Towards sub-millisecond cryo-EM grid preparation

Abstract

Sample preparation is still a significant problem for many single particle cryo-EM workflows and our understanding and developments in the area lag behind that of image processing and microscope design. Over the last few years there has been growing evidence that many of the problems which occur during sample preparation are during the time the sample resides within the thin film created during the conventional blotting process. In parallel, faster grid preparation approaches have been developed for time-resolved cryo-EM experiments allowing for non-equilibrium intermediates to be captured on the ms timescale. Therefore, an important question is how fast can we prepare suitable grids for imaging by cryo-EM and how much does this mitigate the problems observed in sample preparation? Here we use a novel approach which has been developed for time-resolved studies to produce grids on an estimated sub-1 ms timescale. While the method comes with its own challenges, a 3.8 Å reconstruction of apoferritin prepared with the ultrafast method shows that good resolutions can be achieved. Although several orders of magnitude faster than conventional approaches we show using a ribosome sample, that interactions with the air-water interface cannot be avoided with preferred orientations still present. Therefore, the work shows that faster reactions can be captured but poses the question whether speed is the answer to problems with sample preparation.

Fig. 1. Kinetic model of actomyosin dissociation. (a) Schematic and kinetic model. A-M = actomyosin, A-M-ATP = actomyosin–ATP complex, A = actin, M-ATP = myosin–ATP complex. F-actin is shown in grey, nucleotide free myosin shown in blue, ATP-bound myosin shown in pink. The A-M-ATP state is highlighted with a dashed line box. (b) Kinetic modelling of the reaction for 1 mM initial ATP concentration or (c) 0.1 mM initial ATP concentration. Modelling shows that high ATP concentration is needed to enrich the A-M-ATP state of interest, but also results in a faster overall reaction.

Fig. 2. Ultrafast cryo-EM grid preparation captures actomyosin before dissociation. (a) Raw micrograph of actomyosin mixed with 1 mM ATP. (b) Raw micrograph of actomyosin mixed with 2.5 mM ATP and apoferritin as a marker. The scale bars in (a) and (b) correspond to 50 nm. (c) 3D classification result from the 1 mM ATP data, showing clear separation into an actomyosin class (top) and actin class (bottom). (d) Relative actomyosin particle number in the 1 mM ATP and 2.5 mM ATP datasets, showing that only a small fraction of actomyosin complex has dissociated at the time of vitrification.

Fig. 3. Ultrafast cryo-EM grid preparation of apoferritin. (a) Representative micrograph of apoferritin prepared by ultrafast grid preparation. The scale bar corresponds to 50 nm. (b) Reconstruction of apoferritin at 3.8 Å resolution, coloured by subunit. (c) Fourier shell correlation (FSC) curve for the 3.8 Å apoferritin reconstruction, showing correlation between half-maps as solid black line, and correlation between the final map and PDB 6rjh as dotted black line. The 0.143 FSC threshold is marked as dashed red line, the 0.5 FSC threshold as dashed yellow line.

Fig. 4. Ribosome orientations from ultrafast grid preparation. Reconstruction and angular orientation in Mollweide projection for (a) 70S, (b) 50S and (c) 30S ribosome particles. The density of angular orientations is indicated by colour, high density (probability) is shown in yellow, low density in dark blue.