InstaMap:用于冷电磁密度图的即时NGP
Geoffrey Woollard1, Wenda Zhou2, Erik H Thiede1
1Center for Computational Biology, Flatiron Institute, New York, NY 10010, USA.
Acta crystallographica. Section D, Structural biology
|March 26, 2025
概括
灵感来自神经辐射场 (NeRFs) 的新方法InstaMap从冷电子显微镜 (cryo-EM) 数据中更快,更高分辨率地重建3D结构. 这种方法直接在实体空间中处理数据,克服了以前的里埃空间方法的局限性.
科学领域:
- 结构生物学是结构生物学.
- 计算机成像成像技术
- 生物物理学的生物物理.
背景情况:
- 计算机视觉技术,如神经辐射场 (NeRFs),擅长从有限的视图中进行3D重建.
- 神经隐性表示已经应用于冷电子显微镜 (cryo-EM) 进行结构异质性,但通常在里埃空间.
- 与真实空间方法相比,冷EM中的福里埃空间方法在掩盖,物理约束和分辨率评估方面存在挑战.
研究的目的:
- 从计算机视觉中适应先进的神经隐性技术,用于冷电子显微镜 (cryo-EM) 密度图重建.
- 为冷EM数据开发一个实时空间表示,克服现有的里埃空间方法的局限性.
- 引入一个新的框架,InstaMap,用于高效和高分辨率的冷EM重建.
主要方法:
- 使用多分辨率哈希编码框架 (即时-NGP) 直接在真实空间中表示冷-EM密度体积.
- 将InstaMap框架应用于合成和真实冷EM数据集,以进行均的重建.
- 开发了噪声过拟合的策略,实施了掩盖,并扩展了使用曲空间处理分子形状异质性的方法.
主要成果:
- 与其他五种真实空间方法相比,InstaMap在更短的培训时间内实现了更高分辨率的重建,使用合成和真实数据.
- 证明了有效的噪音过度调节和高效的培训,突出了InstaMap的轻量级和快速性质.
- 成功实施了用户定义的掩盖,并扩展了模型构造异质性的方法.
结论:
- 通过利用真实空间神经隐性表示,InstaMap在冷-EM密度地图重建方面取得了重大进展.
- 该方法提供了更好的分辨率,更快的培训,以及比现有技术更大的灵活性 (掩盖,异质性).
- InstaMap代表了计算机视觉创新对结构生物学应用的有希望的适应.
相关概念视频
03:12Freezing Point Depression and Boiling Point Elevation
Boiling Point Elevation
The boiling point of a liquid is the temperature at which its vapor pressure is equal to ambient atmospheric pressure. Since the vapor pressure of a solution is lowered due to the presence of nonvolatile solutes, it stands to reason that the solution’s boiling point will subsequently be increased. Vapor pressure increases with temperature, and so a solution will require a higher temperature than will pure solvent to achieve any given vapor pressure, including one...
The boiling point of a liquid is the temperature at which its vapor pressure is equal to ambient atmospheric pressure. Since the vapor pressure of a solution is lowered due to the presence of nonvolatile solutes, it stands to reason that the solution’s boiling point will subsequently be increased. Vapor pressure increases with temperature, and so a solution will require a higher temperature than will pure solvent to achieve any given vapor pressure, including one...
01:19Magnetic Field Lines
The representation of magnetic fields by magnetic field lines is very useful in visualizing the strength and direction of the magnetic field. Each of the magnetic field lines forms a closed loop. The field lines emerge from the north pole (N), loop around to the south pole (S), and continue through the bar magnet back to the north pole.
Magnetic field lines follow several hard-and-fast rules:
Magnetic field lines follow several hard-and-fast rules:
01:28Magnetostatic Boundary Conditions
An electric field suffers a discontinuity at a surface charge. Similarly, a magnetic field is discontinuous at a surface current. The perpendicular component of a magnetic field is continuous across the interface of two magnetic mediums. In contrast, its parallel component, perpendicular to the current, is discontinuous by the amount equal to the product of the vacuum permeability and the surface current. Like the scalar potential in electrostatics, the vector potential is also continuous...
01:15Insensitive Nuclei Enhanced by Polarization Transfer (INEPT)
Insensitive Nuclei Enhanced by Polarization Transfer (INEPT) is an advanced Nuclear Magnetic Resonance (NMR) technique specifically designed to detect and enhance the signals of low-abundance nuclei, such as carbon-13 and nitrogen-15, in small molecules. The fundamental principle behind INEPT is the transfer of polarization from a more abundant and highly polarizable nucleus, typically hydrogen-1, to the low-abundance nucleus of interest. This process effectively boosts the NMR signal of the...
01:27Energy Line and Hydraulic Gradient Line
Based on Bernoulli's equation, the energy line (EL) and hydraulic grade line (HGL) provide graphical representations of energy distribution in a fluid flow system. For steady, incompressible, inviscid flows, Bernoulli's equation is expressed as:
01:27Gradient Fields
A gradient field is a vector field derived from a scalar field. A scalar field assigns a single numerical value to every point in space, such as temperature, pressure, or electric potential. The gradient field describes how that value changes from point to point. It gives both the direction of the fastest increase and the rate of change in that direction.For a scalar field f(x, y), the gradient is written as\begin{equation*}\nabla f=\left\langle \jfrac{\partial f}{\partial x},\jfrac{\partial...