Learning to automate cryo-electron microscopy data collection with Ptolemy
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...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
International Union of Crystallography
2023-01-01
|
| Series: | IUCrJ |
| Subjects: | |
| Online Access: | http://scripts.iucr.org/cgi-bin/paper?S2052252522010612 |
| _version_ | 1797961675230412800 |
|---|---|
| author | Paul T. Kim Alex J. Noble Anchi Cheng Tristan Bepler |
| author_facet | Paul T. Kim Alex J. Noble Anchi Cheng Tristan Bepler |
| author_sort | Paul T. Kim |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-11T01:02:32Z |
| format | Article |
| id | doaj.art-ec1a47dff0404b9a8981ff2f6acd35cc |
| institution | Directory Open Access Journal |
| issn | 2052-2525 |
| language | English |
| last_indexed | 2024-04-11T01:02:32Z |
| publishDate | 2023-01-01 |
| publisher | International Union of Crystallography |
| record_format | Article |
| series | IUCrJ |
| spelling | doaj.art-ec1a47dff0404b9a8981ff2f6acd35cc2023-01-04T15:52:32ZengInternational Union of CrystallographyIUCrJ2052-25252023-01-011019010210.1107/S2052252522010612pw5021Learning to automate cryo-electron microscopy data collection with PtolemyPaul T. Kim0Alex J. Noble1Anchi Cheng2Tristan Bepler3Simons Machine Learning Center, Simons Electron Microscopy Center, New York Structural Biology Center, New York, NY USASimons Machine Learning Center, Simons Electron Microscopy Center, New York Structural Biology Center, New York, NY USASimons Electron Microscopy Center, New York Structural Biology Center, New York, NY USASimons Machine Learning Center, Simons Electron Microscopy Center, New York Structural Biology Center, New York, NY USAOver 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.http://scripts.iucr.org/cgi-bin/paper?S2052252522010612cryoemautomated cryoem data collectioncomputer visionmicroscope automation softwaremachine learningdeep learningautomationsingle-particle cryoem |
| spellingShingle | Paul T. Kim Alex J. Noble Anchi Cheng Tristan Bepler Learning to automate cryo-electron microscopy data collection with Ptolemy IUCrJ cryoem automated cryoem data collection computer vision microscope automation software machine learning deep learning automation single-particle cryoem |
| title | Learning to automate cryo-electron microscopy data collection with Ptolemy |
| title_full | Learning to automate cryo-electron microscopy data collection with Ptolemy |
| title_fullStr | Learning to automate cryo-electron microscopy data collection with Ptolemy |
| title_full_unstemmed | Learning to automate cryo-electron microscopy data collection with Ptolemy |
| title_short | Learning to automate cryo-electron microscopy data collection with Ptolemy |
| title_sort | learning to automate cryo electron microscopy data collection with ptolemy |
| topic | cryoem automated cryoem data collection computer vision microscope automation software machine learning deep learning automation single-particle cryoem |
| url | http://scripts.iucr.org/cgi-bin/paper?S2052252522010612 |
| work_keys_str_mv | AT paultkim learningtoautomatecryoelectronmicroscopydatacollectionwithptolemy AT alexjnoble learningtoautomatecryoelectronmicroscopydatacollectionwithptolemy AT anchicheng learningtoautomatecryoelectronmicroscopydatacollectionwithptolemy AT tristanbepler learningtoautomatecryoelectronmicroscopydatacollectionwithptolemy |