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

Cryo-electron microscopy (cryo-EM) maps are among the most 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 before modeling in order to improve their interpretability. To that end, approaches based on B-factor correction are the most popular choices, yet they suffer from some limitations such as the fact that the correction is applied globally, ignoring the presence of heterogeneity in the map local quality that cryo-EM reconstructions tend to exhibit. With the aim of overcoming these limitations, here we present DeepEMhacer, a deep learning approach designed to perform automatic post-processing of cryo-EM maps. Trained on a dataset of pairs of experimental cryo-EM maps and maps sharpened by LocScape using their respective atomic models, DeepEMhacer has automatically learned how to post-process experimental maps performing masking-like and sharpening-like operations in a single step. DeepEMhacer has been evaluated on a testing set of 20 different experimental maps, showing its ability to obtain much cleaner and detailed versions of the experimental maps, thus, improving their interpretability. Additionally, we have illustrated the benefits of DeepEMhacer with a use case in which the structure of the SARS-CoV 2 RNA polymerase is improved.This work is supported by the the Comunidad de Madrid through grant CAM (S2017/BMD-3817), the Spanish Ministry of Economy and Competitiveness (BIO2016-76400-R). J.V. acknowledges economical support from the Ramón y Cajal 2018 program (RYC2018-024087- I). R.S. is recipient of an FPU fellowship.Peer reviewe