Integrating AlphaFold and deep learning for atomistic interpretation of cryo-EM maps

Abstract

Interpretation of cryo-electron microscopy (cryo-EM) maps requires building and fitting 3-D atomic models of biological molecules. AlphaFold-predicted models generate initial 3-D coordinates; however, model inaccuracy and conformational heterogeneity often necessitate labor-intensive manual model building and fitting into cryo-EM maps. In this work, we designed a protein model-building workflow, which combines a deep-learning cryo-EM map enhancement tool, ResEM(Resolution EnhanceMent) and AlphaFold. A benchmark test using 37 cryo-EM maps shows that ResEM achieves state-of-the-art performance in optimizing real space model-map correlations between ResEM-enhanced maps and ground-truth models. Furthermore, in a subset of 17 datasets where the initial AlphaFold predictions are less accurate, the workflow significantly improves their model accuracy. Our work demonstrates that the integration of modern deep learning image enhancement and AlphaFold may lead to automated model building and fitting for the atomistic interpretation of cryo-EM maps.