Simcryocluster: a semantic similarity clustering method of cryo-EM images by adopting contrastive learning.

BACKGROUND: Cryo-electron microscopy (Cryo-EM) plays an increasingly important role in the determination of the three-dimensional (3D) structure of macromolecules. In order to achieve 3D reconstruction results close to atomic resolution, 2D single-particle image classification is not only conducive to single-particle selection, but also a key step that affects 3D reconstruction. The main task is to cluster and align 2D single-grain images into non-heterogeneous groups to obtain sharper single-grain images by averaging calculations. The main difficulties are that the cryo-EM single-particle image has a low signal-to-noise ratio (SNR), cannot manually label the data, and the projection direction is random and the distribution is unknown. Therefore, in the low SNR scenario, how to obtain the characteristic information of the effective particles, improve the clustering accuracy, and thus improve the reconstruction accuracy, is a key problem in the 2D image analysis of single particles of cryo-EM. RESULTS: Aiming at the above problems, we propose a learnable deep clustering method and a fast alignment weighted averaging method based on frequency domain space to effectively improve the class averaging results and improve the reconstruction accuracy. In particular, it is very prominent in the feature extraction and dimensionality reduction module. Compared with the classification method based on Bayesian and great likelihood, a large amount of single particle data is required to estimate the relative angle orientation of macromolecular single particles in the 3D structure, and we propose that the clustering method shows good results. CONCLUSIONS: SimcryoCluster can use the contrastive learning method to perform well in the unlabeled high-noise cryo-EM single particle image classification task, making it an important tool for cryo-EM protein structure determination.

Signal enhancement for two-dimensional cryo-EM data processing.

Different tasks in the computational pipeline of single-particle cryo-electron microscopy (cryo-EM) require enhancing the quality of the highly noisy raw images. To this end, we develop an efficient algorithm for signal enhancement of cryo-EM images. The enhanced images can be used for a variety of downstream tasks, such as two-dimensional classification, removing uninformative images, constructing ab initio models, generating templates for particle picking, providing a quick assessment of the data set, dimensionality reduction, and symmetry detection. The algorithm includes built-in quality measures to assess its performance and alleviate the risk of model bias. We demonstrate the effectiveness of the proposed algorithm on several experimental data sets. In particular, we show that the quality of the resulting images is high enough to produce ab initio models of Å resolution. The algorithm is accompanied by a publicly available, documented, and easy-to-use code.

Accelerated 2D Classification With ISAC Using GPUs.

A widely used approach to analyze single particles in electron microscopy data is 2D classification. This process is very computationally expensive, especially when large data sets are analyzed. In this paper we present GPU ISAC, a newly developed, GPU-accelerated version of the established Iterative Stable Alignment and Clustering (ISAC) algorithm for 2D images and generating class averages. While the previously existing implementation of ISAC relied on a computer cluster, GPU ISAC enables users to produce high quality 2D class averages from large-scale data sets on a single desktop machine equipped with affordable, consumer-grade GPUs such as Nvidia GeForce GTX 1080 TI cards. With only two such cards GPU ISAC matches the performance of twelve high end cluster nodes and, using high performance GPUs, is able to produce class averages from a million particles in between six to thirteen hours, depending on data set quality and box size. We also show GPU ISAC to scale linearly in all input dimensions, and thereby capable of scaling well with the increasing data load demand of future data sets. Further user experience improvements integrate GPU ISAC seamlessly into the existing SPHIRE GUI, as well as the TranSPHIRE on-the-fly processing pipeline. It is open source and can be downloaded at https://gitlab.gwdg.de/mpi-dortmund/sphire/cuISAC/.

Expression, purification and microscopic characterization of human ATP-binding cassette sub-family B member 7 protein.

The ATP-binding cassette sub-family B member 7 (ABCB7) is a membrane transport protein located on the inner membrane of mitochondria, which could be involved in the transport of heme from the mitochondria to the cytosol. ABCB7 also plays a central role in the maturation of cytosolic iron-sulfur (Fe/S) cluster-containing proteins, and mutations can cause a series of mitochondrial defects. X-linked sideroblastic anemia and ataxia (XLSA-A) is a rare cause of early onset ataxia, which may be overlooked due to the usually mild asymptomatic anemia. The genetic defect has been identified as a mutation in the ABCB7 gene at Xq12-q13. Here, we report the expression, purification and the 2D projections derived from negatively stained electron micrographs of recombinant H. sapiens ABCB7 (hABCB7), paving the way from an atomic structure determination of ABCB7.

High-Throughput Protein Analysis Using Negative Stain Electron Microscopy and 2D Classification.

High-throughput protein expression and purification allows for fast triaging of several constructs based on expression levels, protein integrity, and solubility. While this technology has been successfully adopted to prioritize constructs for structural biology, it could not inform on important biochemical properties such as domain architecture, homogeneity, and flexibility. Negative staining electron microscopy can be used to quickly evaluate these properties and, if coupled to single particle analysis, can inform on the architecture and conformational state of nearly any protein sample. Here we describe a protocol for negative stain sample preparation, imaging, and two-dimensional (2D) data analysis applicable to a variety of protein complexes. We discuss in more detail a specific application of this technology to large molecule studies to determine the binding sites of individual antibodies on target antigens.

Clustering cryo-EM images of helical protein polymers for helical reconstructions.

Helical protein polymers are often dynamic and complex assemblies, with many conformations and flexible domains possible within the helical assembly. During cryo-electron microscopy reconstruction, classification of the image data into homogeneous subsets is a critical step for achieving high resolution, resolving different conformations and elucidating functional mechanisms. Hence, methods aimed at improving the homogeneity of these datasets are becoming increasingly important. In this paper, we introduce a new algorithm that uses results from 2D image classification to sort 2D classes into groups of similar helical polymers. We show that our approach is able to distinguish helical polymers that differ in conformation, composition, and helical symmetry. Our results on test and experimental cases - actin filaments and amyloid fibrils - illustrate how our approach can be useful to improve the homogeneity of a data set. This method is exclusively applicable to helical polymers and other limitations are discussed.

Rotationally invariant image representation for viewing direction classification in cryo-EM.

We introduce a new rotationally invariant viewing angle classification method for identifying, among a large number of cryo-EM projection images, similar views without prior knowledge of the molecule. Our rotationally invariant features are based on the bispectrum. Each image is denoised and compressed using steerable principal component analysis (PCA) such that rotating an image is equivalent to phase shifting the expansion coefficients. Thus we are able to extend the theory of bispectrum of 1D periodic signals to 2D images. The randomized PCA algorithm is then used to efficiently reduce the dimensionality of the bispectrum coefficients, enabling fast computation of the similarity between any pair of images. The nearest neighbors provide an initial classification of similar viewing angles. In this way, rotational alignment is only performed for images with their nearest neighbors. The initial nearest neighbor classification and alignment are further improved by a new classification method called vector diffusion maps. Our pipeline for viewing angle classification and alignment is experimentally shown to be faster and more accurate than reference-free alignment with rotationally invariant K-means clustering, MSA/MRA 2D classification, and their modern approximations.