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

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

Polarity-Driven Selective Adsorption of Quercetin on Kaolinite: An Integrated DFT and Monte Carlo Study.

Materials (Basel, Switzerland)·2026
Same author

A hybrid classical-quantum algorithm to simulate ECD spectra - the case of tryptophan zwitterions in water.

Physical chemistry chemical physics : PCCP·2026
Same author

Isosorbide as a Molecular Glass: New Insights into the Physicochemical Behavior of a Biobased Diol.

Molecules (Basel, Switzerland)·2025
Same author

Molecular Insights into the Protic Organic Ionic Plastic Crystal (POIPC): Effect of Dopants and Vacancies.

ACS omega·2025
Same author

Molecular Insights into the Structure and Dynamics of Protic Organic Ionic Plastic Crystal (OIPC) 1,7-Diazabicyclo[5.4.0]undec-7-ene ([DBUH])-bis(fluorosulfonyl)imide ([FSI]).

The journal of physical chemistry. B·2025
Same author

Coarse-grained simulation of water: A comparative study and overview.

The Journal of chemical physics·2025

相关实验视频

Updated: Jan 13, 2026

In Silico Modeling Method for Computational Aquatic Toxicology of Endocrine Disruptors: A Software-Based Approach Using QSAR Toolbox
05:47

In Silico Modeling Method for Computational Aquatic Toxicology of Endocrine Disruptors: A Software-Based Approach Using QSAR Toolbox

Published on: August 28, 2019

14.6K

监督机器学习和图形神经网络来预测水中溶解有机化合物的碰撞截面值.

Sadollah Ebrahimi1,2, Louis Criqui1, Armand Soldera1,2

  • 1Department of Chemistry, Université de Sherbrooke, Sherbrooke, QC J1K 2R1, Canada.

Journal of the American Society for Mass Spectrometry
|January 8, 2026
PubMed
概括

准确预测碰撞截面 (CCS) 值有助于环境样本中的分子识别. 机器学习和深度学习模型显示出对增强分类和污染物检测的承诺.

更多相关视频

Characterization of Aquatic Biofilms with Flow Cytometry
08:30

Characterization of Aquatic Biofilms with Flow Cytometry

Published on: June 6, 2018

9.6K
Experimental Multiscale Methodology for Predicting Material Fouling Resistance
09:13

Experimental Multiscale Methodology for Predicting Material Fouling Resistance

1.6K

相关实验视频

Last Updated: Jan 13, 2026

In Silico Modeling Method for Computational Aquatic Toxicology of Endocrine Disruptors: A Software-Based Approach Using QSAR Toolbox
05:47

In Silico Modeling Method for Computational Aquatic Toxicology of Endocrine Disruptors: A Software-Based Approach Using QSAR Toolbox

Published on: August 28, 2019

14.6K
Characterization of Aquatic Biofilms with Flow Cytometry
08:30

Characterization of Aquatic Biofilms with Flow Cytometry

Published on: June 6, 2018

9.6K
Experimental Multiscale Methodology for Predicting Material Fouling Resistance
09:13

Experimental Multiscale Methodology for Predicting Material Fouling Resistance

1.6K

科学领域:

  • 环境化学环境化学
  • 计算化学计算化学
  • 分析化学 分析化学

背景情况:

  • 碰撞截面 (CCS) 预测对于识别复杂环境混合物中的分子至关重要.
  • 现有的分子鉴定方法的准确性和范围可能受到限制.

研究的目的:

  • 开发和评估机器学习和深度学习模型,用于预测各种溶解有机分子的CCS值.
  • 提高分子分类和改善环境样本中的污染物检测.

主要方法:

  • 评估了八种监督回归模型 (例如,随机森林,SVR,投票回归器) 和图形神经网络 (GNN).
  • 模型使用分子指纹 (SMILES) 和结构描述符 (m/z,O/C,H/C,AImod,DBE) 进行训练.
  • 使用来自北冰洋的高分辨率质谱 (HRMS) 数据验证模型性能.

主要成果:

  • 模型性能因分子类而异,特定模型在不同类型的化合物中表现出色 (例如,碳水化合物的投票回归器,碳化合物的随机森林).
  • 图形神经网络 (GNN) 在所有分子类中表现出一致的,具有竞争力的准确性.
  • 验证证实了模型对准确分子结构选择的预测能力.

结论:

  • 建立了一个强大的,数据驱动的CCS预测框架,增强分子分类.
  • 开发的模型显著提高了在环境分析中识别分子结构和检测污染物的精度.