cryo-EM Images Research Articles

Semantic segmentation-based detection algorithm for challenging cryo-electron microscopy RNP samples.

In this study, we present a novel and robust methodology for the automatic detection of influenza A virus ribonucleoproteins (RNPs) in single-particle cryo-electron microscopy (cryo-EM) images. Utilizing a U-net architecture-a type of convolutional neural network renowned for its efficiency in biomedical image segmentation-our approach is based on a pretraining phase with a dataset annotated through visual inspection. This dataset facilitates the precise identification of filamentous RNPs, including the localization of the filaments and their terminal coordinates. A key feature of our method is the application of semantic segmentation techniques, enabling the automated categorization of micrograph pixels into distinct classifications of particle and background. This deep learning strategy allows to robustly detect these intricate particles, a crucial step in achieving high-resolution reconstructions in cryo-EM studies. To encourage collaborative advancements in the field, we have made our routines, the pretrained U-net model, and the training dataset publicly accessible. The reproducibility and accessibility of these resources aim to facilitate further research and validation in the realm of cryo-EM image analysis.

DynaMight: estimating molecular motions with improved reconstruction from cryo-EM images

How to deal with continuously flexing molecules is one of the biggest outstanding challenges in single-particle analysis of proteins from cryogenic-electron microscopy (cryo-EM) images. Here, we present DynaMight, a software tool that estimates a continuous space of conformations in a cryo-EM dataset by learning three-dimensional deformations of a Gaussian pseudo-atomic model of a consensus structure for every particle image. Inversion of the learned deformations is then used to obtain an improved reconstruction of the consensus structure. We illustrate the performance of DynaMight for several experimental cryo-EM datasets. We also show how error estimates on the deformations may be obtained by independently training two variational autoencoders on half sets of the cryo-EM data, and how regularization of the three-dimensional deformations through the use of atomic models may lead to important artifacts due to model bias. DynaMight is distributed as free, open-source software, as part of RELION-5.

SPOT-RASTR-A cryo-EM specimen preparation technique that overcomes problems with preferred orientation and the air/water interface.

In cryogenic electron microscopy (cryo-EM), specimen preparation remains a bottleneck despite recent advancements. Classical plunge freezing methods often result in issues like aggregation and preferred orientations at the air/water interface. Many alternative methods have been proposed, but there remains a lack a universal solution, and multiple techniques are often required for challenging samples. Here, we demonstrate the use of lipid nanotubes with nickel NTA headgroups as a platform for cryo-EM sample preparation. His-tagged specimens of interest are added to the tubules, and they can be frozen by conventional plunge freezing. We show that the nanotubes protect samples from the air/water interface and promote a wider range of orientations. The reconstruction of average subtracted tubular regions (RASTR) method allows for the removal of the nanotubule signal from the cryo-EM images resulting in isolated images of specimens of interest. Testing with β-galactosidase validates the method's ability to capture particles at lower concentrations, overcome preferred orientations, and achieve near-atomic resolution reconstructions. Since the nanotubules can be identified and targeted automatically at low magnification, the method enables fully automated data collection. Furthermore, the particles on the tubes can be automatically identified and centered using 2D classification enabling particle picking without requiring prior information. Altogether, our approach that we call specimen preparation on a tube RASTR holds promise for overcoming air-water interface and preferred orientation challenges and offers the potential for fully automated cryo-EM data collection and structure determination.

Reconstruction and identification of the native PLP synthase complex from Methanosarcina acetivorans lysate.

Many protein-protein interactions behave differently in biochemically purified forms as compared to their in vivo states. As such, determining native protein structures may elucidate structural states previously unknown for even well-characterized proteins. Here we apply the bottom-up structural proteomics method, cryoID , toward a model methanogenic archaeon. While they are keystone organisms in the global carbon cycle and active members of the human microbiome, there is a general lack of characterization of methanogen enzyme structure and function. Through the cryoID approach, we successfully reconstructed and identified the native Methanosarcina acetivorans pyridoxal 5'-phosphate (PLP) synthase (PdxS) complex directly from cryogenic electron microscopy (cryoEM) images of fractionated cellular lysate. We found that the native PdxS complex exists as a homo-dodecamer of PdxS subunits, and the previously proposed supracomplex containing both the synthase (PdxS) and glutaminase (PdxT) was not observed in cellular lysate. Our structure shows that the native PdxS monomer fashions a single 8α/8β TIM-barrel domain, surrounded by seven additional helices to mediate solvent and interface contacts. A density is present at the active site in the cryoEM map and is interpreted as ribose 5-phosphate. In addition to being the first reconstruction of the PdxS enzyme from a heterogeneous cellular sample, our results reveal a departure from previously published archaeal PdxS crystal structures, lacking the 37 amino acid insertion present in these prior cases. This study demonstrates the potential of applying the cryoID workflow to capture native structural states at atomic resolution for archaeal systems, for which traditional biochemical sample preparation is nontrivial.

Determining Protein Secondary Structures in Heterogeneous Medium-Resolution Cryo-EM Images Using CryoSSESeg.

While the acquisition of cryo-electron microscopy (cryo-EM) at near-atomic resolution is becoming more prevalent, a considerable number of density maps are still resolved only at intermediate resolutions (5-10 Å). Due to the large variation in quality among these medium-resolution density maps, extracting structural information from them remains a challenging task. This study introduces a convolutional neural network (CNN)-based framework, cryoSSESeg, to determine the organization of protein secondary structure elements in medium-resolution cryo-EM images. CryoSSESeg is trained on approximately 1300 protein chains derived from around 500 experimental cryo-EM density maps of varied quality. It demonstrates strong performance with residue-level F 1 scores of 0.76 for helix detection and 0.60 for β-sheet detection on average across a set of testing chains. In comparison to traditional image processing tools like SSETracer, which demand significant manual intervention and preprocessing steps, cryoSSESeg demonstrates comparable or superior performance. Additionally, it demonstrates competitive performance alongside another deep learning-based model, Emap2sec. Furthermore, this study underscores the importance of secondary structure quality, particularly adherence to expected shapes, in detection performance, emphasizing the necessity for careful evaluation of the data quality.

CLEAPA: a framework for exploring the conformational landscape of cryo-EM using energy-aware pathfinding algorithm.

Cryo-electron microscopy (cryo-EM) is a powerful technique for studying macromolecules and holds the potential for identifying kinetically preferred transition sequences between conformational states. Typically, these sequences are explored within two-dimensional energy landscapes. However, due to the complexity of biomolecules, representing conformational changes in two dimensions can be challenging. Recent advancements in reconstruction models have successfully extracted structural heterogeneity from cryo-EM images using higher-dimension latent space. Nonetheless, creating high-dimensional conformational landscapes in the latent space and then searching for preferred paths continues to be a formidable task. This study introduces an innovative framework for identifying preferred trajectories within high-dimensional conformational landscapes. Our method encompasses the search for the minimum energy path in the graph, where edge weights are determined based on the energy estimation at each node using local density. The effectiveness of this approach is demonstrated by identifying accurate transition states in both synthetic and real-world datasets featuring continuous conformational changes. The CLEAPA package is available at https://github.com/tengyulin/energy_aware_pathfinding/.

CryoSegNet: accurate cryo-EM protein particle picking by integrating the foundational AI image segmentation model and attention-gated U-Net.

Picking protein particles in cryo-electron microscopy (cryo-EM) micrographs is a crucial step in the cryo-EM-based structure determination. However, existing methods trained on a limited amount of cryo-EM data still cannot accurately pick protein particles from noisy cryo-EM images. The general foundational artificial intelligence-based image segmentation model such as Meta's Segment Anything Model (SAM) cannot segment protein particles well because their training data do not include cryo-EM images. Here, we present a novel approach (CryoSegNet) of integrating an attention-gated U-shape network (U-Net) specially designed and trained for cryo-EM particle picking and the SAM. The U-Net is first trained on a large cryo-EM image dataset and then used to generate input from original cryo-EM images for SAM to make particle pickings. CryoSegNet shows both high precision and recall in segmenting protein particles from cryo-EM micrographs, irrespective of protein type, shape and size. On several independent datasets of various protein types, CryoSegNet outperforms two top machine learning particle pickers crYOLO and Topaz as well as SAM itself. The average resolution of density maps reconstructed from the particles picked by CryoSegNet is 3.33Å, 7% better than 3.58Å of Topaz and 14% better than 3.87Å of crYOLO. It is publicly available at https://github.com/jianlin-cheng/CryoSegNet.

Structure and conformational variability of the HER2-trastuzumab-pertuzumab complex

Single particle analysis from cryogenic transmission electron microscopy (cryo-EM) is particularly attractive for complexes for which structure prediction remains intractable, such as antibody-antigen complexes. Here we obtain the detailed structure of a particularly difficult complex between human epidermal growth factor receptor 2 (HER2) and the antigen-binding fragments from two distinct therapeutic antibodies binding to distant parts of the flexible HER2, pertuzumab and trastuzumab (HTP). We highlight the strengths and limitations of current data processing software in dealing with various kinds of heterogeneities, particularly continuous conformational heterogeneity, and in describing the motions that can be extracted from our dataset. Our HTP structure provides a more detailed view than the one previously available for this ternary complex. This allowed us to pinpoint a previously overlooked loop in domain IV that may be involved both in binding of trastuzumab and in HER2 dimerization. This finding may contribute to explain the synergistic anticancer effect of the two antibodies. We further propose that the flexibility of the HTP complex, beyond the difficulties it causes for cryo-EM analysis, actually reflects regulation of HER2 signaling and its inhibition by therapeutic antibodies. Notably we obtain our best data with ultra-thin continuous carbon grids, showing that with current cameras their use to alleviate particle misdistribution is compatible with a protein complex of only 162 kDa. Perhaps most importantly, we provide here a dataset for such a smallish protein complex for further development of software accounting for continuous conformational heterogeneity in cryo-EM images.

Cryo-EM images of phase-separated lipid bilayer vesicles analyzed with a machine-learning approach

Lateral lipid heterogeneity (i.e., raft formation) in biomembranes plays a functional role in living cells. Three-component mixtures of low- and high-melting lipids plus cholesterol offer a simplified experimental model for raft domains in which a liquid-disordered (Ld) phase coexists with a liquid-ordered (Lo) phase. Using such models, we recently showed that cryogenic electron microscopy (cryo-EM) can detect phase separation in lipid vesicles based on differences in bilayer thickness. However, the considerable noise within cryo-EM data poses a significant challenge for accurately determining the membrane phase state at high spatial resolution. To this end, we have developed an image-processing pipeline that utilizes machine learning (ML) to predict the bilayer phase in projection images of lipid vesicles. Importantly, the ML method exploits differences in both the thickness and molecular density of Lo compared to Ld, which leads to improved phase identification. To assess accuracy, we used artificial images of phase-separated lipid vesicles generated from all-atom molecular dynamics simulations of Lo and Ld phases. Synthetic ground-truth data sets mimicking a series of compositions along a tieline of Ld + Lo coexistence were created and then analyzed with various ML models. For all tieline compositions, we find that the ML approach can correctly identify the bilayer phase with >90% accuracy, thus providing a means to isolate the intensity profiles of coexisting Ld and Lo phases, as well as accurately determine domain-size distributions, number of domains, and phase-area fractions. The method described here provides a framework for characterizing nanoscopic lateral heterogeneities in membranes and paves the way for a more detailed understanding of raft properties in biological contexts.

Drug-induced transitions from micelles to vesicles in ionic surfactant solutions

Surfactant solutions play key roles in scientific research and technological applications. Here we investigated solutions that combined an ionic surfactant, Cetylpyridinium Chloride (CPyCl), with a non-steroidal, anti-inflammatory drug, Sodium Diclofenac (Diclo). The study covered a wide range of compositions and utilized both rheology and cryogenic-Electron Microscopy (cryo-EM). The solutions were prepared at three different concentrations of CPyCl: 5.0 mM, 16.7 mM and 33.0 mM, and we maintained the ratio of surfactant to salt, R=CPyCl/Diclo, within the range of 0.24<R<1.2. Linear viscoelasticity was measured at 25°C. The use of dilute solutions allowed for detailed cryo-EM imaging. By tracking the evolution of the zero-frequency viscosity as a function of Diclo concentration, we identified distinct regions of different rheological responses. The correlation between frequency sweep data and cryo-EM images enabled us to link these regions to specific morphological transitions ranging from spherical micelles to long and entangled wormlike micelles, to branched networks and, eventually, to perforated vesicles. For some systems, we were able to measure the complete spectrum of relaxation times, including the shortest characteristic Rouse time at high frequencies, previously only achieved by Diffusive Wave Spectroscopy. The use of existing models to evaluate the relevant important microstructural parameters such as entanglement, contour, and persistence lengths allowed us to establish a clear correlation between the microstructural parameters derived through rheology and the insights from the cryo-EM analysis.

Cryo-forum: A framework for orientation recovery with uncertainty measure with the application in cryo-EM image analysis

In single-particle cryo-electron microscopy (cryo-EM), efficient determination of orientation parameters for particle images poses a significant challenge yet is crucial for reconstructing 3D structures. This task is complicated by the high noise levels in the datasets, which often include outliers, necessitating several time-consuming 2D clean-up processes. Recently, solutions based on deep learning have emerged, offering a more streamlined approach to the traditionally laborious task of orientation estimation. These solutions employ amortized inference, eliminating the need to estimate parameters individually for each image. However, these methods frequently overlook the presence of outliers and may not adequately concentrate on the components used within the network. This paper introduces a novel approach that uses a 10-dimensional feature vector to represent the orientation and applies a Quadratically-Constrained Quadratic Program to derive the predicted orientation as a unit quaternion, supplemented by an uncertainty metric. Furthermore, we propose a unique loss function that considers the pairwise distances between orientations, thereby enhancing the accuracy of our method. Finally, we also comprehensively evaluate the design choices in constructing the encoder network, a topic that has not received sufficient attention in the literature. Our numerical analysis demonstrates that our methodology effectively recovers orientations from 2D cryo-EM images in an end-to-end manner. Notably, the inclusion of uncertainty quantification allows for direct clean-up of the dataset at the 3D level. Lastly, we package our proposed methods into a user-friendly software suite named cryo-forum, designed for easy access by developers.

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

BackgroundCryo-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.ResultsAiming 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.ConclusionsSimcryoCluster 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

Structure of Amyloid Peptide Ribbons Characterized by Electron Microscopy, Atomic Force Microscopy, and Solid-State Nuclear Magnetic Resonance.

Polypeptides often self-assemble to form amyloid fibrils, which contain cross-β structural motifs and are typically 5-15 nm in width and micrometers in length. In many cases, short segments of longer amyloid-forming protein or peptide sequences also form cross-β assemblies but with distinctive ribbon-like morphologies that are characterized by a well-defined thickness (on the order of 5 nm) in one lateral dimension and a variable width (typically 10-100 nm) in the other. Here, we use a novel combination of data from solid-state nuclear magnetic resonance (ssNMR), dark-field transmission electron microscopy (TEM), atomic force microscopy (AFM), and cryogenic electron microscopy (cryoEM) to investigate the structures within amyloid ribbons formed by residues 14-23 and residues 11-25 of the Alzheimer's disease-associated amyloid-β peptide (Aβ14-23 and Aβ11-25). The ssNMR data indicate antiparallel β-sheets with specific registries of intermolecular hydrogen bonds. Mass-per-area values are derived from dark-field TEM data. The ribbon thickness is determined from AFM images. For Aβ14-23 ribbons, averaged cryoEM images show a periodic spacing of β-sheets. The combined data support structures in which the amyloid ribbon growth direction is the direction of intermolecular hydrogen bonds between β-strands, the ribbon thickness corresponds to the width of one β-sheet (i.e., approximately the length of one molecule), and the variable ribbon width is a variable multiple of the thickness of one β-sheet (i.e., a multiple of the repeat distance in a stack of β-sheets). This architecture for a cross-β assembly may generally exist within amyloid ribbons.

Using machine learning to characterize the structure of coexisting liquid-ordered and liquid-disordered phases from cryo-EM images of lipid vesicles

Using machine learning to characterize the structure of coexisting liquid-ordered and liquid-disordered phases from cryo-EM images of lipid vesicles

Orientation Determination of Cryo-EM Projection Images Using Reliable Common Lines and Spherical Embeddings.

Three-dimensional (3D) reconstruction in single-particle cryo-electron microscopy (cryo-EM) is a critical technique for recovering and studying the fine 3D structure of proteins and other biological macromolecules, where the primary issue is to determine the orientations of projection images with high levels of noise. This paper proposes a method to determine the orientations of cryo-EM projection images using reliable common lines and spherical embeddings. First, the reliability of common lines between projection images is evaluated using a weighted voting algorithm based on an iterative improvement technique and binarized weighting. Then, the reliable common lines are used to calculate the normal vectors and local X-axis vectors of projection images after two spherical embeddings. Finally, the orientations of projection images are determined by aligning the results of the two spherical embeddings using an orthogonal constraint. Experimental results on both synthetic and real cryo-EM projection image datasets demonstrate that the proposed method can achieve higher accuracy in estimating the orientations of projection images and higher resolution in reconstructing preliminary 3D structures than some common line-based methods, indicating that the proposed method is effective in single-particle cryo-EM 3D reconstruction.

Phase separation in model lipid membranes investigated with cryogenic electron microscopy.

We describe a method for investigating lateral membrane heterogeneity using cryogenic electron microscopy (cryo-EM) images of liposomes. The method takes advantage of differences in the thickness and molecular density of ordered and disordered phases that are resolvable in phase contrast cryo-EM. Compared to biophysical techniques like FRET or neutron scattering that yield ensemble-averaged information, cryo-EM provides direct visualization of individual vesicles and can therefore reveal variability that would otherwise be obscured by averaging. Moreover, because the contrast mechanism involves inherent properties of the lipid phases themselves, no extrinsic probes are required. We explain and discuss various complementary analyses of spatially resolved thickness and intensity measurements that enable an assessment of the membrane's phase state. The method opens a window to nanodomain structure in synthetic and biological membranes that should lead to an improved understanding of lipid raft phenomena.

Joint micrograph denoising and protein localization in cryo-electron microscopy

Abstract Cryo-electron microscopy (cryo-EM) is an imaging technique that allows the visualization of proteins and macromolecular complexes at near-atomic resolution. The low electron doses used to prevent radiation damage to the biological samples result in images where the power of noise is 100 times stronger than that of the signal. Accurate identification of proteins from these low signal-to-noise ratio (SNR) images is a critical task, as the detected positions serve as inputs for the downstream 3D structure determination process. Current methods either fail to identify all true positives or result in many false positives, especially when analyzing images from smaller-sized proteins that exhibit extremely low contrast, or require manual labeling that can take days to complete. Acknowledging the fact that accurate protein identification is dependent upon the visual interpretability of micrographs, we propose a framework that can perform denoising and detection in a joint manner and enable particle localization under extremely low SNR conditions using self-supervised denoising and particle identification from sparsely annotated data. We validate our approach on three challenging single-particle cryo-EM datasets and projection images from one cryo-electron tomography dataset with extremely low SNR, showing that it outperforms existing state-of-the-art methods used for cryo-EM image analysis by a significant margin. We also evaluate the performance of our algorithm under decreasing SNR conditions and show that our method is more robust to noise than competing methods.

Biophysical and structural characterization of a multifunctional viral genome packaging motor.

The large dsDNA viruses replicate their DNA as concatemers consisting of multiple covalently linked genomes. Genome packaging is catalyzed by a terminase enzyme that excises individual genomes from concatemers and packages them into preassembled procapsids. These disparate tasks are catalyzed by terminase alternating between two distinct states-a stable nuclease that excises individual genomes and a dynamic motor that translocates DNA into the procapsid. It was proposed that bacteriophage λ terminase assembles as an anti-parallel dimer-of-dimers nuclease complex at the packaging initiation site. In contrast, all characterized packaging motors are composed of five terminase subunits bound to the procapsid in a parallel orientation. Here, we describe biophysical and structural characterization of the λ holoenzyme complex assembled in solution. Analytical ultracentrifugation, small angle X-ray scattering, and native mass spectrometry indicate that 5 subunits assemble a cone-shaped terminase complex. Classification of cryoEM images reveals starfish-like rings with skewed pentameric symmetry and one special subunit. We propose a model wherein nuclease domains of two subunits alternate between a dimeric head-to-head arrangement for genome maturation and a fully parallel arrangement during genome packaging. Given that genome packaging is strongly conserved in both prokaryotic and eukaryotic viruses, the results have broad biological implications.

Classification of helical polymers with deep-learning language models

Many macromolecules in biological systems exist in the form of helical polymers. However, the inherent polymorphism and heterogeneity of samples complicate the reconstruction of helical polymers from cryo-EM images. Currently, available 2D classification methods are effective at separating particles of interest from contaminants, but they do not effectively differentiate between polymorphs, resulting in heterogeneity in the 2D classes. As such, it is crucial to develop a method that can computationally divide a dataset of polymorphic helical structures into homogenous subsets. In this work, we utilized deep-learning language models to embed the filaments as vectors in hyperspace and group them into clusters. Tests with both simulated and experimental datasets have demonstrated that our method – HLM (Helical classification with Language Model) can effectively distinguish different types of filaments, in the presence of many contaminants and low signal-to-noise ratios. We also demonstrate that HLM can isolate homogeneous subsets of particles from a publicly available dataset, resulting in the discovery of a previously unreported filament variant with an extra density around the tau filaments.

Computational models of amorphous ice for accurate simulation of cryo-EM images of biological samples

Simulations of cryo-electron microscopy (cryo-EM) images of biological samples can be used to produce test datasets to support the development of instrumentation, methods, and software, as well as to assess data acquisition and analysis strategies. To be useful, these simulations need to be based on physically realistic models which include large volumes of amorphous ice. The gold standard model for EM image simulation is a physical atom-based ice model produced using molecular dynamics simulations. Although practical for small sample volumes; for simulation of cryo-EM data from large sample volumes, this can be too computationally expensive. We have evaluated a Gaussian Random Field (GRF) ice model which is shown to be more computationally efficient for large sample volumes. The simulated EM images are compared with the gold standard atom-based ice model approach and shown to be directly comparable. Comparison with experimentally acquired data shows the Gaussian random field ice model produces realistic simulations. The software required has been implemented in the Parakeet software package and the underlying atomic models are available online for use by the wider community.