PIXER: an automated particle-selection method based on segmentation using a deep neural network

Abstract

Background: Cryo-electron microscopy (cryo-EM) has become a widely used tool for determining the structures of proteins and macromolecular complexes. To acquire the input for single-particle cryo-EM reconstruction, researchers must select hundreds of thousands of particles from micrographs. As the signal-to-noise ratio (SNR) of micrographs is extremely low, the performance of automated particle-selection methods is still unable to meet research requirements. To free researchers from this laborious work and to acquire a large number of high-quality particles, we propose an automated particle-selection method (PIXER) based on the idea of segmentation using a deep neural network.

Results: First, to accommodate low-SNR conditions, we convert micrographs into probability density maps using a segmentation network. These probability density maps indicate the likelihood that each pixel of a micrograph is part of a particle instead of just background noise. Particles selected from density maps have a more robust signal than do those directly selected from the original noisy micrographs. Second, at present, there is no segmentation-training dataset for cryo-EM. To enable our plan, we present an automated method to generate a training dataset for segmentation using real-world data. Third, we propose a grid-based, local-maximum method to locate the particles from the probability density maps. We tested our method on simulated and real-world experimental datasets and compared PIXER with the mainstream methods RELION, DeepEM and DeepPicker to demonstrate its performance. The results indicate that, as a fully automated method, PIXER can acquire results as good as the semi-automated methods RELION and DeepEM.

Conclusion: To our knowledge, our work is the first to address the particle-selection problem using the segmentation network concept. As a fully automated particle-selection method, PIXER can free researchers from laborious particle-selection work. Based on the results of experiments, PIXER can acquire accurate results under low-SNR conditions within minutes.

Keywords: Cryo-electron microscope; Deep learning; Particle selection; Segmentation; Single-particle analysis.

Fig. 1

The general workflow of the training and test processes of PIXER. The blue part of the image shows the training process for segmentation and classification network. The red part of the image shows the general flow of the test process. The test process works as follows: ①feed micrographs into the segmentation network; ② acquire probability density maps from the network; ③feed density maps to a selection algorithm; ④ generate the preliminary particle coordinates from probability density maps; ⑤ feed the preliminary results into the classification network; and ⑥ generate the results after removing false positive particles

Fig. 2

Illustrations of the PIXER methods. (a) The architecture of the classification and segmentation networks. (b) Workflow of generating training data for segmentation. ① Select particles from micrographs. The coordinates can come from manual or semi-manual particle selection software. ② Perform reconstruction using mainstream software, such as RELION and EMAN. Record the fine-tuned Euler angles and translation parameters. ③ Generate corresponding re-projection images for each particle. ④ Adjust the coordinates based on the translation parameters. ⑤ Fit these re-projection images back into the label image of each micrograph. (c) Procedure for the grid-based, local-maximum particle-selection method. Step 1: Generate the maximum value for each grid. Steps 2 and 3: Perform a parallel local-maximum searching method to locate local-maximum values during the iteration. Step 4: Select the local-maximum results

Fig. 3

Examples of three different kinds of visual features. (a) Examples of particles. (b) Examples of interference factors. (c) Examples of noise images

Fig. 4

Examples of the training data for segmentation. (a) Examples of particles. (b) Corresponding segmentation results

Fig. 5

Performance of the 5 segmentation networks. To choose the appropriate number of parallel Atrous channels for the segmentation network, we trained five different networks separately. The number of parallel Atrous channels these networks are 1 to 5, respectively. In order to control variables, the training dataset, initial parameters from the classification network and all the meta-parameters (except the number of parallel Atrous channels) of these five networks are the same. We test the performance of the five segmentation networks with 5000 randomly selected micrographs 512*512 pixels in size from the data shown in Table 1 to form a validation dataset. We used intersection-over-union ($\mathit{IOU}=\frac{\mathit{\text{GroundTruth}}\cap \mathit{\text{Segmentation Result}}}{\mathit{\text{GroundTruth}}\cup \mathit{\text{Segmentation Result}}}$) statistical results to judge the performance

Fig. 6

Examples of the segmentation results. (a) Examples from GroEL. (b) Examples from EMPAIR-10028. (c) Examples from EMPIAR-10081

Fig. 7

Four representative intermediate results of the grid-based, local-maximum method using one whole micrograph from dataset TRPV (EMPIAR-10005)

Fig. 8

The converged result of the grid-based, local-maximum method of the micrograph from dataset TRPV1 (EMPIAR-10005) [26]. The different colors indicate different levels of particle scores using the same color bar as Fig. 7

Fig. 9

Experiments on simulated data. (a) Example of micrographs including the original micrograph, heat map of probability, binarized segmentation results and final coordinates. (b) Detailed IOU results of 45 micrographs. (c) The IOU results of our method on the simulated data with different SNRs. Here the SNR is defined as $\mathit{SNR}=10{\mathit{log}}_{10}\left(\frac{\sum _{x=0}^N\sum _{y=0}^M\widehat{f}{\left(x,y\right)}^2}{\sum _{x=0}^N\sum _{y=0}^M{\left[f\left(x,y\right)-\widehat{f}\left(x,y\right)\right]}^2}\right)$, where $\widehat{f}\left(x,y\right)$ is the signal of simulated data generated from InSilicoTEM with no noise, and f(x, y) is the simulated data with noise

Fig. 10

Examples of results for the bacteriophage MS2 and TRPV1. (a) Probability density map and the corresponding binarized segmentation results of bacteriophage MS2. (b) Probability density map and the corresponding binarized segmentation results of TRPV1. (c) Example of particle-selection results from the PIXER and RELION methods on bacteriophage MS2. Circles and rectangles indicate results from PIXER and RELION, respectively. The red and blue crosses in Fig. 10c show the FP particles for PIXER and RELION, respectively. (D) Example of the particle-selection results from the DeepPicker and PIXER methods on TRPV1. We use circles and rectangles to denote results from PIXER and DeepPicker, respectively. We also used blue crosses to indicate the FP results of DeepPicker

Fig. 11

Quantity analysis on real datasets using a precision-recall curve. (a) Bacteriophage MS2. (“Precision After Segment” indicates the preliminary results outputted by the segmentation network of PIXER, which haven’t been filtered by classification network.) (b) TRPV1. (c) KLH. (d) Rabbit muscle aldolase