Fully Automated Multi-Grid Cryo-EM Screening using Smart Leginon

Cheng, Anchi; Kim, Paul T.; Kuang, Huihui; Mendez, Joshua H.; Chua, Eugene Y.D.; Maruthi, Kashyap; Wei, Hui; Sawh, Anjelique; Aragon, Mahira; Serbynovskyi, Viacheslav; Neselu, Kasahun; Potter, Clinton S; Carragher, Bridget; Bepler, Tristan; Noble, Alex J.

doi:10.1101/2022.07.23.501225

Cited by 3 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By training on large datasets of sparse microscope operator selection locations, the Ptolemy localization algorithms generalize to diverse gold and carbon holey grids and rank potential collection locations effectively without session-specific parameters, as we have demonstrated on held-out collection sessions within the SEMC/NYSBC dataset and on an independent dataset from another facility. Additionally, Ptolemy has been integrated with the microscope control software Leginon to enable automated data collection in real-life use cases (Cheng et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

“…For an example of integrating Ptolemy into cryoEM datacollection software in practice, please refer to the companion paper to Ptolemy, 'Fully automated multi-grid CryoEM screening using Smart Leginon' (Cheng et al, 2022).…”

Section: Appendix a Ptolemy Implementation Details And Default Modelsmentioning

confidence: 99%

“…Additionally, we compare our medium-magnification localization algorithm to an existing method (Yokoyama et al, 2020) that performs medium-magnification localization (in that study, this is referred to as low-magnification localization) and show that our method yields superior generalization performance. Finally, a separate companion paper has been published: 'Fully automated multi-grid CryoEM screening using Smart Leginon', where the utility of Ptolemy in real-world collection cases is demonstrated and analyzed (Cheng et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning to automate cryo-electron microscopy data collection with Ptolemy

Kim¹,

Noble²,

Cheng³

et al. 2023

IUCrJ

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Appendix a Ptolemy Implementation Details And Default Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning to automate cryo-electron microscopy data collection with Ptolemy

Kim¹,

Noble²,

Cheng³

et al. 2023

IUCrJ

Self Cite

View full text Add to dashboard Cite

show abstract

“…CryoRL is proposed as an algorithm for optimized path planning on the cryo-EM grid, and it is not available in the current data collection software yet. Also, cryoRL does not include any square or hole finders; therefore, other algorithms (Bouvette et al, 2021 ;Cheng et al, 2023 ;Kim et al, 2021 ) are needed to be used in combination with cryoRL. Moreover, the square and hole detectors and square classifiers provide an automatic solution for collecting the prerequisite information for path planning in cryoRL.…”

Section: Limitationsmentioning

confidence: 99%

Optimized path planning surpasses human efficiency in cryo-EM imaging

Fan

et al. 2023

Preprint

View full text Add to dashboard Cite

Cryo-electron microscopy (cryo-EM) represents a powerful technology for determining atomic models of biological macromolecules(Kühlbrandt, 2014). Despite this promise, human-guided cryo-EM data collection practices limit the impact of cryo-EM because of a path planning problem: cryo-EM datasets typically represent 2-5% of the total sample area. Here, we address this fundamental problem by formalizing cryo-EM data collection as a path planning optimization from low signal data. Within this framework, we incorporate reinforcement learning (RL) and deep regression to design an algorithm that uses distributed surveying of cryo-EM samples at low magnification to learn optimal cryo-EM data collection policies. Our algorithm - cryoRL - solves the problem of path planning on cryo-EM grids, allowing the algorithm to maximize data quality in a limited time without human intervention. A head-to-head comparison of cryoRL versus human subjects shows that cryoRL performs in the top 10% of test subjects, surpassing the majority of users in collecting high-quality images from the same sample. CryoRL establishes a general framework that will enable human-free cryo-EM data collection to increase the impact of cryo-EM across life sciences research.

show abstract