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

🤖 Plain-English Summary

Cryo-EM maps are valuable sources of information for protein structure modeling. DeepEMhancer was evaluated on a testing set of 20 different experimental maps, showing its ability to reduce noise levels and obtain more detailed versions of the experimental maps.

🔑 Key Findings

• 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 global B-factor correction, suffer from limitations.
• For instance, they ignore the heterogeneity in the map local quality that reconstructions tend to exhibit.

🔗 Related Resources