1
|
Xu D, Ando N. Miffi: Improving the accuracy of CNN-based cryo-EM micrograph filtering with fine-tuning and Fourier space information. J Struct Biol 2024; 216:108072. [PMID: 38431179 PMCID: PMC11162944 DOI: 10.1016/j.jsb.2024.108072] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2023] [Revised: 02/11/2024] [Accepted: 02/25/2024] [Indexed: 03/05/2024]
Abstract
Efficient and high-accuracy filtering of cryo-electron microscopy (cryo-EM) micrographs is an emerging challenge with the growing speed of data collection and sizes of datasets. Convolutional neural networks (CNNs) are machine learning models that have been proven successful in many computer vision tasks, and have been previously applied to cryo-EM micrograph filtering. In this work, we demonstrate that two strategies, fine-tuning models from pretrained weights and including the power spectrum of micrographs as input, can greatly improve the attainable prediction accuracy of CNN models. The resulting software package, Miffi, is open-source and freely available for public use (https://github.com/ando-lab/miffi).
Collapse
Affiliation(s)
- Da Xu
- Department of Chemistry and Chemical Biology, Cornell University, Ithaca, NY 14853, USA
| | - Nozomi Ando
- Department of Chemistry and Chemical Biology, Cornell University, Ithaca, NY 14853, USA.
| |
Collapse
|
2
|
Xu D, Ando N. Miffi: Improving the accuracy of CNN-based cryo-EM micrograph filtering with fine-tuning and Fourier space information. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2023.12.08.570849. [PMID: 38405773 PMCID: PMC10888874 DOI: 10.1101/2023.12.08.570849] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 02/27/2024]
Abstract
Efficient and high-accuracy filtering of cryo-electron microscopy (cryo-EM) micrographs is an emerging challenge with the growing speed of data collection and sizes of datasets. Convolutional neural networks (CNNs) are machine learning models that have been proven successful in many computer vision tasks, and have been previously applied to cryo-EM micrograph filtering. In this work, we demonstrate that two strategies, fine-tuning models from pretrained weights and including the power spectrum of micrographs as input, can greatly improve the attainable prediction accuracy of CNN models. The resulting software package, Miffi, is open-source and freely available for public use (https://github.com/ando-lab/miffi).
Collapse
Affiliation(s)
- Da Xu
- Department of Chemistry and Chemical Biology, Cornell University, Ithaca, NY 14850, USA
| | - Nozomi Ando
- Department of Chemistry and Chemical Biology, Cornell University, Ithaca, NY 14850, USA
| |
Collapse
|
3
|
Baggen J, Jacquemyn M, Persoons L, Vanstreels E, Pye VE, Wrobel AG, Calvaresi V, Martin SR, Roustan C, Cronin NB, Reading E, Thibaut HJ, Vercruysse T, Maes P, De Smet F, Yee A, Nivitchanyong T, Roell M, Franco-Hernandez N, Rhinn H, Mamchak AA, Ah Young-Chapon M, Brown E, Cherepanov P, Daelemans D. TMEM106B is a receptor mediating ACE2-independent SARS-CoV-2 cell entry. Cell 2023; 186:3427-3442.e22. [PMID: 37421949 PMCID: PMC10409496 DOI: 10.1016/j.cell.2023.06.005] [Citation(s) in RCA: 51] [Impact Index Per Article: 51.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2022] [Revised: 04/24/2023] [Accepted: 06/08/2023] [Indexed: 07/10/2023]
Abstract
SARS-CoV-2 is associated with broad tissue tropism, a characteristic often determined by the availability of entry receptors on host cells. Here, we show that TMEM106B, a lysosomal transmembrane protein, can serve as an alternative receptor for SARS-CoV-2 entry into angiotensin-converting enzyme 2 (ACE2)-negative cells. Spike substitution E484D increased TMEM106B binding, thereby enhancing TMEM106B-mediated entry. TMEM106B-specific monoclonal antibodies blocked SARS-CoV-2 infection, demonstrating a role of TMEM106B in viral entry. Using X-ray crystallography, cryogenic electron microscopy (cryo-EM), and hydrogen-deuterium exchange mass spectrometry (HDX-MS), we show that the luminal domain (LD) of TMEM106B engages the receptor-binding motif of SARS-CoV-2 spike. Finally, we show that TMEM106B promotes spike-mediated syncytium formation, suggesting a role of TMEM106B in viral fusion. Together, our findings identify an ACE2-independent SARS-CoV-2 infection mechanism that involves cooperative interactions with the receptors heparan sulfate and TMEM106B.
Collapse
Affiliation(s)
- Jim Baggen
- KU Leuven Department of Microbiology, Immunology and Transplantation, Laboratory of Virology and Chemotherapy, Rega Institute, Leuven 3000, Belgium.
| | - Maarten Jacquemyn
- KU Leuven Department of Microbiology, Immunology and Transplantation, Laboratory of Virology and Chemotherapy, Rega Institute, Leuven 3000, Belgium
| | - Leentje Persoons
- KU Leuven Department of Microbiology, Immunology and Transplantation, Laboratory of Virology and Chemotherapy, Rega Institute, Leuven 3000, Belgium
| | - Els Vanstreels
- KU Leuven Department of Microbiology, Immunology and Transplantation, Laboratory of Virology and Chemotherapy, Rega Institute, Leuven 3000, Belgium
| | - Valerie E Pye
- Chromatin Structure and Mobile DNA Laboratory, Francis Crick Institute, London NW1 1AT, UK
| | - Antoni G Wrobel
- Structural Biology of Disease Processes Laboratory, Francis Crick Institute, London NW1 1AT, UK
| | - Valeria Calvaresi
- Department of Chemistry, Britannia House, 7 Trinity Street, King's College London, London SE1 1DB, UK
| | - Stephen R Martin
- Structural Biology of Disease Processes Laboratory, Francis Crick Institute, London NW1 1AT, UK
| | - Chloë Roustan
- Structural Biology Science Technology Platform, Francis Crick Institute, London NW1 1AT, UK
| | - Nora B Cronin
- LonCEM Facility, Francis Crick Institute, London NW1 1AT, UK
| | - Eamonn Reading
- Department of Chemistry, Britannia House, 7 Trinity Street, King's College London, London SE1 1DB, UK
| | - Hendrik Jan Thibaut
- KU Leuven Department of Microbiology, Immunology and Transplantation, Laboratory of Virology and Chemotherapy, Translational Platform Virology and Chemotherapy, Rega Institute, Leuven 3000, Belgium
| | - Thomas Vercruysse
- KU Leuven Department of Microbiology, Immunology and Transplantation, Laboratory of Virology and Chemotherapy, Translational Platform Virology and Chemotherapy, Rega Institute, Leuven 3000, Belgium
| | - Piet Maes
- KU Leuven Department of Microbiology, Immunology and Transplantation, Laboratory of Clinical and Epidemiological Virology, Rega Institute, Leuven 3000, Belgium
| | - Frederik De Smet
- KU Leuven Department of Imaging and Pathology, Laboratory for Precision Cancer Medicine, Translational Cell and Tissue Research Unit, Leuven 3000, Belgium
| | - Angie Yee
- Alector LLC, 131 Oyster Point Blvd. Suite 600, South San Francisco, CA 94080, USA
| | - Toey Nivitchanyong
- Alector LLC, 131 Oyster Point Blvd. Suite 600, South San Francisco, CA 94080, USA
| | - Marina Roell
- Alector LLC, 131 Oyster Point Blvd. Suite 600, South San Francisco, CA 94080, USA
| | | | - Herve Rhinn
- Alector LLC, 131 Oyster Point Blvd. Suite 600, South San Francisco, CA 94080, USA
| | - Alusha Andre Mamchak
- Alector LLC, 131 Oyster Point Blvd. Suite 600, South San Francisco, CA 94080, USA
| | | | - Eric Brown
- Alector LLC, 131 Oyster Point Blvd. Suite 600, South San Francisco, CA 94080, USA
| | - Peter Cherepanov
- Chromatin Structure and Mobile DNA Laboratory, Francis Crick Institute, London NW1 1AT, UK; Department of Infectious Disease, Section of Virology, Imperial College London, St Mary's Campus, Norfolk Place, London W2 1PG, UK.
| | - Dirk Daelemans
- KU Leuven Department of Microbiology, Immunology and Transplantation, Laboratory of Virology and Chemotherapy, Rega Institute, Leuven 3000, Belgium.
| |
Collapse
|
4
|
Visheratina A, Visheratin A, Kumar P, Veksler M, Kotov NA. Chirality Analysis of Complex Microparticles using Deep Learning on Realistic Sets of Microscopy Images. ACS NANO 2023; 17:7431-7442. [PMID: 37058327 DOI: 10.1021/acsnano.2c12056] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/19/2023]
Abstract
Nanoscale chirality is an actively growing research field spurred by the giant chiroptical activity, enantioselective biological activity, and asymmetric catalytic activity of chiral nanostructures. Compared to chiral molecules, the handedness of chiral nano- and microstructures can be directly established via electron microscopy, which can be utilized for the automatic analysis of chiral nanostructures and prediction of their properties. However, chirality in complex materials may have multiple geometric forms and scales. Computational identification of chirality from electron microscopy images rather than optical measurements is convenient but is fundamentally challenging, too, because (1) image features differentiating left- and right-handed particles can be ambiguous and (2) three-dimensional structure essential for chirality is 'flattened' into two-dimensional projections. Here, we show that deep learning algorithms can identify twisted bowtie-shaped microparticles with nearly 100% accuracy and classify them as left- and right-handed with as high as 99% accuracy. Importantly, such accuracy was achieved with as few as 30 original electron microscopy images of bowties. Furthermore, after training on bowtie particles with complex nanostructured features, the model can recognize other chiral shapes with different geometries without retraining for their specific chiral geometry with 93% accuracy, indicating the true learning abilities of the employed neural networks. These findings indicate that our algorithm trained on a practically feasible set of experimental data enables automated analysis of microscopy data for the accelerated discovery of chiral particles and their complex systems for multiple applications.
Collapse
Affiliation(s)
- Anastasia Visheratina
- Department of Chemical Engineering and Biointerfaces Institute, University of Michigan, Ann Arbor, Michigan 48109, United States
| | | | - Prashant Kumar
- Department of Chemical Engineering and Biointerfaces Institute, University of Michigan, Ann Arbor, Michigan 48109, United States
| | - Michael Veksler
- Department of Chemical Engineering and Biointerfaces Institute, University of Michigan, Ann Arbor, Michigan 48109, United States
| | - Nicholas A Kotov
- Department of Chemical Engineering and Biointerfaces Institute, University of Michigan, Ann Arbor, Michigan 48109, United States
- Department of Aeronautics, Faculty of Engineering, Imperial College London, South Kensington Campus London, SW7 2AZ, United Kingdom
| |
Collapse
|
5
|
Zeng X, Kahng A, Xue L, Mahamid J, Chang YW, Xu M. High-throughput cryo-ET structural pattern mining by unsupervised deep iterative subtomogram clustering. Proc Natl Acad Sci U S A 2023; 120:e2213149120. [PMID: 37027429 PMCID: PMC10104553 DOI: 10.1073/pnas.2213149120] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2022] [Accepted: 02/24/2023] [Indexed: 04/08/2023] Open
Abstract
Cryoelectron tomography directly visualizes heterogeneous macromolecular structures in their native and complex cellular environments. However, existing computer-assisted structure sorting approaches are low throughput or inherently limited due to their dependency on available templates and manual labels. Here, we introduce a high-throughput template-and-label-free deep learning approach, Deep Iterative Subtomogram Clustering Approach (DISCA), that automatically detects subsets of homogeneous structures by learning and modeling 3D structural features and their distributions. Evaluation on five experimental cryo-ET datasets shows that an unsupervised deep learning based method can detect diverse structures with a wide range of molecular sizes. This unsupervised detection paves the way for systematic unbiased recognition of macromolecular complexes in situ.
Collapse
Affiliation(s)
- Xiangrui Zeng
- Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA15213
| | - Anson Kahng
- Computer Science Department, University of Rochester, Rochester, NY14620
| | - Liang Xue
- Structural and Computational Biology Unit, European Molecular Biology Laboratory, Heidelberg69117, Germany
- Faculty of Biosciences, Collaboration for joint PhD degree between European Molecular Biology Laboratory and Heidelberg University, Heidelberg69117, Germany
| | - Julia Mahamid
- Structural and Computational Biology Unit, European Molecular Biology Laboratory, Heidelberg69117, Germany
| | - Yi-Wei Chang
- Department of Biochemistry and Biophysics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA19104
| | - Min Xu
- Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA15213
| |
Collapse
|
6
|
Kim PT, Noble AJ, Cheng A, Bepler T. Learning to automate cryo-electron microscopy data collection with Ptolemy. IUCRJ 2023; 10:90-102. [PMID: 36598505 PMCID: PMC9812219 DOI: 10.1107/s2052252522010612] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 06/17/2022] [Accepted: 11/03/2022] [Indexed: 06/17/2023]
Abstract
Over the past decade, cryo-electron microscopy (cryoEM) has emerged as an important method for determining near-native, near-atomic resolution 3D structures of biological macromolecules. To meet the increasing demand for cryoEM, automated methods that improve throughput and efficiency of microscope operation are needed. Currently, the targeting algorithms provided by most data-collection software require time-consuming manual tuning of parameters for each grid, and, in some cases, operators must select targets completely manually. However, the development of fully automated targeting algorithms is non-trivial, because images often have low signal-to-noise ratios and optimal targeting strategies depend on a range of experimental parameters and macromolecule behaviors that vary between projects and collection sessions. To address this, Ptolemy provides a pipeline to automate low- and medium-magnification targeting using a suite of purpose-built computer vision and machine-learning algorithms, including mixture models, convolutional neural networks and U-Nets. Learned models in this pipeline are trained on a large set of images from real-world cryoEM data-collection sessions, labeled with locations selected by human operators. These models accurately detect and classify regions of interest in low- and medium-magnification images, and generalize to unseen sessions, as well as to images collected on different microscopes at another facility. This open-source, modular pipeline can be integrated with existing microscope control software to enable automation of cryoEM data collection and can serve as a foundation for future cryoEM automation software.
Collapse
Affiliation(s)
- Paul T. Kim
- Simons Machine Learning Center, Simons Electron Microscopy Center, New York Structural Biology Center, New York, NY USA
| | - Alex J. Noble
- Simons Machine Learning Center, Simons Electron Microscopy Center, New York Structural Biology Center, New York, NY USA
| | - Anchi Cheng
- Simons Electron Microscopy Center, New York Structural Biology Center, New York, NY USA
| | - Tristan Bepler
- Simons Machine Learning Center, Simons Electron Microscopy Center, New York Structural Biology Center, New York, NY USA
| |
Collapse
|
7
|
Sorzano COS, Vilas JL, Ramírez-Aportela E, Krieger J, Del Hoyo D, Herreros D, Fernandez-Giménez E, Marchán D, Macías JR, Sánchez I, Del Caño L, Fonseca-Reyna Y, Conesa P, García-Mena A, Burguet J, García Condado J, Méndez García J, Martínez M, Muñoz-Barrutia A, Marabini R, Vargas J, Carazo JM. Image processing tools for the validation of CryoEM maps. Faraday Discuss 2022; 240:210-227. [PMID: 35861059 DOI: 10.1039/d2fd00059h] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/09/2023]
Abstract
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.
Collapse
Affiliation(s)
- C O S Sorzano
- Natl. Center of Biotechnology, CSIC, c/Darwin, 3, 28049, Madrid, Spain.
| | - J L Vilas
- Natl. Center of Biotechnology, CSIC, c/Darwin, 3, 28049, Madrid, Spain.
| | | | - J Krieger
- Natl. Center of Biotechnology, CSIC, c/Darwin, 3, 28049, Madrid, Spain.
| | - D Del Hoyo
- Natl. Center of Biotechnology, CSIC, c/Darwin, 3, 28049, Madrid, Spain.
| | - D Herreros
- Natl. Center of Biotechnology, CSIC, c/Darwin, 3, 28049, Madrid, Spain.
| | | | - D Marchán
- Natl. Center of Biotechnology, CSIC, c/Darwin, 3, 28049, Madrid, Spain.
| | - J R Macías
- Natl. Center of Biotechnology, CSIC, c/Darwin, 3, 28049, Madrid, Spain.
| | - I Sánchez
- Natl. Center of Biotechnology, CSIC, c/Darwin, 3, 28049, Madrid, Spain.
| | - L Del Caño
- Natl. Center of Biotechnology, CSIC, c/Darwin, 3, 28049, Madrid, Spain.
| | - Y Fonseca-Reyna
- Natl. Center of Biotechnology, CSIC, c/Darwin, 3, 28049, Madrid, Spain.
| | - P Conesa
- Natl. Center of Biotechnology, CSIC, c/Darwin, 3, 28049, Madrid, Spain.
| | - A García-Mena
- Natl. Center of Biotechnology, CSIC, c/Darwin, 3, 28049, Madrid, Spain.
| | - J Burguet
- Depto. de Óptica, Univ. Complutense de Madrid, Pl. Ciencias, 1, 28040, Madrid, Spain
| | - J García Condado
- Biocruces Bizkaia Instituto Investigación Sanitaria, Cruces Plaza, 48903, Barakaldo, Bizkaia, Spain
| | | | - M Martínez
- Natl. Center of Biotechnology, CSIC, c/Darwin, 3, 28049, Madrid, Spain.
| | - A Muñoz-Barrutia
- Univ. Carlos III de Madrid, Avda. de la Universidad 30, 28911, Leganés, Madrid, Spain
| | - R Marabini
- Escuela Politécnica Superior, Univ. Autónoma de Madrid, CSIC, C. Francisco Tomás y Valiente, 11, 28049, Madrid, Spain
| | - J Vargas
- Depto. de Óptica, Univ. Complutense de Madrid, Pl. Ciencias, 1, 28040, Madrid, Spain
| | - J M Carazo
- Natl. Center of Biotechnology, CSIC, c/Darwin, 3, 28049, Madrid, Spain.
| |
Collapse
|
8
|
Zhang Q, Wang Y, Song L, Han M, Song H. Using an improved YOLOv5s network for the automatic detection of silicon on wheat straw epidermis of micrographs. J FIELD ROBOT 2022. [DOI: 10.1002/rob.22120] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
Affiliation(s)
- Qianru Zhang
- College of Mechanical and Electronic Engineering Northwest A&F University Yangling Shaanxi China
- Key Laboratory of Agricultural Internet of Things Ministry of Agriculture and Rural Affairs Yangling Shaanxi China
- Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Services Yangling China
| | - Yunfei Wang
- College of Mechanical and Electronic Engineering Northwest A&F University Yangling Shaanxi China
- Key Laboratory of Agricultural Internet of Things Ministry of Agriculture and Rural Affairs Yangling Shaanxi China
- Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Services Yangling China
| | - Lei Song
- College of Mechanical and Electronic Engineering Northwest A&F University Yangling Shaanxi China
- Key Laboratory of Agricultural Internet of Things Ministry of Agriculture and Rural Affairs Yangling Shaanxi China
- Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Services Yangling China
| | - Mengxuan Han
- College of Mechanical and Electronic Engineering Northwest A&F University Yangling Shaanxi China
- Key Laboratory of Agricultural Internet of Things Ministry of Agriculture and Rural Affairs Yangling Shaanxi China
- Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Services Yangling China
| | - Huaibo Song
- College of Mechanical and Electronic Engineering Northwest A&F University Yangling Shaanxi China
- Key Laboratory of Agricultural Internet of Things Ministry of Agriculture and Rural Affairs Yangling Shaanxi China
- Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Services Yangling China
| |
Collapse
|
9
|
Abstract
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.
Collapse
Affiliation(s)
- Jose Luis Vilas
- Biocomputing Unit, Centro
Nacional de Biotecnologia (CNB-CSIC), Darwin, 3, Campus Universidad Autonoma, 28049 Cantoblanco, Madrid, Spain
| | - Jose Maria Carazo
- Biocomputing Unit, Centro
Nacional de Biotecnologia (CNB-CSIC), Darwin, 3, Campus Universidad Autonoma, 28049 Cantoblanco, Madrid, Spain
| | - Carlos Oscar S. Sorzano
- Biocomputing Unit, Centro
Nacional de Biotecnologia (CNB-CSIC), Darwin, 3, Campus Universidad Autonoma, 28049 Cantoblanco, Madrid, Spain
| |
Collapse
|
10
|
Eldar A, Amos I, Shkolnisky Y. ASOCEM: Automatic Segmentation Of Contaminations in cryo-EM. J Struct Biol 2022; 214:107871. [DOI: 10.1016/j.jsb.2022.107871] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2022] [Revised: 05/10/2022] [Accepted: 05/17/2022] [Indexed: 11/25/2022]
|
11
|
Sorzano COS, Jiménez-Moreno A, Maluenda D, Martínez M, Ramírez-Aportela E, Krieger J, Melero R, Cuervo A, Conesa J, Filipovic J, Conesa P, del Caño L, Fonseca YC, Jiménez-de la Morena J, Losana P, Sánchez-García R, Strelak D, Fernández-Giménez E, de Isidro-Gómez FP, Herreros D, Vilas JL, Marabini R, Carazo JM. On bias, variance, overfitting, gold standard and consensus in single-particle analysis by cryo-electron microscopy. Acta Crystallogr D Struct Biol 2022; 78:410-423. [PMID: 35362465 PMCID: PMC8972802 DOI: 10.1107/s2059798322001978] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2021] [Accepted: 02/18/2022] [Indexed: 12/05/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- C. O. S. Sorzano
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - A. Jiménez-Moreno
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - D. Maluenda
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - M. Martínez
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - E. Ramírez-Aportela
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - J. Krieger
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - R. Melero
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - A. Cuervo
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - J. Conesa
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | | | - P. Conesa
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - L. del Caño
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - Y. C. Fonseca
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - J. Jiménez-de la Morena
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - P. Losana
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - R. Sánchez-García
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - D. Strelak
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
- Masaryk University, Brno, Czech Republic
| | - E. Fernández-Giménez
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - F. P. de Isidro-Gómez
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - D. Herreros
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - J. L. Vilas
- School of Engineering and Applied Science, Yale University, New Haven, CT 06520-829, USA
| | - R. Marabini
- Escuela Politecnica Superior, Universidad Autónoma de Madrid, 28049 Cantoblanco, Madrid, Spain
| | - J. M. Carazo
- Biocomputing Unit, Centro Nacional de Biotecnologia (CNB-CSIC), Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| |
Collapse
|
12
|
Treder KP, Huang C, Kim JS, Kirkland AI. Applications of deep learning in electron microscopy. Microscopy (Oxf) 2022; 71:i100-i115. [DOI: 10.1093/jmicro/dfab043] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2021] [Revised: 08/30/2021] [Accepted: 11/08/2021] [Indexed: 12/25/2022] Open
Abstract
Abstract
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.
Collapse
Affiliation(s)
- Kevin P Treder
- Department of Materials, University of Oxford, Oxford, Oxfordshire OX1 3PH, UK
| | - Chen Huang
- Rosalind Franklin Institute, Harwell Research Campus, Didcot, Oxfordshire OX11 0FA, UK
| | - Judy S Kim
- Department of Materials, University of Oxford, Oxford, Oxfordshire OX1 3PH, UK
- Rosalind Franklin Institute, Harwell Research Campus, Didcot, Oxfordshire OX11 0FA, UK
| | - Angus I Kirkland
- Department of Materials, University of Oxford, Oxford, Oxfordshire OX1 3PH, UK
- Rosalind Franklin Institute, Harwell Research Campus, Didcot, Oxfordshire OX11 0FA, UK
| |
Collapse
|
13
|
Wu JG, Yan Y, Zhang DX, Liu BW, Zheng QB, Xie XL, Liu SQ, Ge SX, Hou ZG, Xia NS. Machine Learning for Structure Determination in Single-Particle Cryo-Electron Microscopy: A Systematic Review. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022; 33:452-472. [PMID: 34932487 DOI: 10.1109/tnnls.2021.3131325] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
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.
Collapse
|
14
|
Advances in Xmipp for Cryo-Electron Microscopy: From Xmipp to Scipion. Molecules 2021; 26:molecules26206224. [PMID: 34684805 PMCID: PMC8537808 DOI: 10.3390/molecules26206224] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2021] [Revised: 09/28/2021] [Accepted: 09/29/2021] [Indexed: 11/21/2022] Open
Abstract
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.
Collapse
|
15
|
Pakhrin SC, Shrestha B, Adhikari B, KC DB. Deep Learning-Based Advances in Protein Structure Prediction. Int J Mol Sci 2021; 22:5553. [PMID: 34074028 PMCID: PMC8197379 DOI: 10.3390/ijms22115553] [Citation(s) in RCA: 47] [Impact Index Per Article: 15.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2021] [Revised: 05/12/2021] [Accepted: 05/18/2021] [Indexed: 12/29/2022] Open
Abstract
Obtaining an accurate description of protein structure is a fundamental step toward understanding the underpinning of biology. Although recent advances in experimental approaches have greatly enhanced our capabilities to experimentally determine protein structures, the gap between the number of protein sequences and known protein structures is ever increasing. Computational protein structure prediction is one of the ways to fill this gap. Recently, the protein structure prediction field has witnessed a lot of advances due to Deep Learning (DL)-based approaches as evidenced by the success of AlphaFold2 in the most recent Critical Assessment of protein Structure Prediction (CASP14). In this article, we highlight important milestones and progresses in the field of protein structure prediction due to DL-based methods as observed in CASP experiments. We describe advances in various steps of protein structure prediction pipeline viz. protein contact map prediction, protein distogram prediction, protein real-valued distance prediction, and Quality Assessment/refinement. We also highlight some end-to-end DL-based approaches for protein structure prediction approaches. Additionally, as there have been some recent DL-based advances in protein structure determination using Cryo-Electron (Cryo-EM) microscopy based, we also highlight some of the important progress in the field. Finally, we provide an outlook and possible future research directions for DL-based approaches in the protein structure prediction arena.
Collapse
Affiliation(s)
- Subash C. Pakhrin
- Department of Electrical Engineering and Computer Science, Wichita State University, Wichita, KS 67260, USA;
| | - Bikash Shrestha
- Department of Computer Science, University of Missouri-St. Louis, St. Louis, MO 63121, USA;
| | - Badri Adhikari
- Department of Computer Science, University of Missouri-St. Louis, St. Louis, MO 63121, USA;
| | - Dukka B. KC
- Department of Electrical Engineering and Computer Science, Wichita State University, Wichita, KS 67260, USA;
| |
Collapse
|
16
|
Kyrilis FL, Belapure J, Kastritis PL. Detecting Protein Communities in Native Cell Extracts by Machine Learning: A Structural Biologist's Perspective. Front Mol Biosci 2021; 8:660542. [PMID: 33937337 PMCID: PMC8082361 DOI: 10.3389/fmolb.2021.660542] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2021] [Accepted: 03/18/2021] [Indexed: 11/13/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Fotis L. Kyrilis
- Interdisciplinary Research Center HALOmem, Charles Tanford Protein Center, Martin Luther University Halle-Wittenberg, Halle (Saale), Germany
- Institute of Biochemistry and Biotechnology, Martin Luther University Halle-Wittenberg, Halle (Saale), Germany
| | - Jaydeep Belapure
- Interdisciplinary Research Center HALOmem, Charles Tanford Protein Center, Martin Luther University Halle-Wittenberg, Halle (Saale), Germany
| | - Panagiotis L. Kastritis
- Interdisciplinary Research Center HALOmem, Charles Tanford Protein Center, Martin Luther University Halle-Wittenberg, Halle (Saale), Germany
- Institute of Biochemistry and Biotechnology, Martin Luther University Halle-Wittenberg, Halle (Saale), Germany
- Biozentrum, Martin Luther University Halle-Wittenberg, Halle (Saale), Germany
| |
Collapse
|
17
|
Thurber KR, Yin Y, Tycko R. Automated picking of amyloid fibrils from cryo-EM images for helical reconstruction with RELION. J Struct Biol 2021; 213:107736. [PMID: 33831509 DOI: 10.1016/j.jsb.2021.107736] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/12/2021] [Revised: 03/31/2021] [Accepted: 04/01/2021] [Indexed: 11/16/2022]
Abstract
Cryogenic electron microscopy (cryo-EM) is an important tool for determining the molecular structure of proteins and protein assemblies, including helical assemblies such as amyloid fibrils. In reconstruction of amyloid fibril structures from cryo-EM images, an important early step is the selection of fibril locations. This fibril picking step is typically done by hand, a tedious process when thousands of images need to be analyzed. Here we present a computer program called FibrilFinder that identifies the locations and directions of fibril segments in cryo-EM images, by using the properties that the fibrils should be linear objects and have widths within a specified range. The program outputs the fibril locations in text files compatible with the RELION density reconstruction program. After RELION is used to extract the particle image boxes contained in the fibril segments identified by FibrilFinder, a second program called FibrilFixer removes boxes that contain more than one fibril, for instance because two fibrils cross each other. As concrete and realistic examples, we describe the application of the two programs to cryo-EM images of two different amyloid fibrils, namely 40-residue amyloid-β fibrils derived from human brain tissue by seeded growth and fibrils formed by the C-terminal half of the low-complexity domain of the RNA-binding protein FUS. Both examples of amyloid fibrils can be picked from cryo-EM images using the same set of FibrilFinder and FibrilFixer parameters, showing that this software does not require re-optimization for each sample. A set of 1337 cryo-EM images was analyzed in 17 min with one multi-core computer. The new fibril picking software should enable the rapid analysis and comparison of more helical structures using cryo-EM, and perhaps serve as part of the greater automation of the entire structure determination process.
Collapse
Affiliation(s)
- Kent R Thurber
- Laboratory of Chemical Physics, National Institute of Diabetes and Digestive and Kidney Diseases, National Institutes of Health, Bethesda, MD 20892-0520, USA.
| | - Yi Yin
- Nuffield Department of Women's & Reproductive Health, University of Oxford, Oxford OX3 9DU, UK
| | - Robert Tycko
- Laboratory of Chemical Physics, National Institute of Diabetes and Digestive and Kidney Diseases, National Institutes of Health, Bethesda, MD 20892-0520, USA
| |
Collapse
|
18
|
Abstract
Abstract
Deep learning is transforming most areas of science and technology, including electron microscopy. This review paper offers a practical perspective aimed at developers with limited familiarity. For context, we review popular applications of deep learning in electron microscopy. Following, we discuss hardware and software needed to get started with deep learning and interface with electron microscopes. We then review neural network components, popular architectures, and their optimization. Finally, we discuss future directions of deep learning in electron microscopy.
Collapse
|
19
|
Melero R, Sorzano COS, Foster B, Vilas JL, Martínez M, Marabini R, Ramírez-Aportela E, Sanchez-Garcia R, Herreros D, del Caño L, Losana P, Fonseca-Reyna YC, Conesa P, Wrapp D, Chacon P, McLellan JS, Tagare HD, Carazo JM. Continuous flexibility analysis of SARS-CoV-2 spike prefusion structures. IUCRJ 2020; 7:S2052252520012725. [PMID: 33063791 PMCID: PMC7553147 DOI: 10.1107/s2052252520012725] [Citation(s) in RCA: 28] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/23/2020] [Accepted: 09/18/2020] [Indexed: 05/09/2023]
Abstract
Using a new consensus-based image-processing approach together with principal component analysis, the flexibility and conformational dynamics of the SARS-CoV-2 spike in the prefusion state have been analysed. These studies revealed concerted motions involving the receptor-binding domain (RBD), N-terminal domain, and subdomains 1 and 2 around the previously characterized 1-RBD-up state, which have been modeled as elastic deformations. It is shown that in this data set there are not well defined, stable spike conformations, but virtually a continuum of states. An ensemble map was obtained with minimum bias, from which the extremes of the change along the direction of maximal variance were modeled by flexible fitting. The results provide a warning of the potential image-processing classification instability of these complicated data sets, which has a direct impact on the interpretability of the results.
Collapse
Affiliation(s)
- Roberto Melero
- Centro Nacional de Biotecnologia–CSIC, Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | | | - Brent Foster
- Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT 06520, USA
| | - José-Luis Vilas
- Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT 06520, USA
| | - Marta Martínez
- Centro Nacional de Biotecnologia–CSIC, Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - Roberto Marabini
- Centro Nacional de Biotecnologia–CSIC, Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
- Universidad Autónoma de Madrid, Calle Francisco Tomás y Valiente 11, 28049 Cantoblanco, Madrid, Spain
| | | | - Ruben Sanchez-Garcia
- Centro Nacional de Biotecnologia–CSIC, Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - David Herreros
- Centro Nacional de Biotecnologia–CSIC, Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - Laura del Caño
- Centro Nacional de Biotecnologia–CSIC, Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - Patricia Losana
- Centro Nacional de Biotecnologia–CSIC, Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | | | - Pablo Conesa
- Centro Nacional de Biotecnologia–CSIC, Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| | - Daniel Wrapp
- Department of Molecular Biosciences, The University of Texas at Austin, Austin, TX 78712, USA
| | - Pablo Chacon
- Department of Biological Physical Chemistry, Instituto Rocasolano–CSIC, Calle de Serrano 119, 28006 Madrid, Spain
| | - Jason S. McLellan
- Department of Molecular Biosciences, The University of Texas at Austin, Austin, TX 78712, USA
| | - Hemant D. Tagare
- Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT 06520, USA
| | - Jose-Maria Carazo
- Centro Nacional de Biotecnologia–CSIC, Calle Darwin 3, 28049 Cantoblanco, Madrid, Spain
| |
Collapse
|
20
|
Melero R, Sorzano COS, Foster B, Vilas JL, Martínez M, Marabini R, Ramírez-Aportela E, Sanchez-Garcia R, Herreros D, del Caño L, Losana P, Fonseca-Reyna YC, Conesa P, Wrapp D, Chacon P, McLellan JS, Tagare HD, Carazo JM. Continuous flexibility analysis of SARS-CoV-2 Spike prefusion structures. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2020:2020.07.08.191072. [PMID: 32676604 PMCID: PMC7359526 DOI: 10.1101/2020.07.08.191072] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
Abstract
With the help of novel processing workflows and algorithms, we have obtained a better understanding of the flexibility and conformational dynamics of the SARS-CoV-2 spike in the prefusion state. We have re-analyzed previous cryo-EM data combining 3D clustering approaches with ways to explore a continuous flexibility space based on 3D Principal Component Analysis. These advanced analyses revealed a concerted motion involving the receptor-binding domain (RBD), N-terminal domain (NTD), and subdomain 1 and 2 (SD1 & SD2) around the previously characterized 1-RBD-up state, which have been modeled as elastic deformations. We show that in this dataset there are not well-defined, stable, spike conformations, but virtually a continuum of states moving in a concerted fashion. We obtained an improved resolution ensemble map with minimum bias, from which we model by flexible fitting the extremes of the change along the direction of maximal variance. Moreover, a high-resolution structure of a recently described biochemically stabilized form of the spike is shown to greatly reduce the dynamics observed for the wild-type spike. Our results provide new detailed avenues to potentially restrain the spike dynamics for structure-based drug and vaccine design and at the same time give a warning of the potential image processing classification instability of these complicated datasets, having a direct impact on the interpretability of the results.
Collapse
Affiliation(s)
- Roberto Melero
- Centro Nacional de Biotecnologia-CSIC, C/ Darwin, 3, 28049, Cantoblanco, Madrid, Spain
| | | | - Brent Foster
- Dept. of Radiology and Biomedical Imaging, Yale University, New Haven, CT 06520, USA
| | - José-Luis Vilas
- Dept. of Radiology and Biomedical Imaging, Yale University, New Haven, CT 06520, USA
| | - Marta Martínez
- Centro Nacional de Biotecnologia-CSIC, C/ Darwin, 3, 28049, Cantoblanco, Madrid, Spain
| | - Roberto Marabini
- Centro Nacional de Biotecnologia-CSIC, C/ Darwin, 3, 28049, Cantoblanco, Madrid, Spain
- Universidad Autónoma de Madrid, c/Tomás y Valiente, 11, 28049, Cantoblanco, Madrid, Spain
| | | | - Ruben Sanchez-Garcia
- Centro Nacional de Biotecnologia-CSIC, C/ Darwin, 3, 28049, Cantoblanco, Madrid, Spain
| | - David Herreros
- Centro Nacional de Biotecnologia-CSIC, C/ Darwin, 3, 28049, Cantoblanco, Madrid, Spain
| | - Laura del Caño
- Centro Nacional de Biotecnologia-CSIC, C/ Darwin, 3, 28049, Cantoblanco, Madrid, Spain
| | - Patricia Losana
- Centro Nacional de Biotecnologia-CSIC, C/ Darwin, 3, 28049, Cantoblanco, Madrid, Spain
| | | | - Pablo Conesa
- Centro Nacional de Biotecnologia-CSIC, C/ Darwin, 3, 28049, Cantoblanco, Madrid, Spain
| | - Daniel Wrapp
- Department of Molecular Biosciences, The University of Texas at Austin, Austin, TX 78712, USA
| | - Pablo Chacon
- Instituto Rocasolano-CSIC, c/Serrano, 119, 28006, Madrid, Spain
| | - Jason S. McLellan
- Department of Molecular Biosciences, The University of Texas at Austin, Austin, TX 78712, USA
| | - Hemant D. Tagare
- Dept. of Radiology and Biomedical Imaging, Yale University, New Haven, CT 06520, USA
| | - Jose-Maria Carazo
- Centro Nacional de Biotecnologia-CSIC, C/ Darwin, 3, 28049, Cantoblanco, Madrid, Spain
| |
Collapse
|
21
|
Wagner T, Lusnig L, Pospich S, Stabrin M, Schönfeld F, Raunser S. Two particle-picking procedures for filamentous proteins: SPHIRE-crYOLO filament mode and SPHIRE-STRIPER. ACTA CRYSTALLOGRAPHICA SECTION D-STRUCTURAL BIOLOGY 2020; 76:613-620. [PMID: 32627734 PMCID: PMC7336381 DOI: 10.1107/s2059798320007342] [Citation(s) in RCA: 36] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/28/2020] [Accepted: 06/01/2020] [Indexed: 12/03/2022]
Abstract
Two approaches for the selection of filaments from cryo-EM micrographs are described. Structure determination of filamentous molecular complexes involves the selection of filaments from cryo-EM micrographs. The automatic selection of helical specimens is particularly difficult, and thus many challenging samples with issues such as contamination or aggregation are still manually picked. Here, two approaches for selecting filamentous complexes are presented: one uses a trained deep neural network to identify the filaments and is integrated in SPHIRE-crYOLO, while the other, called SPHIRE-STRIPER, is based on a classical line-detection approach. The advantage of the crYOLO-based procedure is that it performs accurately on very challenging data sets and selects filaments with high accuracy. Although STRIPER is less precise, the user benefits from less intervention, since in contrast to crYOLO, STRIPER does not require training. The performance of both procedures on Tobacco mosaic virus and filamentous F-actin data sets is described to demonstrate the robustness of each method.
Collapse
Affiliation(s)
- Thorsten Wagner
- Department of Structural Biochemistry, Max Planck Institute of Molecular Physiology, Otto-Hahn-Strasse 11, 44227 Dortmund, Germany
| | - Luca Lusnig
- Department of Structural Biochemistry, Max Planck Institute of Molecular Physiology, Otto-Hahn-Strasse 11, 44227 Dortmund, Germany
| | - Sabrina Pospich
- Department of Structural Biochemistry, Max Planck Institute of Molecular Physiology, Otto-Hahn-Strasse 11, 44227 Dortmund, Germany
| | - Markus Stabrin
- Department of Structural Biochemistry, Max Planck Institute of Molecular Physiology, Otto-Hahn-Strasse 11, 44227 Dortmund, Germany
| | - Fabian Schönfeld
- Department of Structural Biochemistry, Max Planck Institute of Molecular Physiology, Otto-Hahn-Strasse 11, 44227 Dortmund, Germany
| | - Stefan Raunser
- Department of Structural Biochemistry, Max Planck Institute of Molecular Physiology, Otto-Hahn-Strasse 11, 44227 Dortmund, Germany
| |
Collapse
|