通过使用图形神经网络的转移学习来预测新出现的污染物的保留时间
Jiewen Deng1, Junbin Chen1, Jingyi Wang1
1Environmental Research Institute/School of Environment, Guangdong Provincial Key Laboratory of Chemical Pollution and Environmental Safety & MOE Key Laboratory of Theoretical Chemistry of Environment, South China Normal University, Guangzhou 510006, China.
Journal of hazardous materials
|February 1, 2026
概括
本研究引入了一个图形神经网络 (GNN) 转移学习方法,用于预测液体染色体质谱法 (LC-MS) 中的环境污染物保留时间. 这种方法提高了准确性和概括性,减少了对污染物查的实验需求.
科学领域:
- 分析化学 分析化学
- 计算化学的计算化学
- 环境科学 环境科学
背景情况:
- 准确的保留时间 (RT) 预测对于使用液态染色体质谱法 (LC-MS) 对环境有机污染物的非向分析至关重要.
- 实验性RT确定是艰苦的,数据稀缺性是一个重大挑战.
- 传统的机器学习方法往往难以概括,需要大量的特定目标数据.
研究的目的:
- 开发和优化图形神经网络 (GNN) 转移学习方法,以准确地预测环境污染物的RT.
- 克服实验RT确定和LC-MS非目标分析数据稀缺性的局限性.
- 与传统方法相比,评估GNN转移学习的性能和可解释性.
主要方法:
- 系统评估了5个GNN模型,3个预培训优化器,3个培训策略和2个转移学习优化器.
- 利用METLIN-SMRT数据集进行预培训,并将转移学习应用于1051种环境污染物的目标数据集.
- 采用基于梯度的归因分析来评估模型可解释性和可应用性领域的可靠性.
主要成果:
- 最优的GNN模型 (GIN3与微调策略和L-BFGS优化器) 实现了0.894的R2,超过了传统的机器学习 (R2=0.816).
- 转移学习表现出优异的概括性 (8%的训练测试下降,而传统方法的下降率为11-19%),表示自主性和统计学稳定性.
- 基于梯度的分析提供了关于转移学习如何专注于RT预测的关键结构动机的见解.
结论:
- 基于图形的转移学习为环境污染物的RT预测提供了高效和准确的解决方案,克服了数据集大小的限制.
- 开发的模型可以快速选污染物,特别是对于未知的污染物或在具有有限标准的紧急情况下.
- 这种方法减少了对实验的依赖,并通过利用跨领域的染色学知识来推进智能染色学分析.
相关概念视频
00:54Time-Series Graph
5.2K
A time-series graph is a line graph with repeated measurements taken at successive intervals of time. It is also called a time series chart. To construct a time-series graph, one must look at both pieces of a paired data set. The horizontal axis is used to plot the time increments, and the vertical axis is used to plot the values of the variable that one is measuring. By using the axes in this way, each point on the graph will correspond to time and a measured quantity. The points on the graph...
5.2K
02:26Protein Networks
4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
01:27Emerging Adulthood
688
Jeffrey Arnett's concept of emerging adulthood offers a framework to understand the unique developmental stage between adolescence and full-fledged adulthood, generally from ages 18 to 25. This period is marked by extensive exploration and shifts in identity, relationships, and career choices, a process known in psychology as role experimentation. Emerging adulthood reflects the evolving cultural expectations surrounding adulthood and the dynamic process of personal transformation during...
688
01:16Contaminants and Errors
373
Effective sample preparation is crucial for accurate and reliable laboratory analysis. During this process, two significant sources of error can arise: concentration bias from improper sample splitting and contamination caused by methods used to reduce particle size, such as grinding or homogenization. Identifying and minimizing these potential errors is crucial to ensuring the validity of the analysis.
Another key consideration is determining the appropriate number of samples required to...
Another key consideration is determining the appropriate number of samples required to...
373
01:07Ogive Graph
6.8K
An ogive graph is sometimes called a cumulative frequency polygon. It is one type of frequency polygon that shows cumulative frequency. In other words, the cumulative percentages are added to the graph from left to right. An ogive graph plots cumulative frequency on the vertical y-axis and class boundaries along the horizontal x-axis. It’s very similar to a histogram; only instead of rectangles, an ogive displays a single point where the top right of the rectangle would be. Creating this...
6.8K
01:30Graphing Antiderivatives
70
The concept of an antiderivative is fundamental in calculus, describing how a function's values accumulate over time. This process is closely related to physical motion, such as the movement of a rolling ball. As the ball progresses, its position changes in response to variations in velocity, just as an antiderivative graph reflects the cumulative effect of the original function's values.Graphing an antiderivative requires interpreting how a function's values influence the shape of its...
70