gEMpicker: a highly parallel GPU-accelerated particle picking tool for cryo-electron microscopy

Artificial intelligence in cryo-EM protein particle picking: recent advances and remaining challenges

Cryo-electron microscopy (cryo-EM) has revolutionized structural biology by enabling the determination of high-resolution 3-Dimensional (3D) structures of large biological macromolecules. Protein particle picking, the process of identifying individual protein particles in cryo-EM micrographs for building protein structures, has progressed from manual and template-based methods to sophisticated artificial intelligence (AI)-driven approaches in recent years. This review critically examines the evolution and current state of cryo-EM particle picking methods, with an emphasis on the impact of AI. We conducted a comparative evaluation of popular AI-based particle picking methods, using both general machine learning metrics and specific cryo-EM structure determination metrics. This analysis involved constructing the 3D density map from the picked protein particles and assessing the obtained resolution and particle orientation diversity, underscoring the significant impact of AI on cryo-EM particle picking. Despite the advancements, we also identified key obstacles, such as handling complex micrographs with small proteins. The analysis provides insights into the future development of more sophisticated and fully automated AI methods in cryo-EM particle recognition.

REliable PIcking by Consensus (REPIC): a consensus methodology for harnessing multiple cryo-EM particle pickers

Cryo-EM particle identification from micrographs ("picking") is challenging due to the low signal-to-noise ratio and lack of ground truth for particle locations. State-of-the-art computational algorithms ("pickers") identify different particle sets, complicating the selection of the best-suited picker for a protein of interest. Here, we present REliable PIcking by Consensus (REPIC), a computational approach to identifying particles common to the output of multiple pickers. We frame consensus particle picking as a graph problem, which REPIC solves using integer linear programming. REPIC picks high-quality particles even when the best picker is not known a priori or a protein is difficult-to-pick (e.g., NOMPC ion channel). Reconstructions using consensus particles without particle filtering achieve resolutions comparable to those from particles picked by experts. Our results show that REPIC requires minimal (often no) manual intervention, and considerably reduces the burden on cryo-EM users for picker selection and particle picking. Availability: https://github.com/ccameron/REPIC .

A large expert-curated cryo-EM image dataset for machine learning protein particle picking

Cryo-electron microscopy (cryo-EM) is a powerful technique for determining the structures of biological macromolecular complexes. Picking single-protein particles from cryo-EM micrographs is a crucial step in reconstructing protein structures. However, the widely used template-based particle picking process is labor-intensive and time-consuming. Though machine learning and artificial intelligence (AI) based particle picking can potentially automate the process, its development is hindered by lack of large, high-quality labelled training data. To address this bottleneck, we present CryoPPP, a large, diverse, expert-curated cryo-EM image dataset for protein particle picking and analysis. It consists of labelled cryo-EM micrographs (images) of 34 representative protein datasets selected from the Electron Microscopy Public Image Archive (EMPIAR). The dataset is 2.6 terabytes and includes 9,893 high-resolution micrographs with labelled protein particle coordinates. The labelling process was rigorously validated through 2D particle class validation and 3D density map validation with the gold standard. The dataset is expected to greatly facilitate the development of both AI and classical methods for automated cryo-EM protein particle picking.

CryoPPP: A Large Expert-Labelled Cryo-EM Image Dataset for Machine Learning Protein Particle Picking

Cryo-electron microscopy (cryo-EM) is currently the most powerful technique for determining the structures of large protein complexes and assemblies. Picking single-protein particles from cryo-EM micrographs (images) is a key step in reconstructing protein structures. However, the widely used template-based particle picking process is labor-intensive and time-consuming. Though the emerging machine learning-based particle picking can potentially automate the process, its development is severely hindered by lack of large, high-quality, manually labelled training data. Here, we present CryoPPP, a large, diverse, expert-curated cryo-EM image dataset for single protein particle picking and analysis to address this bottleneck. It consists of manually labelled cryo-EM micrographs of 32 non-redundant, representative protein datasets selected from the Electron Microscopy Public Image Archive (EMPIAR). It includes 9,089 diverse, high-resolution micrographs (∼300 cryo-EM images per EMPIAR dataset) in which the coordinates of protein particles were labelled by human experts. The protein particle labelling process was rigorously validated by both 2D particle class validation and 3D density map validation with the gold standard. The dataset is expected to greatly facilitate the development of machine learning and artificial intelligence methods for automated cryo-EM protein particle picking. The dataset and data processing scripts are available at https://github.com/BioinfoMachineLearning/cryoppp.

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.

CASSPER is a semantic segmentation-based particle picking algorithm for single-particle cryo-electron microscopy

Particle identification and selection, which is a prerequisite for high-resolution structure determination of biological macromolecules via single-particle cryo-electron microscopy poses a major bottleneck for automating the steps of structure determination. Here, we present a generalized deep learning tool, CASSPER, for the automated detection and isolation of protein particles in transmission microscope images. This deep learning tool uses Semantic Segmentation and a collection of visually prepared training samples to capture the differences in the transmission intensities of protein, ice, carbon, and other impurities found in the micrograph. CASSPER is a semantic segmentation based method that does pixel-level classification and completely eliminates the need for manual particle picking. Integration of Contrast Limited Adaptive Histogram Equalization (CLAHE) in CASSPER enables high-fidelity particle detection in micrographs with variable ice thickness and contrast. A generalized CASSPER model works with high efficiency on unseen datasets and can potentially pick particles on-the-fly, enabling data processing automation.

Single-Particle cryo-EM as a Pipeline for Obtaining Atomic Resolution Structures of Druggable Targets in Preclinical Structure-Based Drug Design

Single-particle cryo-electron microscopy (cryo-EM) and three-dimensional (3D) image processing have gained importance in the last few years to obtain atomic structures of drug targets. Obtaining atomic-resolution 3D structure better than ~2.5 Å is a standard approach in pharma companies to design and optimize therapeutic compounds against drug targets like proteins. Protein crystallography is the main technique in solving the structures of drug targets at atomic resolution. However, this technique requires protein crystals which in turn is a major bottleneck. It was not possible to obtain the structure of proteins better than 2.5 Å resolution by any other methods apart from protein crystallography until 2015. Recent advances in single-particle cryo-EM and 3D image processing have led to a resolution revolution in the field of structural biology that has led to high-resolution protein structures, thus breaking the cryo-EM resolution barriers to facilitate drug discovery. There are 24 structures solved by single-particle cryo-EM with resolution 2.5 Å or better in the EMDataBank (EMDB) till date. Among these, five cryo-EM 3D reconstructions of proteins in the EMDB have their associated coordinates deposited in Protein Data Bank (PDB), with bound inhibitor/ ligand. Thus, for the first time, single-particle cryo-EM was included in the structure-based drug design (SBDD) pipeline for solving protein structures independently or where crystallography has failed to crystallize the protein. Further, this technique can be complementary and supplementary to protein crystallography field in solving 3D structures. Thus, single-particle cryo-EM can become a standard approach in pharmaceutical industry in the design, validation, and optimization of therapeutic compounds targeting therapeutically important protein molecules during preclinical drug discovery research. The present chapter will describe briefly the history and the principles of single-particle cryo-EM and 3D image processing to obtain atomic-resolution structure of proteins and their complex with their drug targets/ligands.

Advances in image processing for single-particle analysis by electron cryomicroscopy and challenges ahead

Electron cryomicroscopy (cryoEM) is essential for the study and functional understanding of non-crystalline macromolecules such as proteins. These molecules cannot be imaged using X-ray crystallography or other popular methods. CryoEM has been successfully used to visualize macromolecular complexes such as ribosomes, viruses, and ion channels. Determination of structural models of these at various conformational states leads to insight on how these molecules function. Recent advances in imaging technology have given cryoEM a scientific rebirth. As a result of these technological advances image processing and analysis have yielded molecular structures at atomic resolution. Nevertheless there continue to be challenges in image processing, and in this article we will touch on the most essential in order to derive an accurate three-dimensional model from noisy projection images. Traditional approaches, such as k-means clustering for class averaging, will be provided as background. We will then highlight new approaches for each image processing subproblem, including a 3D reconstruction method for asymmetric molecules using just two projection images and deep learning algorithms for automated particle picking.

APPLE picker: Automatic particle picking, a low-effort cryo-EM framework

Particle picking is a crucial first step in the computational pipeline of single-particle cryo-electron microscopy (cryo-EM). Selecting particles from the micrographs is difficult especially for small particles with low contrast. As high-resolution reconstruction typically requires hundreds of thousands of particles, manually picking that many particles is often too time-consuming. While template-based particle picking is currently a popular approach, it may suffer from introducing manual bias into the selection process. In addition, this approach is still somewhat time-consuming. This paper presents the APPLE (Automatic Particle Picking with Low user Effort) picker, a simple and novel approach for fast, accurate, and template-free particle picking. This approach is evaluated on publicly available datasets containing micrographs of β-galactosidase, T20S proteasome, 70S ribosome and keyhole limpet hemocyanin projections.

Big data in cryoEM: automated collection, processing and accessibility of EM data

The scope and complexity of cryogenic electron microscopy (cryoEM) data has greatly increased, and will continue to do so, due to recent and ongoing technical breakthroughs that have led to much improved resolutions for macromolecular structures solved using this method. This big data explosion includes single particle data as well as tomographic tilt series, both generally acquired as direct detector movies of ∼10-100 frames per image or per tilt-series. We provide a brief survey of the developments leading to the current status, and describe existing cryoEM pipelines, with an emphasis on the scope of data acquisition, methods for automation, and use of cloud storage and computing.

A Two-Phase Improved Correlation Method for Automatic Particle Selection in Cryo-EM

Particle selection from cryo-electron microscopy (Cryo-EM) images is very important for high-resolution reconstruction of macromolecular structure. The methods of particle selection can be roughly grouped into two classes, template-matching methods and feature-based methods. In general, template-matching methods usually generate better results than feature-based methods. However, the accuracy of template-matching methods is restricted by the noise and low contrast of Cryo-EM images. Moreover, the processing speed of template-matching methods, restricted by the random orientation of particles, further limits their practical applications. In this paper, combining the advantages of feature-based methods and template-matching methods, we present a two-phase improved correlation method for automatic, fast particle selection. In Phase I, we generate a preliminary particle set using rotation-invariant features of particles. In Phase II, we filter the preliminary particle set using a correlation method to reduce the interference of the high noise background and improve the precision of particle selection. We apply several optimization strategies, including a modified adaboost algorithm, Divide and Conquer technique, cascade strategy and graphics processing unit parallel technique, to improve feature recognition ability and reduce processing time. In addition, we developed two correlation score functions for different correlation situations. Experimental results on the benchmark of Cryo-EM images show that our method can improve the accuracy and processing speed of particle selection significantly.

cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination

Single-particle electron cryomicroscopy (cryo-EM) is a powerful method for determining the structures of biological macromolecules. With automated microscopes, cryo-EM data can often be obtained in a few days. However, processing cryo-EM image data to reveal heterogeneity in the protein structure and to refine 3D maps to high resolution frequently becomes a severe bottleneck, requiring expert intervention, prior structural knowledge, and weeks of calculations on expensive computer clusters. Here we show that stochastic gradient descent (SGD) and branch-and-bound maximum likelihood optimization algorithms permit the major steps in cryo-EM structure determination to be performed in hours or minutes on an inexpensive desktop computer. Furthermore, SGD with Bayesian marginalization allows ab initio 3D classification, enabling automated analysis and discovery of unexpected structures without bias from a reference map. These algorithms are combined in a user-friendly computer program named cryoSPARC (http://www.cryosparc.com).

Structure-function insights reveal the human ribosome as a cancer target for antibiotics

Many antibiotics in clinical use target the bacterial ribosome by interfering with the protein synthesis machinery. However, targeting the human ribosome in the case of protein synthesis deregulations such as in highly proliferating cancer cells has not been investigated at the molecular level up to now. Here we report the structure of the human 80S ribosome with a eukaryote-specific antibiotic and show its anti-proliferative effect on several cancer cell lines. The structure provides insights into the detailed interactions in a ligand-binding pocket of the human ribosome that are required for structure-assisted drug design. Furthermore, anti-proliferative dose response in leukaemic cells and interference with synthesis of c-myc and mcl-1 short-lived protein markers reveals specificity of a series of eukaryote-specific antibiotics towards cytosolic rather than mitochondrial ribosomes, uncovering the human ribosome as a promising cancer target.

The ribosome of bacteria and other unicellular pathogens is a common target for antibiotic drugs. Here the authors determine a structure of the human ribosome bound to the translation inhibitor cycloheximide, and provide evidence that targeting the ribosome is a promising avenue for cancer therapy.

Structure of the initiation-competent RNA polymerase I and its implication for transcription

Eukaryotic RNA polymerase I (Pol I) is specialized in rRNA gene transcription synthesizing up to 60% of cellular RNA. High level rRNA production relies on efficient binding of initiation factors to the rRNA gene promoter and recruitment of Pol I complexes containing initiation factor Rrn3. Here, we determine the cryo-EM structure of the Pol I-Rrn3 complex at 7.5 Å resolution, and compare it with Rrn3-free monomeric and dimeric Pol I. We observe that Rrn3 contacts the Pol I A43/A14 stalk and subunits A190 and AC40, that association re-organizes the Rrn3 interaction interface, thereby preventing Pol I dimerization; and Rrn3-bound and monomeric Pol I differ from the dimeric enzyme in cleft opening, and localization of the A12.2 C-terminus in the active centre. Our findings thus support a dual role for Rrn3 in transcription initiation to stabilize a monomeric initiation competent Pol I and to drive pre-initiation complex formation.

Eukaryotic RNA polymerase I (Pol I) is responsible for the transcription of rRNA genes. Here the authors determine the cryo-EM structure of the Pol I-Rrn3 complex, providing insight into how Rrn3 stabilizes the monomeric initiation competent Pol I to drive pre-initiation complex formation.

gEMfitter: a highly parallel FFT-based 3D density fitting tool with GPU texture memory acceleration

Fitting high resolution protein structures into low resolution cryo-electron microscopy (cryo-EM) density maps is an important technique for modeling the atomic structures of very large macromolecular assemblies. This article presents "gEMfitter", a highly parallel fast Fourier transform (FFT) EM density fitting program which can exploit the special hardware properties of modern graphics processor units (GPUs) to accelerate both the translational and rotational parts of the correlation search. In particular, by using the GPU's special texture memory hardware to rotate 3D voxel grids, the cost of rotating large 3D density maps is almost completely eliminated. Compared to performing 3D correlations on one core of a contemporary central processor unit (CPU), running gEMfitter on a modern GPU gives up to 26-fold speed-up. Furthermore, using our parallel processing framework, this speed-up increases linearly with the number of CPUs or GPUs used. Thus, it is now possible to use routinely more robust but more expensive 3D correlation techniques. When tested on low resolution experimental cryo-EM data for the GroEL-GroES complex, we demonstrate the satisfactory fitting results that may be achieved by using a locally normalised cross-correlation with a Laplacian pre-filter, while still being up to three orders of magnitude faster than the well-known COLORES program.