Cargando…
Adaptive differentiable grids for cryo-electron tomography reconstruction and denoising
MOTIVATION: Tilt-series cryo-electron tomography is a powerful tool widely used in structural biology to study 3D structures of micro-organisms, macromolecular complexes, etc. Still, the reconstruction process remains an arduous task due to several challenges: The missing-wedge acquisition, sample m...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10560095/ https://www.ncbi.nlm.nih.gov/pubmed/37810456 http://dx.doi.org/10.1093/bioadv/vbad131 |
_version_ | 1785117656058167296 |
---|---|
author | Wang, Yuanhao Idoughi, Ramzi Rückert, Darius Li, Rui Heidrich, Wolfgang |
author_facet | Wang, Yuanhao Idoughi, Ramzi Rückert, Darius Li, Rui Heidrich, Wolfgang |
author_sort | Wang, Yuanhao |
collection | PubMed |
description | MOTIVATION: Tilt-series cryo-electron tomography is a powerful tool widely used in structural biology to study 3D structures of micro-organisms, macromolecular complexes, etc. Still, the reconstruction process remains an arduous task due to several challenges: The missing-wedge acquisition, sample misalignment and motion, the need to process large data, and, especially, a low signal-to-noise ratio. RESULTS: Inspired by the recently introduced neural representations, we propose an adaptive learning-based representation of the density field of the captured sample. This representation consists of an octree structure, where each node represents a 3D density grid optimized from the captured projections during the training process. This optimization is performed using a loss that combines a differentiable image formation model with different regularization terms: total variation, boundary consistency, and a cross-nodes non-local constraint. The final reconstruction is obtained by interpolating the learned density grid at the desired voxel positions. The evaluation of our approach using captured data of viruses and cells shows that our proposed representation is well adapted to handle missing wedges, and improves the signal-to-noise ratio of the reconstructed tomogram. The reconstruction quality is highly improved in comparison to the state-of-the-art methods, while using the lowest computing time footprint. AVAILABILITY AND IMPLEMENTATION: The code is available on Github at https://github.com/yuanhaowang1213/adaptivediffgrid_ex. |
format | Online Article Text |
id | pubmed-10560095 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-105600952023-10-08 Adaptive differentiable grids for cryo-electron tomography reconstruction and denoising Wang, Yuanhao Idoughi, Ramzi Rückert, Darius Li, Rui Heidrich, Wolfgang Bioinform Adv Original Article MOTIVATION: Tilt-series cryo-electron tomography is a powerful tool widely used in structural biology to study 3D structures of micro-organisms, macromolecular complexes, etc. Still, the reconstruction process remains an arduous task due to several challenges: The missing-wedge acquisition, sample misalignment and motion, the need to process large data, and, especially, a low signal-to-noise ratio. RESULTS: Inspired by the recently introduced neural representations, we propose an adaptive learning-based representation of the density field of the captured sample. This representation consists of an octree structure, where each node represents a 3D density grid optimized from the captured projections during the training process. This optimization is performed using a loss that combines a differentiable image formation model with different regularization terms: total variation, boundary consistency, and a cross-nodes non-local constraint. The final reconstruction is obtained by interpolating the learned density grid at the desired voxel positions. The evaluation of our approach using captured data of viruses and cells shows that our proposed representation is well adapted to handle missing wedges, and improves the signal-to-noise ratio of the reconstructed tomogram. The reconstruction quality is highly improved in comparison to the state-of-the-art methods, while using the lowest computing time footprint. AVAILABILITY AND IMPLEMENTATION: The code is available on Github at https://github.com/yuanhaowang1213/adaptivediffgrid_ex. Oxford University Press 2023-09-22 /pmc/articles/PMC10560095/ /pubmed/37810456 http://dx.doi.org/10.1093/bioadv/vbad131 Text en © The Author(s) 2023. Published by Oxford University Press. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Original Article Wang, Yuanhao Idoughi, Ramzi Rückert, Darius Li, Rui Heidrich, Wolfgang Adaptive differentiable grids for cryo-electron tomography reconstruction and denoising |
title | Adaptive differentiable grids for cryo-electron tomography reconstruction and denoising |
title_full | Adaptive differentiable grids for cryo-electron tomography reconstruction and denoising |
title_fullStr | Adaptive differentiable grids for cryo-electron tomography reconstruction and denoising |
title_full_unstemmed | Adaptive differentiable grids for cryo-electron tomography reconstruction and denoising |
title_short | Adaptive differentiable grids for cryo-electron tomography reconstruction and denoising |
title_sort | adaptive differentiable grids for cryo-electron tomography reconstruction and denoising |
topic | Original Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10560095/ https://www.ncbi.nlm.nih.gov/pubmed/37810456 http://dx.doi.org/10.1093/bioadv/vbad131 |
work_keys_str_mv | AT wangyuanhao adaptivedifferentiablegridsforcryoelectrontomographyreconstructionanddenoising AT idoughiramzi adaptivedifferentiablegridsforcryoelectrontomographyreconstructionanddenoising AT ruckertdarius adaptivedifferentiablegridsforcryoelectrontomographyreconstructionanddenoising AT lirui adaptivedifferentiablegridsforcryoelectrontomographyreconstructionanddenoising AT heidrichwolfgang adaptivedifferentiablegridsforcryoelectrontomographyreconstructionanddenoising |