Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

High-Resolution Mass Spectrometry (HRMS)

High-Resolution Mass Spectrometry (HRMS)

The resolution of a mass spectrometer depends on the efficiency of separating ions with different ion masses. The mass of an atom is approximated to the sum of the masses of protons and neutrons inside, considering the masses of protons and neutrons as equal. However, the masses of the proton (1.6726 × 10−24 g) and neutron (1.6749 × 10−24 g) are not truly equal. There is a minor error in the expression of atomic masses relative to the simplest atom of hydrogen. For...

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

Molecular-level traits of root exudates in tropical forest trees reflect nitrogen-fixation strategy and phenological shifts.

The New phytologist·2026

Same author

Chemical space blind spots: how chromatographic selectivity dictates chemical measurability and coverage of LC-HRMS comprehensive analysis.

Chemical communications (Cambridge, England)·2026

Same author

From Spectra to Local Networks: Evaluating MS<sup>2</sup> Similarity Metrics.

Analytical chemistry·2026

Same author

Advancing the Discovery of Emerging Contaminants: A Leap in Technology and Data.

Environmental science & technology·2026

Same author

Communicating Confidence in the Reliability of Micro- and Nanoplastic Identification in Human Health Studies.

Environment & health (Washington, D.C.)·2026

Same author

Electronics-free soft robotic minitablet for on-demand gastric molecular sensing and diagnostics in vivo.

Science advances·2026

Search research articles

相关实验视频

Updated: Sep 11, 2025

An Integrated Workflow of Identification and Quantification on FDR Control-Based Untargeted Metabolome

An Integrated Workflow of Identification and Quantification on FDR Control-Based Untargeted Metabolome

Published on: September 20, 2022

机器学习用于RPLC/HRMS非目标化工作流中的增强识别概率.

Hiu-Lok Ngan¹, Viktoriia Turkina², Denice van Herwerden²

¹State Key Laboratory of Environmental and Biological Analysis, Department of Chemistry, Hong Kong Baptist University, Kowloon, Hong Kong 999077 P. R. China.

Analytical chemistry

|August 12, 2025

概括

本研究引入了一种机器学习方法,使用预测的保留时间指数来改善基于HRMS的非目标分析中的化学物质识别. 该方法显著提高了复杂样本中农药的识别概率.

更多相关视频

Large Scale Non-targeted Metabolomic Profiling of Serum by Ultra Performance Liquid Chromatography-Mass Spectrometry UPLC-MS

Large Scale Non-targeted Metabolomic Profiling of Serum by Ultra Performance Liquid Chromatography-Mass Spectrometry UPLC-MS

Published on: March 14, 2013

Identifying Per- and Polyfluorinated Chemical Species with a Combined Targeted and Non-Targeted-Screening High-Resolution Mass Spectrometry Workflow

Identifying Per- and Polyfluorinated Chemical Species with a Combined Targeted and Non-Targeted-Screening High-Resolution Mass Spectrometry Workflow

Published on: April 18, 2019

相关实验视频

Last Updated: Sep 11, 2025

An Integrated Workflow of Identification and Quantification on FDR Control-Based Untargeted Metabolome

An Integrated Workflow of Identification and Quantification on FDR Control-Based Untargeted Metabolome

Published on: September 20, 2022

Large Scale Non-targeted Metabolomic Profiling of Serum by Ultra Performance Liquid Chromatography-Mass Spectrometry UPLC-MS

Large Scale Non-targeted Metabolomic Profiling of Serum by Ultra Performance Liquid Chromatography-Mass Spectrometry UPLC-MS

Published on: March 14, 2013

Identifying Per- and Polyfluorinated Chemical Species with a Combined Targeted and Non-Targeted-Screening High-Resolution Mass Spectrometry Workflow

Identifying Per- and Polyfluorinated Chemical Species with a Combined Targeted and Non-Targeted-Screening High-Resolution Mass Spectrometry Workflow

Published on: April 18, 2019

科学领域:

分析化学分析化学
质谱测量质量谱测量
机器学习机器学习

背景情况:

基于高分辨率质谱 (HRMS) 的非目标分析 (NTA) 在很大程度上依赖于光谱匹配来进行化学识别,特别是在没有保留数据的情况下.
准确的化学识别对于解释各种科学领域的复杂样品成分至关重要.

研究的目的:

开发和验证一种基于机器学习 (ML) 的新型方法,以提高基于HRMS的NTA中的化学识别概率 (IP).
利用从分子指纹和累积中性损失中获得的预测保留时间指数 (RTIs) 来提高光谱匹配精度.

主要方法:

开发了三个ML模型:分子指纹 (MF) 到RTI,累积中性损失 (CNL) 到RTI,以及真正/负光谱匹配的二元分类模型.
在广泛的数据集上训练模型,包括校准和实验光谱,并使用独立的测试集进行验证.
整合预测的RTIs与光谱库搜索,并使用F1得分和马修斯相关系数等指标评估性能,以识别农药.

主要成果:

在MF和CNL衍生的RTI值之间的高相关性 (R2=0.96训练,0.88测试) 表明真正光谱匹配的误差减少.
在空白样本中,k-最近邻近算法获得了0.65的加权F1得分和0.30的MCC,用于在空白样本中识别农药 (1-1000ppb).
与图书馆单独匹配不同样本稀释量相比,平均农药IP增加了46.7-54.5%.

结论:

机器学习模型有效地预测RTIs,减少HRMS-NTA中的识别不确定性.
拟议的ML方法显著提高了化学识别的可靠性,特别是复杂矩阵中的农药.
这种方法为推进化学发现和分析科学中表征提供了强大的工具.