Three-dimensional reconstruction of icosahedral particles from single micrographs in real time at the microscope

Abstract

Single particle analysis is a valuable tool in cryo-electron microscopy for determining the structure of biological complexes. However, the conformational state and the preparation of the sample are factors that play a critical role in the ultimate attainable resolution. In some cases extensive analysis at the microscope of a sample under different conditions is required to derive the optimal acquisition conditions. Currently this analysis is limited to raw micrographs, thus conveying only limited information on the structure of the complex. We are developing a computing system that generates a three-dimensional reconstruction from a single micrograph acquired under cryogenic and low dose conditions, and containing particles with icosahedral symmetry. The system provides the microscopist with immediate structural information from a sample while it is in the microscope and during the preliminary acquisition stage. The system is designed to run without user intervention on a multi-processor computing resource and integrates all the processing steps required for the analysis. Tests performed on experimental data sets show that the probability of obtaining a reliable reconstruction from one micrograph is primarily determined by the quality of the sample, with success rates close to 100% when sample conditions are optimal, and decreasing to about 60% when conditions are sub-optimal. The time required to generate a reconstruction depends significantly on the diameter of the particles, and in most instances takes about 1min. The proposed approach can provide valuable three-dimensional information, albeit at low resolution, on conformational states, epitope binding, and stoichiometry of icosahedral multi-protein complexes.

Keywords: 3D reconstruction; Automation; Cryo-electron microscopy; Icosahedral particles; Image processing; Single particle analysis.

Figure 1

Automated reconstruction workflow. The system continuously monitors if micrographs are acquired, and new images are immediately added to the queue for processing. The only input parameter required from the user at the beginning of the procedure is the radius of the particle. Pre-processing involves making two copies of the micrograph binned at different sizes and format conversion. These copies are then processed in parallel to estimate the microscope CTF and to pick the particles from the available field of view. Once the particle images are extracted and the microscope acquisition parameters (astigmatism, defocus) are available, a set of ten separate RMCs is launched. These models are iteratively refined in parallel, on separate processors, and the final 3D reconstruction results are compared to select the best reconstruction.

Figure 2

Graphical user interface of AutoRTM. Acquired images are displayed as soon as they are available, usually within two seconds, at the left side of the interface window. Particles picked by the program are highlighted with red circles. The incoherent Fourier Transform calculated from the acquired image and a simulated Contrast Transfer Function are displayed at the top-center of the interface window at left and right sides, respectively. Just below this split display, a central, 1-pixel thick section from the 3D reconstruction selected as the best of the ten candidate reconstructions is shown. At the top-right of the interface window, under the Micrograph tab, are various control buttons that allow the microscopist to view previous results along with quantitative information on the results of the processing. These include the number of particles picked, and the estimate of the defocus values along the minimum and the maximum axes. Initial settings, such as the estimated particle radius and the name of the directory that is constantly monitored for new images, are specified under the Session tab. Central sections from all ten candidate reconstructions can be inspected by opening an additional window, shown at the bottom.

Figure 3

Data sets used for the benchmark tests. A representative micrograph is shown for each data set (bar = 100 nm).

Figure 4

Dependency of computational time on number of particles picked from each micrograph. Plot of the time required to process each micrograph and calculate one random model (1-RMC time) against the number of particles automatically picked and used for each reconstruction. All times are rounded to the nearest second.

Figure 5

Equatorial density sections of reconstructions. For each data set, a comparison is shown between a 3D reconstruction determined from the particles in one micrograph and the 3D reconstruction from all the particles available. The relative contrast of the reconstructions is the same as that used for Figure 3 (i.e. high density features appear darker than the surrounding background). Bar, 20 nm. Left column: central sections of the 3D reconstructions obtained from selected micrographs by AutoRTM. The number of particle images extracted automatically from each selected micrograph and how many of those agree with the particles selected manually by the user (in parenthesis) are noted at the bottom left of each panel. Right column: central sections of 3D reconstructions obtained from entire data sets of micrographs as originally processed by experienced users. The number of particle images used to compute each reconstruction is given at the bottom left of each panel.

Figure 6

Analysis of factors that affect success rate. (A, B) Success rate plotted against the number of iterations used to process ten initial random models. (C, D) Success rate plotted against the number of RMCs executed through ten iterations. In (A) and (C) the initial random models were generated from particle images picked automatically. In (B) and (D) the random models were generated from particle images identified manually in the micrographs.

Figure 7

Defocus error analysis. Histogram plot of defocus error estimated for each data set. The error is defined as the difference between the average defocus value estimated by an experienced user and the average defocus value obtained using the AutoRTM program. Note that the scale of the abscissa is different for each plot.

Figure 8

Particle detection analysis. Left column: plot of precision against recall for all the micrographs processed. A red ellipse is drawn for each data set centered at the average value for each measure, with semi-axes equal to the standard deviation. Right column: plots of precision against the average defocus as estimated by an experienced user. Note that the scale of the defocus axis is different for each plot.