DeepRes: a new deep-learning- and aspect-based local resolution method for electron-microscopy maps

Machine learning approaches to cryoEM density modification differentially affect biomacromolecule and ligand density quality

The application of machine learning to cryogenic electron microscopy (cryoEM) data analysis has added a valuable set of tools to the cryoEM data processing pipeline. As these tools become more accessible and widely available, the implications of their use should be assessed. We noticed that machine learning map modification tools can have differential effects on cryoEM densities. In this perspective, we evaluate these effects to show that machine learning tools generally improve densities for biomacromolecules while generating unpredictable results for ligands. This unpredictable behavior manifests both in quantitative metrics of map quality and in qualitative investigations of modified maps. The results presented here highlight the power and potential of machine learning tools in cryoEM, while also illustrating some of the risks of their unexamined use.

DeepETPicker: Fast and accurate 3D particle picking for cryo-electron tomography using weakly supervised deep learning

To solve three-dimensional structures of biological macromolecules in situ, large numbers of particles often need to be picked from cryo-electron tomograms. However, adoption of automated particle-picking methods remains limited because of their technical limitations. To overcome the limitations, we develop DeepETPicker, a deep learning model for fast and accurate picking of particles from cryo-electron tomograms. Training of DeepETPicker requires only weak supervision with low numbers of simplified labels, reducing the burden of manual annotation. The simplified labels combined with the customized and lightweight model architecture of DeepETPicker and accelerated pooling enable substantial performance improvement. When tested on simulated and real tomograms, DeepETPicker outperforms the competing state-of-the-art methods by achieving the highest overall accuracy and speed, which translate into higher authenticity and coordinates accuracy of picked particles and higher resolutions of final reconstruction maps. DeepETPicker is provided in open source with a user-friendly interface to support cryo-electron tomography in situ.

DeepQs: Local quality assessment of cryo-EM density map by deep learning map-model fit score

Cryogenic electron microscopy maps are valuable for determining macromolecule structures. A proper quality assessment method is essential for cryo-EM map selection or revision. This article presents DeepQs, a novel approach to estimate local quality for 3D cryo-EM density maps, using a deep-learning algorithm based on map-model fit score. DeepQs is a parameter-free method for users and incorporates structural information between map and its related atomic model into well-trained models by deep learning. More specifically, the DeepQs approach leverages the interplay between map and atomic model through predefined map-model fit score, Q-score. DeepQs can get close results to the ground truth map-model fit scores with only cryo-EM map as input. In experiments, DeepQs demonstrates the lowest root mean square error with standard method Fourier shell correlation metric and high correlation with map-model fit score, Q-score, when compared with other local quality estimation methods in high-resolution dataset (<=5 Å). DeepQs can also be applied to evaluate the quality of the post-processed maps. In both cases, DeepQs runs faster by using GPU acceleration. Our program is available at http://www.csbio.sjtu.edu.cn/bioinf/DeepQs for academic use.

Novel Artificial Intelligence-Based Approaches for Ab Initio Structure Determination and Atomic Model Building for Cryo-Electron Microscopy

Single particle cryo-electron microscopy (cryo-EM) has emerged as the prevailing method for near-atomic structure determination, shedding light on the important molecular mechanisms of biological macromolecules. However, the inherent dynamics and structural variability of biological complexes coupled with the large number of experimental images generated by a cryo-EM experiment make data processing nontrivial. In particular, ab initio reconstruction and atomic model building remain major bottlenecks that demand substantial computational resources and manual intervention. Approaches utilizing recent innovations in artificial intelligence (AI) technology, particularly deep learning, have the potential to overcome the limitations that cannot be adequately addressed by traditional image processing approaches. Here, we review newly proposed AI-based methods for ab initio volume generation, heterogeneous 3D reconstruction, and atomic model building. We highlight the advancements made by the implementation of AI methods, as well as discuss remaining limitations and areas for future development.

Local heterogeneity analysis of crystallographic and cryo-EM maps using shell-approximation

In X-ray crystallography and cryo-EM, experimental maps can be heterogeneous, showing different level of details in different regions. In this work we interpret heterogeneity in terms of two parameters, assigned individually for each atom, combining the conventional atomic displacement parameter with the resolution of the atomic image in the map. We propose a local real-space procedure to estimate the values of these heterogeneity parameters, assuming that a fragment of the density map and atomic positions are given. The procedure is based on an analytic representation of the atomic image, as a function of the inhomogeneity parameters and atomic coordinates. In this article, we report the results of the tests both with maps simulated and those derived from experimental data. For simulated maps containing regions with different resolutions, the method determines the local map resolution around the atomic centers and the values of the displacement parameter with reasonable accuracy. For experimental maps, obtained as a Fourier synthesis of a given global resolution, estimated values of the local resolution are close to the global one, and the values of the estimated displacement parameters are close to the respective values of the closest atoms in the refined model. Shown successful applications of the proposed method to experimental crystallographic and cryo-EM maps can be seen as a practical proof of method.

Recent breakthroughs in computational structural biology harnessing the power of sequences and structures

Recent advances in computational approaches and their integration into structural biology enable tackling increasingly complex questions. Here, we discuss several key areas, highlighting breakthroughs and remaining challenges. Theoretical modeling has provided tools to accurately predict and design protein structures on a scale currently difficult to achieve using experimental approaches. Molecular Dynamics simulations have become faster and more precise, delivering actionable information inaccessible by current experimental methods. Virtual screening workflows allow a high-throughput approach to discover ligands that bind and modulate protein function, while Machine Learning methods enable the design of proteins with new functionalities. Integrative structural biology combines several of these approaches, pushing the frontiers of structural and functional characterization to ever larger systems, advancing towards a complete understanding of the living cell. These breakthroughs will accelerate and significantly impact diverse areas of science.

CryoRes: Local Resolution Estimation of Cryo-EM Density Maps by Deep Learning

Recent progress in cryo-EM research has ignited a revolution in biological macromolecule structure determination. Resolution is an essential parameter for quality assessment of a cryo-EM density map, and it is known that resolution varies in different regions of a map. Currently available methods for local resolution estimation require manual adjustment of parameters and in some cases necessitate acquisition or de novo generation of so-called "half maps". Here, we developed CryoRes, a deep-learning algorithm to estimate local resolution directly from a single final cryo-EM density map, specifically by learning resolution-aware patterns of density map voxels through supervised training on a large dataset comprising 1,174 experimental cryo-EM density maps. CryoRes significantly outperforms all of the state-of-the-art competing resolution estimation methods, achieving an average RMSE of 2.26 Å for local resolution estimation relative to the currently most reliable FSC-based method blocres, yet requiring only the single final map as input. Further, CryoRes is able to generate a molecular mask for each map, with accuracy 12.12% higher than the masks generated by ResMap. CryoRes is ultra-fast, fully automatic, parameter-free, applicable to cryo-EM subtomogram data, and freely available at https://cryores.zhanglab.net.

Multiple-image super-resolution of cryo-electron micrographs based on deep internal learning

Single-particle cryo-electron microscopy (cryo-EM) is a powerful imaging modality capable of visualizing proteins and macromolecular complexes at near-atomic resolution. The low electron-doses used to prevent radiation damage to the biological samples, however, result in images where the power of the noise is 100 times greater than the power of the signal. To overcome these low signal-to-noise ratios (SNRs), hundreds of thousands of particle projections are averaged to determine the three-dimensional structure of the molecule of interest. The sampling requirements of high-resolution imaging impose limitations on the pixel sizes that can be used for acquisition, limiting the size of the field of view and requiring data collection sessions of several days to accumulate sufficient numbers of particles. Meanwhile, recent image super-resolution (SR) techniques based on neural networks have shown state-of-the-art performance on natural images. Building on these advances, here, we present a multiple-image SR algorithm based on deep internal learning designed specifically to work under low-SNR conditions. Our approach leverages the internal image statistics of cryo-EM movies and does not require training on ground-truth data. When applied to single-particle datasets of apoferritin and T20S proteasome, we show that the resolution of the 3D structure obtained from SR micrographs can surpass the limits imposed by the imaging system. Our results indicate that the combination of low magnification imaging with in silico image SR has the potential to accelerate cryo-EM data collection by virtue of including more particles in each exposure and doing so without sacrificing resolution.

Cryo-EM reveals the molecular basis oflaminin polymerization and LN-lamininopathies

Laminin polymerization is the major step in basement membranes assembly. Its failures cause laminin N-terminal domain lamininopathies including Pierson syndrome. We have employed cryo-electron microscopy to determine a 3.7 Å structure of the trimeric laminin polymer node containing α1, β1 and γ1 subunits. The structure reveals the molecular basis of calcium-dependent formation of laminin lattice, and provides insights into polymerization defects manifesting in human disease.

Cryo-EM structure of Shiga toxin 2 in complex with the native ribosomal P-stalk reveals residues involved in the binding interaction

Shiga toxin 2a (Stx2a) is the virulence factor of enterohemorrhagic Escherichia coli. The catalytic A1 subunit of Stx2a (Stx2A1) interacts with the ribosomal P-stalk for loading onto the ribosome and depurination of the sarcin-ricin loop, which halts protein synthesis. Because of the intrinsic flexibility of the P-stalk, a structure of the Stx2a-P-stalk complex is currently unknown. We demonstrated that the native P-stalk pentamer binds to Stx2a with nanomolar affinity, and we employed cryo-EM to determine a structure of the 72 kDa Stx2a complexed with the P-stalk. The structure identifies Stx2A1 residues involved in binding and reveals that Stx2a is anchored to the P-stalk via only the last six amino acids from the C-terminal domain of a single P-protein. For the first time, the cryo-EM structure shows the loop connecting Stx2A1 and Stx2A2, which is critical for activation of the toxin. Our principal component analysis of the cryo-EM data reveals the intrinsic dynamics of the Stx2a-P-stalk interaction, including conformational changes in the P-stalk binding site occurring upon complex formation. Our computational analysis unveils the propensity for structural rearrangements within the C-terminal domain, with its C-terminal six amino acids transitioning from a random coil to an α-helix upon binding to Stx2a. In conclusion, our cryo-EM structure sheds new light into the dynamics of the Stx2a-P-stalk interaction and indicates that the binding interface between Stx2a and the P-stalk is the potential target for drug discovery.

Image processing tools for the validation of CryoEM maps

The number of maps deposited in public databases (Electron Microscopy Data Bank, EMDB) determined by cryo-electron microscopy has quickly grown in recent years. With this rapid growth, it is critical to guarantee their quality. So far, map validation has primarily focused on the agreement between maps and models. From the image processing perspective, the validation has been mostly restricted to using two half-maps and the measurement of their internal consistency. In this article, we suggest that map validation can be taken much further from the point of view of image processing if 2D classes, particles, angles, coordinates, defoci, and micrographs are also provided. We present a progressive validation scheme that qualifies a result validation status from 0 to 5 and offers three optional qualifiers (A, W, and O) that can be added. The simplest validation state is 0, while the most complete would be 5AWO. This scheme has been implemented in a website https://biocomp.cnb.csic.es/EMValidationService/ to which reconstructed maps and their ESI can be uploaded.

Analytic modeling of inhomogeneous-resolution maps in cryo-electron microscopy and crystallography

Refinement of macromolecular atomic models versus experimental maps in crystallography and cryo-electron microscopy is a critical step in structure solution. For an appropriate comparison, model maps should mimic the imperfections in the experimental maps, mainly atomic disorder and limited resolution, which are often inhomogeneous over the molecular region. In the suggested method, these model maps are calculated as the sum of atomic contributions expressed through a specifically designed function describing a solitary spherical wave. Thanks to this function, atomic contributions are analytically expressed through their atomic displacement parameter and local resolution, a value now associated with each atom. Such a full analytic dependence of inhomogeneous-resolution map values on model parameters permits the refinement of all of these parameters together.

Making ripples in the comparison of calculated and experimental maps for real-space refinement and assessment by analytic modelling of local resolution

Commentary is given on a paper [Urzhumtsev & Lunin (2022). IUCrJ, 9, 728-734] proposing a new method for the analytic modelling of inhomogeneous resolution in electrostatic potential volumes and electron density maps for improved real-space refinement.

Higher resolution in cryo-EM by the combination of macromolecular prior knowledge and image-processing tools

Single-particle cryo-electron microscopy has become a powerful technique for the 3D structure determination of biological molecules. The last decade has seen an astonishing development of both hardware and software, and an exponential growth of new structures obtained at medium-high resolution. However, the knowledge accumulated in this field over the years has hardly been utilized as feedback in the reconstruction of new structures. In this context, this article explores the use of the deep-learning approach deepEMhancer as a regularizer in the RELION refinement process. deepEMhancer introduces prior information derived from macromolecular structures, and contributes to noise reduction and signal enhancement, as well as a higher degree of isotropy. These features have a direct effect on image alignment and reduction of overfitting during iterative refinement. The advantages of this combination are demonstrated for several membrane proteins, for which it is especially useful because of their high disorder and flexibility.

Artificial Intelligence in Cryo-Electron Microscopy

Cryo-electron microscopy (cryo-EM) has become an unrivaled tool for determining the structure of macromolecular complexes. The biological function of macromolecular complexes is inextricably tied to the flexibility of these complexes. Single particle cryo-EM can reveal the conformational heterogeneity of a biochemically pure sample, leading to well-founded mechanistic hypotheses about the roles these complexes play in biology. However, the processing of increasingly large, complex datasets using traditional data processing strategies is exceedingly expensive in both user time and computational resources. Current innovations in data processing capitalize on artificial intelligence (AI) to improve the efficiency of data analysis and validation. Here, we review new tools that use AI to automate the data analysis steps of particle picking, 3D map reconstruction, and local resolution determination. We discuss how the application of AI moves the field forward, and what obstacles remain. We also introduce potential future applications of AI to use cryo-EM in understanding protein communities in cells.

Emerging Themes in CryoEM─Single Particle Analysis Image Processing

Cryo-electron microscopy (CryoEM) has become a vital technique in structural biology. It is an interdisciplinary field that takes advantage of advances in biochemistry, physics, and image processing, among other disciplines. Innovations in these three basic pillars have contributed to the boosting of CryoEM in the past decade. This work reviews the main contributions in image processing to the current reconstruction workflow of single particle analysis (SPA) by CryoEM. Our review emphasizes the time evolution of the algorithms across the different steps of the workflow differentiating between two groups of approaches: analytical methods and deep learning algorithms. We present an analysis of the current state of the art. Finally, we discuss the emerging problems and challenges still to be addressed in the evolution of CryoEM image processing methods in SPA.

Validation analysis of EMDB entries

The Electron Microscopy Data Bank (EMDB) is the central archive of the electron cryo-microscopy (cryo-EM) community for storing and disseminating volume maps and tomograms. With input from the community, EMDB has developed new resources for the validation of cryo-EM structures, focusing on the quality of the volume data alone and that of the fit of any models, themselves archived in the Protein Data Bank (PDB), to the volume data. Based on recommendations from community experts, the validation resources are developed in a three-tiered system. Tier 1 covers an extensive and evolving set of validation metrics, including tried and tested metrics as well as more experimental ones, which are calculated for all EMDB entries and presented in the Validation Analysis (VA) web resource. This system is particularly useful for cryo-EM experts, both to validate individual structures and to assess the utility of new validation metrics. Tier 2 comprises a subset of the validation metrics covered by the VA resource that have been subjected to extensive testing and are considered to be useful for specialists as well as nonspecialists. These metrics are presented on the entry-specific web pages for the entire archive on the EMDB website. As more experience is gained with the metrics included in the VA resource, it is expected that consensus will emerge in the community regarding a subset that is suitable for inclusion in the tier 2 system. Tier 3, finally, consists of the validation reports and servers that are produced by the Worldwide Protein Data Bank (wwPDB) Consortium. Successful metrics from tier 2 will be proposed for inclusion in the wwPDB validation pipeline and reports. The details of the new resource are described, with an emphasis on the tier 1 system. The output of all three tiers is publicly available, either through the EMDB website (tiers 1 and 2) or through the wwPDB ftp sites (tier 3), although the content of all three will evolve over time (fastest for tier 1 and slowest for tier 3). It is our hope that these validation resources will help the cryo-EM community to obtain a better understanding of the quality and of the best ways to assess the quality of cryo-EM structures in EMDB and PDB.

On bias, variance, overfitting, gold standard and consensus in single-particle analysis by cryo-electron microscopy

Single-particle analysis (SPA) by cryo-electron microscopy comprises the estimation of many parameters along its image-processing pipeline. Overfitting observed in SPA is normally due to misestimated parameters, and the only way to identify these is by comparing the estimates of multiple algorithms or, at least, multiple executions of the same algorithm.

Cryo-electron microscopy (cryoEM) has become a well established technique to elucidate the 3D structures of biological macromolecules. Projection images from thousands of macromolecules that are assumed to be structurally identical are combined into a single 3D map representing the Coulomb potential of the macromolecule under study. This article discusses possible caveats along the image-processing path and how to avoid them to obtain a reliable 3D structure. Some of these problems are very well known in the community. These may be referred to as sample-related (such as specimen denaturation at interfaces or non-uniform projection geometry leading to underrepresented projection directions). The rest are related to the algorithms used. While some have been discussed in depth in the literature, such as the use of an incorrect initial volume, others have received much less attention. However, they are fundamental in any data-analysis approach. Chiefly among them, instabilities in estimating many of the key parameters that are required for a correct 3D reconstruction that occur all along the processing workflow are referred to, which may significantly affect the reliability of the whole process. In the field, the term overfitting has been coined to refer to some particular kinds of artifacts. It is argued that overfitting is a statistical bias in key parameter-estimation steps in the 3D reconstruction process, including intrinsic algorithmic bias. It is also shown that common tools (Fourier shell correlation) and strategies (gold standard) that are normally used to detect or prevent overfitting do not fully protect against it. Alternatively, it is proposed that detecting the bias that leads to overfitting is much easier when addressed at the level of parameter estimation, rather than detecting it once the particle images have been combined into a 3D map. Comparing the results from multiple algorithms (or at least, independent executions of the same algorithm) can detect parameter bias. These multiple executions could then be averaged to give a lower variance estimate of the underlying parameters.

Applications of deep learning in electron microscopy

We review the growing use of machine learning in electron microscopy (EM) driven in part by the availability of fast detectors operating at kiloHertz frame rates leading to large data sets that cannot be processed using manually implemented algorithms. We summarize the various network architectures and error metrics that have been applied to a range of EM-related problems including denoising and inpainting. We then provide a review of the application of these in both physical and life sciences, highlighting how conventional networks and training data have been specifically modified for EM.

Machine Learning for Structure Determination in Single-Particle Cryo-Electron Microscopy: A Systematic Review

Recently, single-particle cryo-electron microscopy (cryo-EM) has become an indispensable method for determining macromolecular structures at high resolution to deeply explore the relevant molecular mechanism. Its recent breakthrough is mainly because of the rapid advances in hardware and image processing algorithms, especially machine learning. As an essential support of single-particle cryo-EM, machine learning has powered many aspects of structure determination and greatly promoted its development. In this article, we provide a systematic review of the applications of machine learning in this field. Our review begins with a brief introduction of single-particle cryo-EM, followed by the specific tasks and challenges of its image processing. Then, focusing on the workflow of structure determination, we describe relevant machine learning algorithms and applications at different steps, including particle picking, 2-D clustering, 3-D reconstruction, and other steps. As different tasks exhibit distinct characteristics, we introduce the evaluation metrics for each task and summarize their dynamics of technology development. Finally, we discuss the open issues and potential trends in this promising field.

Atypical structural snapshots of human cytomegalovirus GPCR interactions with host G proteins

Human cytomegalovirus (HCMV) encodes G protein-coupled receptors (GPCRs) US28 and US27, which facilitate viral pathogenesis through engagement of host G proteins. Here we report cryo-electron microscopy structures of US28 and US27 forming nonproductive and productive complexes with Gi and Gq, respectively, exhibiting unusual features with functional implications. The "orphan" GPCR US27 lacks a ligand-binding pocket and has captured a guanosine diphosphate-bound inactive Gi through a tenuous interaction. The docking modes of CX3CL1-US28 and US27 to Gi favor localization to endosome-like curved membranes, where US28 and US27 can function as nonproductive Gi sinks to attenuate host chemokine-dependent Gi signaling. The CX3CL1-US28-Gq/11 complex likely represents a trapped intermediate during productive signaling, providing a view of a transition state in GPCR-G protein coupling for signaling. Our collective results shed new insight into unique G protein-mediated HCMV GPCR structural mechanisms, compared to mammalian GPCR counterparts, for subversion of host immunity.

Cryo-EM structure of a tetrameric photosystem I from Chroococcidiopsis TS-821, a thermophilic, unicellular, non-heterocyst-forming cyanobacterium

Photosystem I (PSI) is one of two photosystems involved in oxygenic photosynthesis. PSI of cyanobacteria exists in monomeric, trimeric, and tetrameric forms, in contrast to the strictly monomeric form of PSI in plants and algae. The tetrameric organization raises questions about its structural, physiological, and evolutionary significance. Here we report the ∼3.72 Å resolution cryo-electron microscopy structure of tetrameric PSI from the thermophilic, unicellular cyanobacterium Chroococcidiopsis sp. TS-821. The structure resolves 44 subunits and 448 cofactor molecules. We conclude that the tetramer is arranged via two different interfaces resulting from a dimer-of-dimers organization. The localization of chlorophyll molecules permits an excitation energy pathway within and between adjacent monomers. Bioinformatics analysis reveals conserved regions in the PsaL subunit that correlate with the oligomeric state. Tetrameric PSI may function as a key evolutionary step between the trimeric and monomeric forms of PSI organization in photosynthetic organisms.

A cryo-electron microscopy support film formed by 2D crystals of hydrophobin HFBI

Cryo-electron microscopy (cryo-EM) has become a powerful tool to resolve high-resolution structures of biomacromolecules in solution. However, air-water interface induced preferred orientations, dissociation or denaturation of biomacromolecules during cryo-vitrification remains a limiting factor for many specimens. To solve this bottleneck, we developed a cryo-EM support film using 2D crystals of hydrophobin HFBI. The hydrophilic side of the HFBI film adsorbs protein particles via electrostatic interactions and sequesters them from the air-water interface, allowing the formation of sufficiently thin ice for high-quality data collection. The particle orientation distribution can be regulated by adjusting the buffer pH. Using this support, we determined the cryo-EM structures of catalase (2.29 Å) and influenza haemagglutinin trimer (2.56 Å), which exhibited strong preferred orientations using a conventional cryo-vitrification protocol. We further show that the HFBI film is suitable to obtain high-resolution structures of small proteins, including aldolase (150 kDa, 3.28 Å) and haemoglobin (64 kDa, 3.6 Å). Our work suggests that HFBI films may have broad future applications in increasing the success rate and efficiency of cryo-EM.

It's noisy out there! A review of denoising techniques in cryo-electron tomography

Cryo-electron tomography is the only technique that can provide sub-nanometer resolved images of cell regions or even whole cells, without the need of labeling or staining methods. Technological advances over the past decade in electron microscope stability, cameras, stage precision and software have resulted in faster acquisition speeds and considerably improved resolution. In pursuit of even better image resolution, researchers seek to reduce noise - a crucial factor affecting the reliability of the tomogram interpretation and ultimately limiting the achieved resolution. Sub-tomogram averaging is the method of choice for reducing noise in repetitive objects. However, when averaging is not applicable, a trade-off between reducing noise and conserving genuine image details must be achieved. Thus, denoising is an important process that improves the interpretability of the tomogram not only directly but also by facilitating other downstream tasks, such as segmentation and 3D visualization. Here, I review contemporary denoising techniques for cryo-electron tomography by taking into account noise-specific properties of both reconstruction and detector noise. The outcomes of different techniques are compared, in order to help researchers select the most appropriate for each dataset and to achieve better and more reliable interpretation of the tomograms.

Advances in Xmipp for Cryo-Electron Microscopy: From Xmipp to Scipion

Xmipp is an open-source software package consisting of multiple programs for processing data originating from electron microscopy and electron tomography, designed and managed by the Biocomputing Unit of the Spanish National Center for Biotechnology, although with contributions from many other developers over the world. During its 25 years of existence, Xmipp underwent multiple changes and updates. While there were many publications related to new programs and functionality added to Xmipp, there is no single publication on the Xmipp as a package since 2013. In this article, we give an overview of the changes and new work since 2013, describe technologies and techniques used during the development, and take a peek at the future of the package.

Image Processing in Cryo-Electron Microscopy of Single Particles: The Power of Combining Methods

Cryo-electron microscopy has established as a mature structural biology technique to elucidate the three-dimensional structure of biological macromolecules. The Coulomb potential of the sample is imaged by an electron beam, and fast semi-conductor detectors produce movies of the sample under study. These movies have to be further processed by a whole pipeline of image-processing algorithms that produce the final structure of the macromolecule. In this chapter, we illustrate this whole processing pipeline putting in value the strength of "meta algorithms," which are the combination of several algorithms, each one with different mathematical rationale, in order to distinguish correctly from incorrectly estimated parameters. We show how this strategy leads to superior performance of the whole pipeline as well as more confident assessments about the reconstructed structures. The "meta algorithms" strategy is common to many fields and, in particular, it has provided excellent results in bioinformatics. We illustrate this combination using the workflow engine, Scipion.

DeepEMhancer: a deep learning solution for cryo-EM volume post-processing

Cryo-EM maps are valuable sources of information for protein structure modeling. However, due to the loss of contrast at high frequencies, they generally need to be post-processed to improve their interpretability. Most popular approaches, based on global B-factor correction, suffer from limitations. For instance, they ignore the heterogeneity in the map local quality that reconstructions tend to exhibit. Aiming to overcome these problems, we present DeepEMhancer, a deep learning approach designed to perform automatic post-processing of cryo-EM maps. Trained on a dataset of pairs of experimental maps and maps sharpened using their respective atomic models, DeepEMhancer has learned how to post-process experimental maps performing masking-like and sharpening-like operations in a single step. DeepEMhancer was evaluated on a testing set of 20 different experimental maps, showing its ability to reduce noise levels and obtain more detailed versions of the experimental maps. Additionally, we illustrated the benefits of DeepEMhancer on the structure of the SARS-CoV-2 RNA polymerase.

Sanchez-Garcia et al. present DeepEMhancer, a deep learning-based method that can automatically perform post-processing of raw cryo-electron microscopy density maps. The authors report that DeepEMhancer globally improves local quality of density maps, and may represent a useful tool for novel structures where PDB models are not readily available.

3DBionotes COVID-19 Edition

Summary

The web platform 3DBionotes-WS integrates multiple web services and an interactive web viewer to provide a unified environment in which biological annotations can be analyzed in their structural context. Since the COVID-19 outbreak, new structural data from many viral proteins have been provided at a very fast pace. This effort includes many cryogenic electron microscopy (cryo-EM) studies, together with more traditional ones (X-rays, NMR), using several modeling approaches and complemented with structural predictions. At the same time, a plethora of new genomics and interactomics information (including fragment screening and structure-based virtual screening efforts) have been made available from different servers. In this context, we have developed 3DBionotes-COVID-19 as an answer to: (i) the need to explore multiomics data in a unified context with a special focus on structural information and (ii) the drive to incorporate quality measurements, especially in the form of advanced validation metrics for cryo-EM.

Availability and implementation

https://3dbionotes.cnb.csic.es/ws/covid19.

Supplementary information

Supplementary data are available at Bioinformatics online.

Detecting Protein Communities in Native Cell Extracts by Machine Learning: A Structural Biologist's Perspective

Native cell extracts hold great promise for understanding the molecular structure of ordered biological systems at high resolution. This is because higher-order biomolecular interactions, dubbed as protein communities, may be retained in their (near-)native state, in contrast to extensively purifying or artificially overexpressing the proteins of interest. The distinct machine-learning approaches are applied to discover protein-protein interactions within cell extracts, reconstruct dedicated biological networks, and report on protein community members from various organisms. Their validation is also important, e.g., by the cross-linking mass spectrometry or cell biology methods. In addition, the cell extracts are amenable to structural analysis by cryo-electron microscopy (cryo-EM), but due to their inherent complexity, sorting structural signatures of protein communities derived by cryo-EM comprises a formidable task. The application of image-processing workflows inspired by machine-learning techniques would provide improvements in distinguishing structural signatures, correlating proteomic and network data to structural signatures and subsequently reconstructed cryo-EM maps, and, ultimately, characterizing unidentified protein communities at high resolution. In this review article, we summarize recent literature in detecting protein communities from native cell extracts and identify the remaining challenges and opportunities. We argue that the progress in, and the integration of, machine learning, cryo-EM, and complementary structural proteomics approaches would provide the basis for a multi-scale molecular description of protein communities within native cell extracts.

Structural interpretation of cryo-EM image reconstructions

The productivity of single-particle cryo-EM as a structure determination method has rapidly increased as many novel biological structures are being elucidated. The ultimate result of the cryo-EM experiment is an atomic model that should faithfully represent the computed image reconstruction. Although the principal approach of atomic model building and refinement from maps resembles that of the X-ray crystallographic methods, there are important differences due to the unique properties resulting from the 3D image reconstructions. In this review, we discuss the practiced work-flow from the cryo-EM image reconstruction to the atomic model. We give an overview of (i) resolution determination methods in cryo-EM including local and directional resolution variation, (ii) cryo-EM map contrast optimization including complementary map types that can help in identifying ambiguous density features, (iii) atomic model building and (iv) refinement in various resolution regimes including (v) their validation and (vi) discuss differences between X-ray and cryo-EM maps. Based on the methods originally developed for X-ray crystallography, the path from 3D image reconstruction to atomic coordinates has become an integral and important part of the cryo-EM structure determination work-flow that routinely delivers atomic models.

Algorithmic robustness to preferred orientations in single particle analysis by CryoEM

The presence of preferred orientations in single particle analysis (SPA) by cryo-Electron Microscopy (cryoEM) is currently one of the hurdles preventing many structural analyses from yielding high-resolution structures. Although the existence of preferred orientations is mostly related to the grid preparation, in this technical note, we show that some image processing algorithms used for angular assignment and three-dimensional (3D) reconstruction are more robust than others to these detrimental conditions. We exemplify this argument with three different data sets in which the presence of preferred orientations hindered achieving a 3D reconstruction without artifacts or, even worse, a 3D reconstruction could never be achieved.

FSC-Q: a CryoEM map-to-atomic model quality validation based on the local Fourier shell correlation

In recent years, advances in cryoEM have dramatically increased the resolution of reconstructions and, with it, the number of solved atomic models. It is widely accepted that the quality of cryoEM maps varies locally; therefore, the evaluation of the maps-derived structural models must be done locally as well. In this article, a method for the local analysis of the map-to-model fit is presented. The algorithm uses a comparison of two local resolution maps. The first is the local FSC (Fourier shell correlation) between the full map and the model, while the second is calculated between the half maps normally used in typical single particle analysis workflows. We call the quality measure "FSC-Q", and it is a quantitative estimation of how much of the model is supported by the signal content of the map. Furthermore, we show that FSC-Q may be helpful to detect overfitting. It can be used to complement other methods, such as the Q-score method that estimates the resolvability of atoms.

Local resolution estimates of cryoEM reconstructions

The field of cryoEM has quickly advanced in last years with the new biochemical, technological, methodological and computational developments. It has allowed significant progresses in Structural Biology, typically reaching quasi-atomic resolutions in the reconstructed maps. However, this rapid advance has also generated new questions relevant to resolution estimates. The global resolution metrics and their criteria have been deeply discussed in the last decade, but despite that, it remains as an important issue in the field. Recently, the introduction of local resolution measurements has changed how cryoEM reconstructions are interpreted, providing information about the existence of heterogeneity, flexibility, and angular assignment errors, and using it as a tool to aid in modeling. In this review we revisit the concept of local resolution and the different algorithms in the current state of the art. However, the concept of local resolution is not uniquely defined, and each implementation measures different features. This may lead to inappropriate interpretation of local resolution maps. Hence, a set of good practices is provided in this review to avoid misleading and over-interpretation of the reconstructions.

Integration of Cryo-EM Model Building Software in Scipion

Advances in cryo-electron microscopy (cryo-EM) have made it possible to obtain structures of large biological macromolecules at near-atomic resolution. This "resolution revolution" has encouraged the use and development of modeling tools able to produce high-quality atomic models from cryo-EM density maps. Unfortunately, many practical problems appear when combining different packages in the same processing workflow, which make difficult the use of these tools by non-experts and, therefore, reduce their utility. We present here a major extension of the image processing framework Scipion that provides inter-package integration in the model building area and full tracking of the complete workflow, from image processing to structure validation.