English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

X-ray free-electron lasers (XFELs) offer unique capabilities for measuringthe structure and dynamics of biomolecules, helping us understand the basicbuilding blocks of life. Notably, high-repetition-rate XFELs enable singleparticle imaging (X-ray SPI) where individual, weakly scattering biomoleculesare imaged under near-physiological conditions with the opportunity to accessfleeting states that cannot be captured in cryogenic or crystallizedconditions. Existing X-ray SPI reconstruction algorithms, which estimate theunknown orientation of a particle in each captured image as well as its shared3D structure, are inadequate in handling the massive datasets generated bythese emerging XFELs. Here, we introduce X-RAI, an online reconstructionframework that estimates the structure of a 3D macromolecule from large X-raySPI datasets. X-RAI consists of a convolutional encoder, which amortizes poseestimation over large datasets, as well as a physics-based decoder, whichemploys an implicit neural representation to enable high-quality 3Dreconstruction in an end-to-end, self-supervised manner. We demonstrate thatX-RAI achieves state-of-the-art performance for small-scale datasets insimulation and challenging experimental settings and demonstrate itsunprecedented ability to process large datasets containing millions ofdiffraction images in an online fashion. These abilities signify a paradigmshift in X-ray SPI towards real-time capture and reconstruction.

Scalable 3D Reconstruction From Single Particle X-Ray Diffraction Images Based on Online Machine Learning