Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Exploring the hydrate landscape using data mining on the Cambridge structural database (CSD).

International journal of pharmaceutics·2024

Same author

The structure of magnesium stearate trihydrate determined from a micrometre-sized single crystal using a microfocused synchrotron X-ray beam.

Acta crystallographica Section B, Structural science, crystal engineering and materials·2023

Same author

Corrigendum to "Polysorbate 80 controls Morphology, structure and stability of human insulin Amyloid-Like spherulites" [J. Colloid Interface Sci. 606(Part 2) (2022) 1928-1939].

Journal of colloid and interface science·2023

Same author

Dynamics and disorder: on the stability of pyrazinamide polymorphs.

Acta crystallographica Section B, Structural science, crystal engineering and materials·2022

Same author

Polysorbate 80 controls Morphology, structure and stability of human insulin Amyloid-Like spherulites.

Journal of colloid and interface science·2021

Same author

X-ray diffraction data as a source of the vibrational free-energy contribution in polymorphic systems.

IUCrJ·2019

Search research articles

相关实验视频

Updated: Sep 19, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

阶段播种可以通过深度学习为结构化解决方案提供通道.

Anders Østergaard Madsen¹

¹Department of Pharmacy, University of Copenhagen, Copenhagen, Denmark.

Acta crystallographica. Section A, Foundations and advances

|June 10, 2025

概括

此摘要是机器生成的。

这项研究引入了一种阶段播种方法,将人工智能 (AI) 与ab initio分阶段整合起来. 它通过使用人工智能生成的相种子来增强晶体结构解决方案,简化了复杂的晶体分析.

关键词:

人工智能的人工智能是人工智能.结晶学方法结晶学方法播种阶段播种阶段

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

相关实验视频

Last Updated: Sep 19, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

科学领域:

晶体学晶体学是指结晶学.
科学中的人工智能.
计算化学计算化学

背景情况:

Ab initio相位是X射线晶体学用于确定分子结构的基石.
解决复杂的晶体结构,特别是大型和非中心对称的晶体结构,仍然具有计算挑战性.
将人工智能 (AI) 集成到传统的结晶学工作流中,有可能提高效率.

研究的目的:

提出一种新的阶段播种方法,将人工智能与已建立的初始分期技术相结合.
为了证明人工智能生成的相种子如何增强传统的晶体结构解决方案.
通过将问题转化为分类任务来逐步减少人工智能的计算负担.

主要方法:

拟议的方法使用了一个小部分的近似相位值,称为"相位种子",可能由机器学习模型生成.
阶段值被分离成角形容器,将连续阶段问题转换为分类任务.
这种方法旨在协助,而不是取代传统的初始阶段化方法.

主要成果:

阶段播种方法显著增强了传统的晶体学分相技术.
混合方法对改善结构解决方案,特别是对具有挑战性的晶体样本有希望.
离散化减少了在晶体相位化中对人工智能训练的计算需求.

结论:

阶段播种方法代表了人工智能辅助晶体绘图工作流程的一个有希望的混合策略.
这种方法促进了人工智能与已建立的晶体学工具的整合,以改进结构确定.
未来的研究可以探索人工智能的进一步应用,以推进晶体相位分析.