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

VSEPR Theory for Determination of Electron Pair Geometries
Associative Learning01:27

Associative Learning

Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...

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

Fine-tuning large language models to generate single-atom catalyst synthesis procedures.

Communications chemistry·2026
Same author

From Microcurrents to Macrodynamics: Harnessing Mixed Potentials for Large, Tunable Acceleration of Belousov-Zhabotinsky Oscillations.

Journal of the American Chemical Society·2026
Same author

Strong Dipole-Dipole Interaction Promotes Electrocatalytic Acetylene Semihydrogenation over Symmetric Organo-Electrocatalysts.

Journal of the American Chemical Society·2026
Same author

Ligand-Modulated Release of Copper Active Sites Extends Ethylene Production in CO<sub>2</sub> Electroreduction.

Journal of the American Chemical Society·2026
Same author

TANGO: direct optimization of constrained synthesizability for generative molecular design.

Nature computational science·2026
Same author

Scientific knowledge graph and ontology generation using open large language models.

Digital discovery·2026
Same journal

DeepDOX1: A Dual-Drive Framework Integrating Deep Learning and First-Principles Quantum Chemistry for Drug-Protein Affinity Prediction.

JACS Au·2026
Same journal

Catalyst-Controlled Regiodivergent C-H Olefination of Furanyl Carbamates through a Rational Approach.

JACS Au·2026
Same journal

Charting the Biosynthetic Landscape of Hybrid Polyketide-Nonribosomal Peptide-Specialized Lipids.

JACS Au·2026
Same journal

Valence-State-Dependent Surface Lattice Oxygen in CeO<sub>2</sub>‑Modified VPO Catalysts: Elucidating the Mechanism of <i>n</i>‑Butane Selective Oxidation to Maleic Anhydride.

JACS Au·2026
Same journal

Quantitative Insights into Pressure-Dependent Mass Transport and Reaction Kinetics in Electrochemical CO<sub>2</sub> Reduction.

JACS Au·2026
Same journal

3‑Methylthiopropionic Acid Kills Carbapenem-Resistant <i>Klebsiella pneumoniae</i> by Disrupting Membrane Integrity and Bioenergetics.

JACS Au·2026
查看所有相关文章

相关实验视频

Updated: May 11, 2026

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids
08:21

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

2.6K

增强记忆:采样高效的生成分子设计与强化学习.

Jeff Guo1,2, Philippe Schwaller1,2

  • 1Laboratory of Artificial Chemical Intelligence (LIAC), Institut des Sciences et Ingénierie Chimiques, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne 1015, Switzerland.

JACS Au
|June 28, 2024
PubMed
概括
此摘要是机器生成的。

有效地设计新的分子是很困难的. 这项研究介绍了增强记忆,这是一种新的算法,通过重复使用数据,在分子设计中显著提高样本效率,从而实现最先进的结果.

更多相关视频

Author Spotlight: In Silico Creation and Impact of Carbonylated Amino Acids on Protein Structure and Function
05:57

Author Spotlight: In Silico Creation and Impact of Carbonylated Amino Acids on Protein Structure and Function

Published on: April 26, 2024

359
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

543

相关实验视频

Last Updated: May 11, 2026

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids
08:21

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

2.6K
Author Spotlight: In Silico Creation and Impact of Carbonylated Amino Acids on Protein Structure and Function
05:57

Author Spotlight: In Silico Creation and Impact of Carbonylated Amino Acids on Protein Structure and Function

Published on: April 26, 2024

359
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

543

科学领域:

  • 计算化学是一种计算化学.
  • 人工智能在药物发现中的作用
  • 材料信息学 材料信息学

背景情况:

  • 在*de novo*分子设计中,样本效率是一个关键的挑战,尤其是在使用计算上昂贵的预言时.
  • 现有的分子生成模型,特别是那些使用增强学习的简化分子输入线路输入系统 (SMILES) 的模型,显示出有希望的结果,但可以进一步优化.
  • 高精度预言通常需要大量的计算资源,在可行的预算内限制了实际的分子优化.

研究的目的:

  • 提高分子生成模型的样本效率.
  • 开发一种新的算法,尽量减少对昂贵的计算属性预测器 (预言器) 的调用.
  • 建立一个新的最先进的 *de novo* 分子设计.

主要方法:

  • 实施经验重复,以改进现有算法.
  • 提出了一个新的算法,增强记忆,将数据增强与体验重复结合起来.
  • 在多个模型更新中证明了Oracle分数的可重复使用性.

主要成果:

  • 经验重复显著提高了几个先前算法的性能.
  • 增强型内存在各种任务中显著提高了样本效率.
  • 在样本效率高的*de novo*分子设计中实现了最先进的性能.

结论:

  • 增强记忆在样本效率高的分子设计方面取得了重大进展.
  • 该算法对于利用任务,药物发现和材料设计是有效的.
  • 这种方法可以在实际计算约束下以昂贵的Oracle进行优化.