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

Structure-Activity Relationships and Drug Design01:28

Structure-Activity Relationships and Drug Design

Drug design is a dynamic field that involves discovering and developing new medications based on specific biological targets. This process heavily relies on structure-activity relationships (SAR) and quantitative structure-activity relationships (QSAR) to guide the design and optimization of efficient drugs.
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence its...
Methods of Medium Optimization01:28

Methods of Medium Optimization

Optimizing growth media enhances microbial proliferation and maximizes product yield. Statistical experimental design methodologies provide structured and reproducible approaches, offering progressively higher levels of robustness and efficiency.The One-Factor-at-a-Time (OFAT) MethodThe One-Factor-at-a-Time (OFAT) method involves adjusting a single variable while keeping all others constant. However, it cannot detect interactions between variables, often leading to suboptimal outcomes when...

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

Toward Lab-Ready AI Synthesis Plans with Protection Strategies and Route Scoring.

Journal of chemical information and modeling·2026
Same author

From concept to chemistry: integrating protection group strategy and reaction feasibility into non-natural amino acid synthesis planning.

Chemical science·2025
Same author

Precedent Finder: Locating Pareto-Optimal Reactions.

Journal of chemical information and modeling·2025
Same author

Measuring the efficiency of synthetic routes and transformations using vectors derived from similarity and complexity.

Chemical science·2025
Same author

Introducing the Inaugural Early Career Board for <i>Chemical Research in Toxicology</i>.

Chemical research in toxicology·2025
Same author

Advancing Human and Environmental Safety Science Using <i>In Silico</i> Methods.

Chemical research in toxicology·2025

相关实验视频

Updated: May 10, 2026

High-throughput Synthesis of Carbohydrates and Functionalization of Polyanhydride Nanoparticles
14:37

High-throughput Synthesis of Carbohydrates and Functionalization of Polyanhydride Nanoparticles

Published on: July 6, 2012

11.4K

研究计算机辅助合成规划的效率.

Peter B R Hartog1,2, Annie M Westerlund1, Igor V Tetko2

  • 1Molecular AI, Discovery Sciences, R&D, AstraZeneca, Pepparedsleden 1, 431 83 Mölndal, Sweden.

Journal of chemical information and modeling
|January 31, 2025
PubMed
概括

为化学合成规划优化机器学习模型是关键. 虽然更快的单步预测很重要,但这些预测的多样性和信心更显著地影响了整体的多步搜索效率.

更多相关视频

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: Accelerating Discovery in Microporous Material Chemistry
07:20

Author Spotlight: Accelerating Discovery in Microporous Material Chemistry

Published on: October 6, 2023

3.5K

相关实验视频

Last Updated: May 10, 2026

High-throughput Synthesis of Carbohydrates and Functionalization of Polyanhydride Nanoparticles
14:37

High-throughput Synthesis of Carbohydrates and Functionalization of Polyanhydride Nanoparticles

Published on: July 6, 2012

11.4K
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: Accelerating Discovery in Microporous Material Chemistry
07:20

Author Spotlight: Accelerating Discovery in Microporous Material Chemistry

Published on: October 6, 2023

3.5K

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
  • 机器学习用于合成规划.

背景情况:

  • 机器学习 (ML) 模型对于有效的化学合成路径生成至关重要.
  • 当前的回复合成模型往往太慢,无法在实践中应用.
  • 减少ML模型的推断时间和碳足迹是一个重大挑战.

研究的目的:

  • 为了减少回归合成的Chemformer模型的推断时间.
  • 研究替代变压器架构,知识蒸 (KD) 和超参数优化.
  • 评估这些优化对单步和多步搜索效率的影响.

主要方法:

  • 评估了与知识蒸 (KD) 密切相关的变压器架构.
  • 调查的基于特征和基于响应的KD.
  • 基于推断时间和模型准确性的优化超参数.
  • 评估了单步预测速度和多步搜索效率.

主要成果:

  • 在使用KD时,替代变压器架构的性能不佳.
  • 减少模型尺寸和提高单步速度是重要的,但不够.
  • 多步骤搜索效率更多地受到单步预测的多样性和信心的影响.
  • 仅仅知识蒸并没有显著提高多步效率.

结论:

  • 进一步的研究应该将KD与其他技术相结合,以改善合成规划.
  • 反合成中的多步搜索效率是复杂的,并且受到超出单步模型速度的因素的影响.
  • 在基于蒙特卡洛的回复合成中平衡勘探和开采是至关重要的.