Cargando…

3D Structure From 2D Microscopy Images Using Deep Learning

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Blundell, Benjamin, Sieben, Christian, Manley, Suliana, Rosten, Ed, Ch’ng, QueeLim, Cox, Susan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9581024/
https://www.ncbi.nlm.nih.gov/pubmed/36303741
http://dx.doi.org/10.3389/fbinf.2021.740342
_version_ 1784812524874498048
author Blundell, Benjamin
Sieben, Christian
Manley, Suliana
Rosten, Ed
Ch’ng, QueeLim
Cox, Susan
author_facet Blundell, Benjamin
Sieben, Christian
Manley, Suliana
Rosten, Ed
Ch’ng, QueeLim
Cox, Susan
author_sort Blundell, Benjamin
collection PubMed
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.
format Online
Article
Text
id pubmed-9581024
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-95810242022-10-26 3D Structure From 2D Microscopy Images Using Deep Learning Blundell, Benjamin Sieben, Christian Manley, Suliana Rosten, Ed Ch’ng, QueeLim Cox, Susan Front Bioinform Bioinformatics 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. Frontiers Media S.A. 2021-10-28 /pmc/articles/PMC9581024/ /pubmed/36303741 http://dx.doi.org/10.3389/fbinf.2021.740342 Text en Copyright © 2021 Blundell, Sieben, Manley, Rosten, Ch’ng and Cox. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Bioinformatics
Blundell, Benjamin
Sieben, Christian
Manley, Suliana
Rosten, Ed
Ch’ng, QueeLim
Cox, Susan
3D Structure From 2D Microscopy Images Using Deep Learning
title 3D Structure From 2D Microscopy Images Using Deep Learning
title_full 3D Structure From 2D Microscopy Images Using Deep Learning
title_fullStr 3D Structure From 2D Microscopy Images Using Deep Learning
title_full_unstemmed 3D Structure From 2D Microscopy Images Using Deep Learning
title_short 3D Structure From 2D Microscopy Images Using Deep Learning
title_sort 3d structure from 2d microscopy images using deep learning
topic Bioinformatics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9581024/
https://www.ncbi.nlm.nih.gov/pubmed/36303741
http://dx.doi.org/10.3389/fbinf.2021.740342
work_keys_str_mv AT blundellbenjamin 3dstructurefrom2dmicroscopyimagesusingdeeplearning
AT siebenchristian 3dstructurefrom2dmicroscopyimagesusingdeeplearning
AT manleysuliana 3dstructurefrom2dmicroscopyimagesusingdeeplearning
AT rostened 3dstructurefrom2dmicroscopyimagesusingdeeplearning
AT chngqueelim 3dstructurefrom2dmicroscopyimagesusingdeeplearning
AT coxsusan 3dstructurefrom2dmicroscopyimagesusingdeeplearning