Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Predicting Molecular Geometry02:27

Predicting Molecular Geometry

44.6K
VSEPR Theory for Determination of Electron Pair Geometries
44.6K

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 celecoxib polymorph landscape using AIMNet2 machine learning interatomic potential.

Chemical science·2026
Same author

Advancing Reproducibility and Open Data in Theoretical and Computational Chemistry.

Journal of chemical theory and computation·2026
Same author

Structure Prediction of Organic/Inorganic Interfaces with Genarris.

Journal of chemical theory and computation·2026
Same author

AIQM3: Targeting Coupled-Cluster Accuracy with Semi-Empirical Speed across Seven Main-Group Elements.

Journal of chemical theory and computation·2026
Same author

Open Molecular Crystals 2025 (OMC25) dataset and models.

Scientific data·2026
Same author

Machine learning interatomic potentials at the centennial crossroads of quantum mechanics.

Nature computational science·2025
Same journal

<i>Ordo ab Chao</i>: Crystallographic Disorder as a Window into Ionic Liquid Structure.

Crystal growth & design·2026
Same journal

Correction to "Potential Multiaxial Molecular Ferroelectricity through Chiral Cation Replacement".

Crystal growth & design·2026
Same journal

Compression of Ribavirin to 35 GPa.

Crystal growth & design·2026
Same journal

MOCVD Growth of κ‑Ga<sub>2</sub>O<sub>3</sub> on Al-Rich Al <sub><i>x</i></sub> Ga<sub>1-<i>x</i></sub> N Templates: Phase Diagram and Microstructural Evolution.

Crystal growth & design·2026
Same journal

Microfluidic Laser-Induced Nucleation of Air Microbubbles and Crystals in Urea-Isopropanol Solutions.

Crystal growth & design·2026
Same journal

Crystal Growth, Structures, and Optical Bandgaps of Cuprous Rare-Earth Molybdates.

Crystal growth & design·2026
查看所有相关文章

相关实验视频

Updated: Jan 11, 2026

A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

69.7K

使用AIMNet2神经网络潜力的有效分子晶体结构预测和稳定性评估.

Kamal Singh Nayal1, Dana O'Connor2, Roman Zubatyuk1

  • 1Department of Chemistry, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, Pennsylvania 15213, United States.

Crystal growth & design
|November 10, 2025
PubMed
概括
此摘要是机器生成的。

机器学习的原子间潜力 (MLIP) 通过对分子的训练来加速晶体结构预测. 这种方法在没有昂贵的周期计算的情况下准确地排列了晶体稳定性,并且在各种化学应用中被证明是有效的.

更多相关视频

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins
05:08

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins

Published on: July 8, 2025

918
Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules
10:58

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Published on: July 25, 2013

17.5K

相关实验视频

Last Updated: Jan 11, 2026

A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

69.7K
Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins
05:08

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins

Published on: July 8, 2025

918
Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules
10:58

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Published on: July 25, 2013

17.5K

科学领域:

  • 材料化学 材料化学
  • 计算材料科学科学 计算材料科学
  • 晶体学 晶体学是指结晶学.

背景情况:

  • 准确的晶体结构预测 (CSP) 对于材料发现至关重要,但计算成本昂贵.
  • 传统方法依赖于第一原则计算,对于需要数百万次能源评估的大型系统来说,这些计算变得过度.
  • 剑桥晶体数据中心 (CCDC) 的盲测试强调了需要更高效的CSP方法的需求.

研究的目的:

  • 开发和验证用于晶体结构预测的计算效率高的方法.
  • 为了证明在CSP分子上训练的机器学习原子间潜能 (MLIP) 的有效性.
  • 评估AIMNet2 MLIPs在准确地描述CSP景观和排名晶体稳定性的表现.

主要方法:

  • 培训目标特定的AIMNet2机器学习的原子间潜力 (MLIPs) 在密度函数理论 (DFT) 分子集群 (n-mers) 的计算上.
  • 使用气相分散校正的DFT参考数据来训练MLIP.
  • 应用训练有素的MLIP来评估CSP工作流中的候选晶体结构的相对稳定性.

主要成果:

  • 在n-mer数据上训练的MLIP成功地扩展到晶体环境,准确地描述了CSP景观.
  • 该方法根据相对稳定性对候选晶体结构进行了正确的排名,证明了其有效性.
  • AIMNet2潜力在与制药,光电子和农业化学品相关的各种化学系统中表现强.

结论:

  • 针对特定目标的MLIP可显著加快CSP工作流程.
  • 这种方法有效地捕捉了热力学晶体稳定性的物理,仅使用分子集群数据,避免了昂贵的周期性计算.
  • 在日常的CSP任务中,AIMNet2 MLIP为完全的DFT计算提供了一个有希望和高效的替代方案.