloride transport , 2019, eLife.

[30]  Carlos Oscar S Sorzano,et al.  DeepRes: a new deep-learning- and aspect-based local resolution method for electron-microscopy maps , 2019, IUCrJ.