{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Blundell B"],"funding":["Biotechnology and Biological Sciences Research Council"],"pagination":["740342"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9581024"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["1"],"pubmed_abstract":["Understanding the structure of a protein complex is crucial in determining 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. Here we present a deep learning solution for reconstructing the protein complexes 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 discarded, 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."],"journal":["Frontiers in bioinformatics"],"pubmed_title":["3D Structure From 2D Microscopy Images Using Deep Learning."],"pmcid":["PMC9581024"],"funding_grant_id":["BB/S507519/1","BB/M009513/1"],"pubmed_authors":["Sieben C","Manley S","Cox S","Blundell B","Ch'ng Q","Rosten E"],"additional_accession":[]},"is_claimable":false,"name":"3D Structure From 2D Microscopy Images Using Deep Learning.","description":"Understanding the structure of a protein complex is crucial in determining 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. Here we present a deep learning solution for reconstructing the protein complexes 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 discarded, 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.","dates":{"release":"2021-01-01T00:00:00Z","publication":"2021","modification":"2025-04-03T21:29:33.756Z","creation":"2025-04-03T21:29:33.756Z"},"accession":"S-EPMC9581024","cross_references":{"pubmed":["36303741"],"doi":["10.3389/fbinf.2021.740342"]}}