YYYue Yu

Yue Yu

*This is an algorithmically generated author record based on publicly available information.

Yue Yu has a total of 146 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Lessons learned from a Kaggle challenge for particle picking in cryo-electron tomography

    by Ariana Peck, Joshua Hutchings, Jonathan Schwartz, Yue Yu, Utz H. Ermel, Saugat Kandel, Dari Kimanius, Zhuowen Zhao, Shawn Zheng, Brendan Artley, et al.


  • Open Access

    A Crossed Laser Phase Plate for CryoEM

    by Yue Yu, Anchi Cheng, Elizabeth Montabana, Noeli Paz Soldán, Eric S. Cooper, Jessie T. Zhang, Jeremy J. Axelrod, Petar N. Petrov, Amir Torkaman, Dylan Roof, et al.

    The laser phase plate (LPP) enables phase-contrast imaging in cryogenic electron microscopy (cryoEM), enhancing image contrast without compromising high-resolution information. Here we report the implementation of a crossed laser phase plate (xLPP) comprising two optical cavities oriented orthogonally, installed in a ThermoFisher Scientific Krios G4 microscope equipped with a newly designed transfer lens module. We demonstrate the expected, strong contrast enhancement and stable, additive phase shifts of 90°, with a contrast transfer function (CTF) that closely matches theory. Single-particle analysis (SPA) of apoferritin, a standard benchmark sample, reached a resolution of 1.79 Å, demonstrating the system is capable of acquiring high-resolution cryoEM data. When imaging thick E. coli cells (∼350 nm), the xLPP enhances contrast and increases low-frequency template-matching signal. Together, these results establish the feasibility of the xLPP and highlight its potential for high-contrast, high-resolution cryoEM imaging of biological systems.


  • Top Cited Papers
    Open Access

    Language Modeling Materializes a World Model of Protein Biology

    by Salvatore Candido, Thomas Hayes, Alexander Derry, Roshan Rao, Zeming Lin, Robert Verkuil, Bryan Z. Wu, Jin Sub Lee, Elise S. Bruguera, Jehan A. Keval, et al.

    Proteins are fundamental to life. The full extent of their biology is beyond our ability to characterize with experimental approaches in the physical laboratory. Accurate digital representations could accelerate the discovery of protein biology through virtual experiments. We propose language modeling to learn unified and general representations that can be scaled to all of protein biology. Building on these representations, we develop a structure prediction model that exceeds the performance of established methods for biomolecular complex prediction across benchmarks, including for the interactions of antibodies with their targets. A simple search procedure yields high experimental success rates for the discovery of proteins with nanomolar binding affinities for both miniproteins and single-chain antibodies, a modality critical for therapeutic design. Study of the concepts in the language model's representation space reveals a systematic organization aligned with the reductionist understanding of proteins developed through empirical science. Leveraging this organization, we generate a comprehensive map of protein biology encompassing over 6.8 billion sequences and 1.1 billion predicted structures, identifying connections across known and unknown biology. As a whole, this shows language modeling as a powerful substrate for representing the biology of proteins, operating across scales from the prediction and design of protein interactions at the atomic level, to identifying properties of proteins at different levels of granularity and abstraction, to the scale of mapping connections between proteins across billions of years of evolution.


  • Top Cited Papers
    Open Access

    AreTomoLive: automated reconstruction of comprehensively corrected and denoised cryo-electron tomograms in real time and at high throughput

    by Ariana Peck, Yue Yu, Mohammadreza Paraan, Dari Kimanius, Utz H. Ermel, Joshua Hutchings, Jonathan Schwartz, Daniel Serwas, Hannah Siems, Norbert S. Hill, et al.

    High-throughput data processing is necessary to realize the full potential of cryo-electron tomography and subtomogram averaging. The field’s fragmented software landscape remains a considerable hurdle to this end. Here we present AreTomoLive, an automated preprocessing pipeline composed of two GPU-accelerated packages. The first, AreTomo3, streamlines tomographic alignment and reconstruction, with new features to fully account for sample geometry and locally correct the contrast transfer function. The second package, DenoisET, leverages AreTomo3’s comprehensively corrected tomograms to retain more intermediate-resolution features during contrast enhancement. Collectively, this pipeline prioritizes automation to support data preprocessing concurrent with data collection at scale.


  • Open Access

    Evaluating the Volta phase plate for improved tomogram alignment in cryo-electron tomography

    by Joshua Hutchings, Daniel Ji, Shawn Zheng, Elizabeth A. Montabana, Utz H. Ermel, Ariana Peck, Jonathan Schwartz, Rahel Woldeyes, Mohammadreza Paraan, Mallak Ali, et al.

    The Volta phase plate (VPP) can enhance low-frequency phase contrast in cryo-electron microscopy (cryo-EM) and cryo-electron tomography (cryo-ET), but its impact on tomogram alignment has not been systematically assessed. Using sub-2 Å single-particle analysis (SPA) and analytical contrast transfer function (CTF) modeling, we show that despite high-frequency information loss and moderate signal damping, the VPP enhances signal in low-frequency bands that are crucial for tilt-series alignment. We show that VPP tomograms exhibit increased contrast and remain higher in contrast post denoising, for thick and crowded specimens. Quantitative comparison of tomograms acquired with and without the VPP shows improved tilt-axis orientation measurements and a higher fraction of tomograms amenable to local tilt-series alignment. Although acquisition with the VPP yields lower subtomogram averaging (STA) resolution, these results show that the primary benefits of the VPP for cryo-ET are contrast enhancement and improved tilt-series alignment robustness, which are crucial for studying cellular ultrastructure and protein organization in crowded environments, where STA at moderate resolutions remains valuable.


  • Open Access

    Lessons learned from a Kaggle challenge for particle picking in cryo-electron tomography

    by Ariana Peck, Joshua Hutchings, Jonathan Schwartz, Yue Yu, Utz H. Ermel, Saugat Kandel, Dari Kimanius, Zhuowen Zhao, Shawn Zheng, Brendan Artley, et al.

    The difficulty of particle picking in cryo-electron tomography remains a barrier to routine in situ structure determination. Machine learning is well-suited to overcome this bottleneck with efficient algorithms that generalize across molecular species. To spur new algorithm development, we held a three-month Kaggle challenge that tasked contestants with annotating five molecular species across hundreds of experimental tomograms. This competition successfully engaged >1000 participants from diverse fields and delivered particle pickers that outperformed existing state-of-the-art. Systematic comparisons of the contestants’ submissions revealed the tolerance of subtomogram averaging to moderate but not severe over-picking and underscored the need for more robust measures of annotation quality. The winning models also highlighted the importance of data augmentation to overcome limited training data. All competition tomograms along with the ground truth and winning teams’ annotations have been released on the CryoET Data Portal as a resource to benchmark current and future tools for particle picking.


  • Top Cited Papers
    Open Access

    Dose-efficient cryo-electron microscopy for thick samples using tilt- corrected scanning transmission electron microscopy

    by Yue Yu, Katherine A. Spoth, Michael Colletta, Kayla X. Nguyen, Steven E. Zeltmann, Xiyue S. Zhang, Mohammadreza Paraan, Mykhailo Kopylov, Charlie Dubbeldam, Daniel Serwas, et al.

    Cryogenic electron microscopy is a powerful tool in structural biology. In thick specimens, challenges arise as an exponentially larger fraction of the transmitted electrons lose energy from inelastic scattering and can no longer be properly focused as a result of chromatic aberrations in the post-specimen optics. Rather than filtering out the inelastic scattering at the price of reducing potential signal, as is done in energy-filtered transmission electron microscopy, we show how a dose-efficient and unfiltered image can be rapidly obtained using tilt-corrected bright-field scanning transmission electron microscopy data collected on a pixelated detector. Enhanced contrast and a 3–5× improvement in dose efficiency are observed for two-dimensional images of intact bacterial cells and large organelles using tilt-corrected bright-field scanning transmission electron microscopy compared to energy-filtered transmission electron microscopy for thicknesses beyond 500 nm. As a proof of concept for the technique’s performance in structural determination, we present a single-particle analysis map at sub-nanometer resolution for a highly symmetric virus-like particle determined from 789 particles.


  • Open Access

    A realistic phantom dataset for benchmarking cryo-ET data annotation

    by Ariana Peck, Yue Yu, Jonathan Schwartz, Anchi Cheng, Utz Heinrich Ermel, Joshua Hutchings, Saugat Kandel, Dari Kimanius, Elizabeth A. Montabana, Daniel Serwas, et al.

    Cryo-electron tomography (cryo-ET) is a powerful technique for imaging molecular complexes in their native cellular environments. However, identifying the vast majority of molecular species in cellular tomograms remains prohibitively difficult. Machine learning (ML) methods provide an opportunity to automate the annotation process, but algorithm development has been hindered by the lack of large, standardized datasets. Here we present an experimental phantom dataset with comprehensive ground-truth annotations for six molecular species to spur new algorithm development and benchmark existing tools. This annotated dataset is available on the CryoET Data Portal with infrastructure to streamline access for methods developers across fields.


  • Open Access

    AreTomoLive: Automated reconstruction of comprehensively-corrected and denoised cryo-electron tomograms in real-time and at high throughput

    by Ariana Peck, Yue Yu, Mohammadreza Paraan, Dari Kimanius, Utz Ermel, Joshua Hutchings, Daniel Serwas, Hannah Siems, Norbert Hill, Mallak Ali, et al.

    A high throughput processing pipeline that performs comprehensive corrections is needed to realize the full potential of cryo-electron tomography and subtomogram averaging. The field’s fragmented software landscape remains a significant hurdle to this end. Here we present AreTomoLive, an automated real-time pipeline composed of two GPU-accelerated packages. The first, AreTomo3, streamlines tomographic alignment and reconstruction, with new features to fully account for sample geometry, locally correct the contrast transfer function, and curate data for downstream tasks. The second package, DenoisET, is a new implementation of the machine learning algorithm Noise2Noise and runs in parallel with AreTomo3 to perform contrast enhancement. To reduce barriers to routine use, AreTomoLive prioritizes automation: AreTomo3 autonomously pauses and reactivates processing depending on the status of data collection, while DenoisET algorithmically determines when to transition from training to inference. AreTomoLive endeavors to advance cryoET for in situ structural analysis with its comprehensive corrections and full automation.


  • Open Access

    AreTomoLive: Automated reconstruction of comprehensively-corrected and denoised cryo-electron tomograms in real-time and at high throughput

    by Ariana Peck, Yue Yu, Mohammadreza Paraan, Dari Kimanius, Utz Heinrich Ermel, Joshua Hutchings, Daniel Serwas, Hannah Siems, Norbert S. Hill, Mallak Ali, et al.

    A high throughput processing pipeline that performs comprehensive corrections is needed to realize the full potential of cryo-electron tomography and subtomogram averaging. The field’s fragmented software landscape remains a significant hurdle to this end. Here we present AreTomoLive, an automated real-time pipeline composed of two GPU-accelerated packages. The first, AreTomo3, streamlines tomographic alignment and reconstruction, with new features to fully account for sample geometry, locally correct the contrast transfer function, and curate data for downstream tasks. The second package, DenoisET, is a new implementation of the machine learning algorithm Noise2Noise and runs in parallel with AreTomo3 to perform contrast enhancement. To reduce barriers to routine use, AreTomoLive prioritizes automation: AreTomo3 autonomously pauses and reactivates processing depending on the status of data collection, while DenoisET algorithmically determines when to transition from training to inference. AreTomoLive endeavors to advance cryoET for in situ structural analysis with its comprehensive corrections and full automation.