RT Journal Article
SR Electronic
T1 Super-Resolution Cryo-EM Maps With 3D Deep Generative Networks
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2021.01.12.426430
DO 10.1101/2021.01.12.426430
A1 Sai Raghavendra Maddhuri Venkata Subramaniya
A1 Genki Terashi
A1 Daisuke Kihara
YR 2021
UL http://biorxiv.org/content/early/2021/01/14/2021.01.12.426430.abstract
AB An increasing number of biological macromolecules have been solved with cryo-electron microscopy (cryo-EM). Over the past few years, the resolutions of density maps determined by cryo-EM have largely improved in general. However, there are still many cases where the resolution is not high enough to model molecular structures with standard computational tools. If the resolution obtained is near the empirical border line (3-4 Å), a small improvement of resolution will significantly facilitate structure modeling. Here, we report SuperEM, a novel deep learning-based method that uses a three-dimensional generative adversarial network for generating an improved-resolution EM map from an experimental EM map. SuperEM is designed to work with EM maps in the resolution range of 3 Å to 6 Å and has shown an average resolution improvement of 1.0 Å on a test dataset of 36 experimental maps. The generated super-resolution maps are shown to result in better structure modelling of proteins.Competing Interest StatementThe authors have declared no competing interest.