A primer to single-particle cryo-electron microscopy

Abstract

Cryo-electron microscopy (cryo-EM) of single-particle specimens is used to determine the structure of proteins and macromolecular complexes without the need for crystals. Recent advances in detector technology and software algorithms now allow images of unprecedented quality to be recorded and structures to be determined at near-atomic resolution. However, compared with X-ray crystallography, cryo-EM is a young technique with distinct challenges. This primer explains the different steps and considerations involved in structure determination by single-particle cryo-EM to provide an overview for scientists wishing to understand more about this technique and the interpretation of data obtained with it, as well as a starting guide for new practitioners.

Figure 1. The Steps Involved in Structure Determination by Single-Particle Cryo-EM

A single-particle project should start with a characterization of the specimen in negative stain (left arm of the workflow). Only once the EM images, or potentially 2D class averages, are satisfactory, i.e., the particles are mono-disperse and show little aggregation and a manageable degree of heterogeneity (“low-resolution” sample refinement), is the sample ready for analysis by cryo-EM (right arm of the workflow). The images, 2D class averages and 3D maps obtained with vitrified specimens may indicate that the sample requires further improvement to reach near-atomic resolution (“high-resolution” sample refinement).

Figure 2. Single-Particle Cryo-EM Images with Motion Correction

Most data recorded with DDD cameras are dose-fractionated image stacks (movies) that can be motion-corrected. (A) A typical cryo-EM image of vitrified archaeal 20S proteasome particles embedded in a thin layer of vitreous ice. The image is the sum of the raw movie frames without motion correction. (B) Trace of motion of all movie frames determined using a whole-frame motion-correction algorithm (Li et al., 2013a). Note that the movement between frames is large at the beginning but then slows down. (C) The left panel shows the power spectrum calculated from the sum of the raw movie frames without motion correction. The right panel shows the power spectrum calculated from the sum of movie frames after motion correction. Motion correction restores Thon rings to close to 3Å resolution (dashed circle). (D) Sum of the movie frames that were shifted according to the shifts shown in (B). Note that the images shown in (A) and (D) are indistinguishable by eye, but differ significantly in the quality of the Thon rings seen in their power spectra (C).

Figure 3. Principle of the K-means Algorithm Used in Single-Particle EM Structure Determination Protocols

(A) In the basic K-means algorithm, the particle images are compared with a set of class averages using a correlation measure that yields the class assignment. Based on the updated class assignments, new class averages are then calculated. Simply by adding 2D alignment of the images to the templates using a correlation function, the algorithm is converted to Multi-Reference Alignment (MRA) (indicated by text in red font). (B) Principle of the projection matching technique used for 3D single-particle EM structure refinement. The best match of an image to a template yields the Euler angles that were used to generate the template, while a 2D alignment step yields the third, in-plane Euler angle and the two in-plane translations, the total of five orientation parameters required for 3D reconstruction step.

Figure 4. Evaluation and Validation of a 3D EM Structure

Critical evaluation of EM structural results is of utmost importance due to potential model bias and unavoidable noise alignment inherent to the single-particle EM structure determination method. Ultimate confirmation of the map, particularly of the details at the limit of the resolution claimed, is best done by independent structure determination, possibly using different software packages, even if one uses the same dataset. Here, we show the results of two outcomes for the structure determination of the TRPV1 channel. (A) Originally, the structure was solved using RELION (Scheres, 2012): the refinement was initialized with an RCT model, and the final map represents the best class produced by 3D MRA (Liao et al., 2013). (B) The structure determination was repeated using the same 2D dataset. 2D MRA was performed using IMAGIC (van Heel et al., 1996), an initial model was generated using EMAN2 (Tang et al., 2007), and refinement and 3D MRA were done in FREALIGN (Grigorieff, 2007; Lyumkis et al., 2013). For consistency, the rotationally averaged power spectrum of map (B) was set to that of map (A). Interestingly, while the two maps are visually very similar, only ~60% of particles in the best class determined by RELION coincide with those in the best class determined by FREALIGN. This difference likely reflects limitations of K-means-based clustering approaches and, possibly, points to the fact that the number of classes used was too low. (C,D) The side-chain densities in the best parts of the map shown in (A) agree with those of the map shown in (B), validating these details. However, some weaker peripheral density features in the maps shown in (A) and (B) exhibit noticeable differences (see also Supplemental Information and Figure S2). (E) Angular uncertainty and blurring affects the FSC curves, and thus the resolution reported: calculation of 3D reconstructions using multiple, probability-weighted copies of each particle image (“soft matching”, see Supplemental Information) can lead to an apparent improvement in the resolution (RELION, black curve) while hard matching yields more conservative results (FREALIGN, red curve). The difference is, however, too small to affect the interpretation of the maps and also lies within the general uncertainty bounds of the FSC methodology, which also depends on other data-processing steps, as, for example, masking of the map. (F) The resolution of the map is non-uniform. The local resolution of the map shown in (B) was calculated (Penczek, 2014c) and indicates that densities within the membrane domain, and particularly around the pore, are better resolved than those in the extracellular domains. 3D maps were rendered using UCSF Chimera (Pettersen et al., 2004)