Scaling up cryo-EM for biology and chemistry: The journey from niche technology to mainstream method

de la Cruz, M. Jason; Eng, Edward T.

doi:10.1016/j.str.2023.09.009

Cited by 7 publications

(3 citation statements)

References 140 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent advancements in cryogenic electron microscopy (cryoEM) [1, 2] have elevated it from a specialized technique to a cornerstone of structural biology [3, 4]. Cryogenic electron tomography (cryoET), an extension of cryoEM, offers detailed three-dimensional (3D) representations of macromolecules, cells, and tissues in states close to their natural environment at nanometer-scale resolution [5].…”

Section: Introductionmentioning

confidence: 99%

Missing Wedge Completion via Unsupervised Learning with Coordinate Networks

Van Veen,

Galaz-Montoya,

Shen

et al. 2024

Preprint

View full text Add to dashboard Cite

Cryogenic electron tomography (cryoET) is a powerful tool in structural biology, enabling detailed 3D imaging of biological specimens at a resolution of nanometers. Despite its potential, cryoET faces challenges such as the missing wedge problem, which limits reconstruction quality due to incomplete data collection angles. Recently, supervised deep learning methods with convolutional neural networks (CNNs) have considerably addressed this issue; however, their pretraining renders them susceptible to inaccuracies and artifacts, particularly when representative training data is scarce. To overcome these limitations, we introduce a proof-of-concept unsupervised learning approach using coordinate networks (CNs) that optimizes network weights directly against input projections. This eliminates the need for pretraining, reducing reconstruction runtime by 3−20×compared to supervised methods. Our results from benchmarksin silicoshow improved shape completion and reduction of missing wedge artifacts, assessed through several voxel-based image quality metrics in real space and a novel directional Fourier Shell Correlation (FSC) metric. Our study illuminates benefits and considerations of both supervised and unsupervised approaches, guiding the development of improved reconstruction strategies.

show abstract

Section: Introductionmentioning

confidence: 99%

Missing Wedge Completion via Unsupervised Learning with Coordinate Networks

Van Veen,

Galaz-Montoya,

Shen

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Technological advances ranging from better specimen support grids ( Russo and Passmore, 2014 ; Yu et al, 2016 ; Noble et al, 2018 ; Doerr, 2019 ), cryopreservation devices ( Jain et al, 2012 ; Darrow et al, 2019 ), detectors ( Levin et al, 2023 ; Peng et al, 2023 ), microscopes ( Fréchin et al, 2023 ) and associated hardware such as energy filters ( Grimm et al, 1997 ), cold field emission guns ( Hamaguchi et al, 2019 ; Kato et al, 2019 ), phase plates ( Danev and Baumeister, 2017 ), and increasingly sophisticated and automated software for data collection ( Thompson et al, 2019 ) and processing ( Punjani et al, 2017 ) have reduced the cost of macromolecular structure determination by cryoEM SPA ( Chua et al, 2022 ), turning it from a niche technique into a mainstream method ( de la Cruz and Eng, 2023 ). Although SPA is unlikely to find immediate applications in histopathology, its technological developments spill over and benefit cryoET and related methodologies, the latter being predictably much more likely to revolutionize cellular pathology in the years to come.…”

Section: Introductionmentioning

confidence: 99%

The advent of preventive high-resolution structural histopathology by artificial-intelligence-powered cryogenic electron tomography

Galaz-Montoya

2024

Front. Mol. Biosci.

View full text Add to dashboard Cite

Advances in cryogenic electron microscopy (cryoEM) single particle analysis have revolutionized structural biology by facilitating the in vitro determination of atomic- and near-atomic-resolution structures for fully hydrated macromolecular complexes exhibiting compositional and conformational heterogeneity across a wide range of sizes. Cryogenic electron tomography (cryoET) and subtomogram averaging are rapidly progressing toward delivering similar insights for macromolecular complexes in situ, without requiring tags or harsh biochemical purification. Furthermore, cryoET enables the visualization of cellular and tissue phenotypes directly at molecular, nanometric resolution without chemical fixation or staining artifacts. This forward-looking review covers recent developments in cryoEM/ET and related technologies such as cryogenic focused ion beam milling scanning electron microscopy and correlative light microscopy, increasingly enhanced and supported by artificial intelligence algorithms. Their potential application to emerging concepts is discussed, primarily the prospect of complementing medical histopathology analysis. Machine learning solutions are poised to address current challenges posed by “big data” in cryoET of tissues, cells, and macromolecules, offering the promise of enabling novel, quantitative insights into disease processes, which may translate into the clinic and lead to improved diagnostics and targeted therapeutics.

show abstract

“…Recent advancements in cryogenic electron microscopy (cryoEM) [1,2] have elevated it from a specialized technique to a cornerstone of structural biology [3,4] and molecular sciences [5]. Cryogenic electron tomography (cryoET), an extension of cryoEM, offers detailed three-dimensional (3D) representations of macromolecules, cells, and tissues in states close to their natural environment at nanometer-scale resolution [6].…”

Section: Introductionmentioning

confidence: 99%

Missing Wedge Completion via Unsupervised Learning with Coordinate Networks

Van Veen,

Galaz-Montoya,

Shen

et al. 2024

IJMS

View full text Add to dashboard Cite

Cryogenic electron tomography (cryoET) is a powerful tool in structural biology, enabling detailed 3D imaging of biological specimens at a resolution of nanometers. Despite its potential, cryoET faces challenges such as the missing wedge problem, which limits reconstruction quality due to incomplete data collection angles. Recently, supervised deep learning methods leveraging convolutional neural networks (CNNs) have considerably addressed this issue; however, their pretraining requirements render them susceptible to inaccuracies and artifacts, particularly when representative training data is scarce. To overcome these limitations, we introduce a proof-of-concept unsupervised learning approach using coordinate networks (CNs) that optimizes network weights directly against input projections. This eliminates the need for pretraining, reducing reconstruction runtime by 3–20× compared to supervised methods. Our in silico results show improved shape completion and reduction of missing wedge artifacts, assessed through several voxel-based image quality metrics in real space and a novel directional Fourier Shell Correlation (FSC) metric. Our study illuminates benefits and considerations of both supervised and unsupervised approaches, guiding the development of improved reconstruction strategies.

show abstract

Scaling up cryo-EM for biology and chemistry: The journey from niche technology to mainstream method

Cited by 7 publications

References 140 publications

Missing Wedge Completion via Unsupervised Learning with Coordinate Networks

Missing Wedge Completion via Unsupervised Learning with Coordinate Networks

The advent of preventive high-resolution structural histopathology by artificial-intelligence-powered cryogenic electron tomography

Missing Wedge Completion via Unsupervised Learning with Coordinate Networks

Contact Info

Product

Resources

About