相关实验视频

Updated: Jul 2, 2025

Optimizing Sample Preparation for Cryogenic Electron Microscopy

Optimizing Sample Preparation for Cryogenic Electron Microscopy

Published on: April 11, 2025

化变压器:一种用于从化-电磁显微镜中采集蛋白质颗粒的变压器模型

Ashwin Dhakal^1,2, Rajan Gyawali^1,2, Liguo Wang³

¹Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211, United States.

Bioinformatics (Oxford, England)

|February 26, 2024

概括

CryoTransformer精确地从冷电子显微镜 (cryo-EM) 图像中挑选蛋白质颗粒,改进了3D结构重建. 这种人工智能工具可以自动选择粒子,克服当前方法的局限性,以便更好地进行冷EM数据分析.

科学领域:

结构生物学结构生物学
生物物理学的生物物理.
计算生物学计算生物学

背景情况:

低温电子显微镜 (cryo-EM) 对于确定大型蛋白质复杂结构至关重要.
在冷EM中手动采集颗粒是劳动密集型和耗时的.
目前用于粒子挑选的AI方法缺乏精度和回忆力,影响结构质量.

研究的目的:

开发一个自动化和准确的粒子采集方法,用于冷EM.
为了提高从冷EM数据重建的蛋白质结构的质量.

主要方法:

开发了CryoTransformer,这是一个利用变压器,残余网络和图像处理的AI模型.
在CryoPPP数据集上训练并验证了CryoTransformer,这是最大的标记cryo-EM粒子数据集.

主要成果:

与最先进的机器学习方法相比,CryoTransformer表现出卓越的性能.
实现了更高分辨率的3D密度图,并改善了粒子采集中的F1分数.
成功解决了基于人工智能的现有粒子采集技术的局限性.

结论:

化转换器显著提高了化EM中蛋白质颗粒采集的准确性和效率.
该方法促进了冷EM数据处理的自动化.
CryoTransformer是公开的,促进了结构生物学领域的进一步研究和应用.

更多相关视频

Expression and Purification of the Human Lipid-sensitive Cation Channel TRPC3 for Structural Determination by Single-particle Cryo-electron Microscopy

Expression and Purification of the Human Lipid-sensitive Cation Channel TRPC3 for Structural Determination by Single-particle Cryo-electron Microscopy

Published on: January 7, 2019

Miniaturized Sample Preparation for Transmission Electron Microscopy

Miniaturized Sample Preparation for Transmission Electron Microscopy

Published on: July 27, 2018

相关概念视频

Cryo-electron Microscopy

Cryo-electron Microscopy

Conventional electron microscopy (EM) involves dehydration, fixation, and staining of biological samples, which distorts the native state of biological molecules and results in several artifacts. Also, the high-energy electron beam damages the sample and makes it difficult to obtain high-resolution images. These issues can be addressed using cryo-EM, which uses frozen samples and gentler electron beams. The technique was developed by Jacques Dubochet, Joachim Frank, and Richard Henderson, for...