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

45.2K
VSEPR Theory for Determination of Electron Pair Geometries
45.2K
Molecular Models02:00

Molecular Models

43.5K
Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.
43.5K
Predicting Reaction Outcomes02:24

Predicting Reaction Outcomes

10.1K
Kinetics describes the rate and path by which a reaction occurs. In contrast, thermodynamics deals with state functions and describes the properties, behavior, and components of a system. It is not concerned with the path taken by the process and cannot address the rate at which a reaction occurs. Although it does provide information about what can happen during a reaction process, it does not describe the detailed steps of what appears on an atomic or a molecular level. On the other hand,...
10.1K
Ligand Binding and Linkage00:49

Ligand Binding and Linkage

5.5K
Allosteric proteins have more than one ligand binding site; the binding of a ligand to any of these sites influences the binding of ligands to the other sites. When a protein is allosteric, its binding sites are called coupled or linked.  In the case of enzymes, the site that binds to the substrate is known as the active site and the other site is known as the regulatory site. When a ligand binds to the regulatory site, this leads to conformational changes in the protein that can influence...
5.5K
Ligand Binding and Linkage00:49

Ligand Binding and Linkage

4.0K
4.0K
Improving Translational Accuracy02:07

Improving Translational Accuracy

14.1K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
14.1K

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

Local nonequilibrium thermodynamics of polymer collapse dynamics.

The Journal of chemical physics·2025
Same author

Hybrid coarse-grained and all-atom molecular dynamics simulation studies of binary biological lipid membranes containing chlorosulfolipids.

The Journal of chemical physics·2025
Same author

Pressure-Dependent Shape and Edge Configurations of MoS<sub>2</sub> by Kinetic Monte Carlo Simulation.

ACS nano·2024
Same author

Inhibition mechanism of testis-expressed gene 14 (TEX14) in cytokinetic abscission: Well-tempered metadynamics simulation studies.

The Journal of chemical physics·2023
Same author

Structure and stability of polydiacetylene membrane systems: Molecular dynamics simulation studies.

Journal of computational chemistry·2022
Same author

Chlorosulfolipid (Danicalipin A) Membrane Structure: Hybrid Molecular Dynamics Simulation Studies.

The journal of physical chemistry letters·2021

相关实验视频

Updated: Jan 17, 2026

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

1.0K

评估在大型语言模型中的语境学习,用于分子性质回归.

Chan Young Joe1, Kyungwoo Song2,3, Rakwoo Chang1

  • 1Department of Applied Chemistry, University of Seoul, Seoul, Republic of Korea.

Journal of computational chemistry
|January 15, 2026
PubMed
概括

大型语言模型 (LLM) 是有前途的,但在科学回归任务的真实上下文学习方面存在困难. 机器学习模型在分子性质预测方面提供了更大的稳定性,特别是在具有挑战性的条件下.

关键词:
在SMILES的代表处.功能性的分布之外的功能.在语境学习中学习.大型语言模型.分子性质预测分子性质预测快捷方式学习学习结构活动 景观指数

更多相关视频

Pharmacophore Modeling for Targets with Extensive Ligand Libraries: A Case Study on SARS-CoV-2 Mpro
05:50

Pharmacophore Modeling for Targets with Extensive Ligand Libraries: A Case Study on SARS-CoV-2 Mpro

Published on: September 26, 2025

1.4K

相关实验视频

Last Updated: Jan 17, 2026

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

1.0K
Pharmacophore Modeling for Targets with Extensive Ligand Libraries: A Case Study on SARS-CoV-2 Mpro
05:50

Pharmacophore Modeling for Targets with Extensive Ligand Libraries: A Case Study on SARS-CoV-2 Mpro

Published on: September 26, 2025

1.4K

科学领域:

  • 人工智能的人工智能
  • 计算化学计算化学
  • 机器学习 机器学习

背景情况:

  • 大型语言模型 (LLM) 在自然语言任务中表现出色.
  • 它们在科学回归中进行上下文学习 (ICL) 的能力尚不清楚.
  • 评估科学领域的LLM绩效需要专门的评估框架.

研究的目的:

  • 在科学回归任务中,系统地评估七个大型语言模型 (LLM) 的上下文学习能力.
  • 研究LLM在受控条件下对分子性质预测的性能,旨在隔离快捷方式学习并诱导分布外 (OOD) 行为.
  • 将LLM性能与传统机器学习 (ML) 基线进行比较.

主要方法:

  • 一个由56个转换任务组成的受控框架被用来评估7个关于分子性质预测的LLM.
  • 任务的设计是为了隔离快捷方式的学习,并诱导功能性分布外 (OOD) 行为.
  • 通过将LLM结果与机器学习 (ML) 基线进行比较来评估绩效.

主要成果:

  • 在原始分子重量预测上,LLMs实现了近乎完美的性能,这可能是由于快捷线索.
  • 在数据的非线性转换下,LLM的性能显著恶化.
  • 机器学习 (ML) 基线表现出更大的稳定性,导致性能交叉,ML超过了LLMs.
  • 分析确定了分布式描述符和结构活动景观指数 (SALI) 作为任务有利性的预测指标.

结论:

  • 针对科学回归的LLM的上下文学习是有限的,容易受到捷径学习的影响.
  • 机器学习模型为分子性质预测提供了更强大,更可靠的性能,特别是在分布之外的场景中.
  • 分布描述符和SALI可以指导化学应用中选择合适的AI/ML方法.