期刊
IUCRJ
卷 8, 期 -, 页码 60-75出版社
INT UNION CRYSTALLOGRAPHY
DOI: 10.1107/S2052252520014384
关键词
3D reconstruction; image processing; single-particle cryo-EM; imaging; structure determination; cryo-electron microscopy
资金
- Leverhulme Trust
- Engineering and Physical Sciences Research Council (EPSRC) [EP/M00483X/1, EP/S026045/1, EP/N014588/1]
- Alan Turing Institute
- Swedish Foundation for Strategic Research [AM13-0049, ID14-0055]
- UK Medical Research Council [MC_UP_A025_1013]
- Wave 1 of the UK Research and Innovation (UKRI) Strategic Priorities Fund under the EPSRC [EP/T001569/1]
- RISE project CHiPS
- Cantab Capital Institute for the Mathematics of Information
- RISE project NoMADS
- EPSRC [EP/S026045/1, EP/M00483X/1, EP/T001569/1] Funding Source: UKRI
- MRC [MC_UP_A025_1013] Funding Source: UKRI
- Swedish Foundation for Strategic Research (SSF) [ID14-0055] Funding Source: Swedish Foundation for Strategic Research (SSF)
This paper introduces a regularization framework for cryo-EM structure determination that utilizes prior knowledge about biological structures through a convolutional neural network trained on known macromolecular structures. The method yields better reconstructions than current state-of-the-art techniques for simulated data, and possibilities for extending this work to experimental cryo-EM data are discussed.
Three-dimensional reconstruction of the electron-scattering potential of biological macromolecules from electron cryo-microscopy (cryo-EM) projection images is an ill-posed problem. The most popular cryo-EM software solutions to date rely on a regularization approach that is based on the prior assumption that the scattering potential varies smoothly over three-dimensional space. Although this approach has been hugely successful in recent years, the amount of prior knowledge that it exploits compares unfavorably with the knowledge about biological structures that has been accumulated over decades of research in structural biology. Here, a regularization framework for cryo-EM structure determination is presented that exploits prior knowledge about biological structures through a convolutional neural network that is trained on known macromolecular structures. This neural network is inserted into the iterative cryo-EM structure-determination process through an approach that is inspired by regularization by denoising. It is shown that the new regularization approach yields better reconstructions than the current state of the art for simulated data, and options to extend this work for application to experimental cryo-EM data are discussed.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据