Tools for Model Building and Optimization into Near-Atomic Resolution Electron Cryo-Microscopy Density Maps

Abstract

Electron cryo-microscopy (cryoEM) has advanced dramatically to become a viable tool for high-resolution structural biology research. The ultimate outcome of a cryoEM study is an atomic model of a macromolecule or its complex with interacting partners. This chapter describes a variety of algorithms and software to build a de novo model based on the cryoEM 3D density map, to optimize the model with the best stereochemistry restraints and finally to validate the model with proper protocols. The full process of atomic structure determination from a cryoEM map is described. The tools outlined in this chapter should prove extremely valuable in revealing atomic interactions guided by cryoEM data.

Keywords: CryoEM map-derived model; Model optimization; Model validation.

Fig. 1

Structure features of CryoEM maps determined at different resolutions. (A) Beta-galactosidase at 2.2 Å (EMDB2984, PDB 5A1A). (B) Brome mosaic virus at 3.8 Å (EMDB6000, PDB 3J7L). (C) IP3R1 at 4.7 Å (EMDB6369, PDB 3JAV).

Fig. 2

An overview of three steps of atomic model determination from near-atomic resolution data. (Left) De novo building methods take primary sequence and map, and automatically produce a backbone model with sequence registered, identifying which regions in the map correspond to particular sequences. (Center) Model optimization takes an initial model—either produced from de novo building, or from a high-resolution homologue—and optimizes the coordinates to better agree with the map, as well as adopt more physically realistic geometry. (Right) Model validation aims to assess—both globally and locally—the accuracy of a model, given experimental data. Such tools are useful not only for assessing overall accuracy but also for tuning parameters of optimization.

Fig. 3

Modeling a 3.5 Å cryoEM map of VipA/B (Kudryashev et al., 2015). (A) The 3.5 Å reconstruction (EMDB2699) of VipA/B, the contractile sheath of the type VI secretion system. (B) A model of the two protein components, built using Rosetta de novo building followed by optimization with RosettaCM (PDB 3J9G). (C) A close-up view of the asymmetric unit model, shown in density. The two panels on the right show regions of relatively low local resolution; Rosetta de novo allowed placement of the models in these regions.

Fig. 4

Modeling a 3.8 Å cryoEM map of VP6 of rotavirus. (A) A segmented density map of a capsid protein subunit of rotavirus (VP6) determined at 3.8 Å (EMDB1460). (B) A de novo model built by pathwalker superimposed on the density map. (C) A crystal structure of the same protein (PDB 1QHD). (D) A Cα rms deviation between the cryoEM model and crystal structure with the most and least deviation in red (gray in the print version) and blue (dark gray in the print version), respectively.

Fig. 5

Modeling IP3R1 from a 4.7 Å cryoEM map (EMDB6369) (Fan et al., 2015). (A) The model (PDB 3JAV) was built using a variety of modeling protocols, shown from two views. The model is of the entire tetramer with 85% chain connectivity per chain, partly due to the presence of isoforms at the SI, SII, and SIII sites causing specimen heterogeneity and partly due to the limited map resolution. (B) The annotation of the 10 structural domains of a single IP3R1 subunit with 2700 amino acids. (C) A schematic of the corresponding domains in the linear sequence.

Fig. 6

The types of motion possible during Rosetta optimization. (Left) Two different regions of relatively low local resolution in the 3.4 Å resolution map of TRPV1; Rosetta refinement (right two panels) allows for significant conformational difference from the deposited structure (left two panels). (Right) Despite the significant backbone movement in the course of optimization, an ensemble of low energy models, resulting from independent trajectories, are well converged.

Fig. 7

An example of model optimization using DireX to model distinct conformational states of F-actin from a 4.8 Å cryoEM map (Galkin, Orlova, Vos, Schroder, & Egelman, 2015). (A) A 4.8 Å resolution reconstruction of F-actin (EMDB6179) into which a model has been built and optimized (PDB 3J8I). (B and C) Two alternate, low-occupancy conformations of actin, titled T1 and T2, into which the initial model has been refined. Even though the data are of relatively low resolution, DireX attempts to maintain as many contacts as possible during refinement.

Fig. 8

Model validation of a 3.8 Å cryoEM map of brome mosaic virus (EMDB6000) (Wang et al., 2014) by (A) deviation between two independent models at the Cα level (PDB 3J7M and PDB 3J7N). (B) FSC between model and experimental map from two independent data sets.

Fig. 9

(A) A schematic of the use of EMRinger for model validation (Barad et al., 2015). Given a backbone model and a density map, EMRinger considers all possible positions for a putative Cγ and identifies density peaks at a given threshold; the fractions of these peaks over the whole structure, which are rotameric are used to assess the quality of the model. (B) The results of EMRinger analysis on a sample system: the x-axis plots various density value cutoffs and the y-axis shows the EMRinger Z-score. Higher values are better, with Z-score of > 2 indicating high-quality structures.