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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Understanding the structure of a protein complex is crucial indetermining itsfunction. However, retrieving accurate 3D structures from microscopy images ishighly challenging, particularly as many imaging modalities aretwo-dimensional. Recent advances in Artificial Intelligence have been appliedto this problem, primarily using voxel based approaches to analyse sets ofelectron microscopy images. Herewe present a deep learning solution forreconstructing the protein com-plexes from a number of 2D single moleculelocalization microscopy images, with the solution being completelyunconstrained. Our convolutional neural network coupled with a differentiablerenderer predicts pose and derives a single structure. After training, thenetwork is dis-carded, with the output of this method being a structural modelwhich fits the data-set. We demonstrate the performance of our system on twoprotein complexes: CEP152 (which comprises part of the proximal toroid of thecentriole) and centrioles.

3D Structure from 2D Microscopy images using Deep Learning