3D Structure from 2D Microscopy images using Deep Learning
This addresses the challenge of accurate 3D structure determination from 2D microscopy images for biologists, though it appears incremental as it builds on existing AI approaches in this domain.
The paper tackles the problem of reconstructing 3D protein structures from 2D microscopy images by introducing a deep learning method that uses a convolutional neural network with a differentiable renderer to predict poses and derive a single structural model, demonstrating its performance on protein complexes like CEP152 and centrioles.
Understanding the structure of a protein complex is crucial indetermining its function. However, retrieving accurate 3D structures from microscopy images is highly challenging, particularly as many imaging modalities are two-dimensional. Recent advances in Artificial Intelligence have been applied to this problem, primarily using voxel based approaches to analyse sets of electron microscopy images. Herewe present a deep learning solution for reconstructing the protein com-plexes from a number of 2D single molecule localization microscopy images, with the solution being completely unconstrained. Our convolutional neural network coupled with a differentiable renderer predicts pose and derives a single structure. After training, the network is dis-carded, with the output of this method being a structural model which fits the data-set. We demonstrate the performance of our system on two protein complexes: CEP152 (which comprises part of the proximal toroid of the centriole) and centrioles.