<br>ChloroDBPFinder：机器学习引导下通过非靶向 LC-HRMS 分析识别氯化消毒副产物,Analytical Chemistry

当前位置： X-MOL 学术 › Anal. Chem. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

ChloroDBPFinder：机器学习引导下通过非靶向 LC-HRMS 分析识别氯化消毒副产物
Analytical Chemistry ( IF 6.7 ) Pub Date : 2024-01-31 , DOI: 10.1021/acs.analchem.3c05124
Tingting Zhao ₁ , Nicholas J P Wawryk ₂ , Shipei Xing ₁ , Brian Low ₁ , Gigi Li ₁ , Huaxu Yu ₁ , Yukai Wang ₁ , Qiming Shen ₂ , Xing-Fang Li ₂ , Tao Huan ₁

Affiliation

高分辨率质谱 (HRMS) 是一种重要的分析工具，能够以公正的方式表征氯化消毒副产物 (Cl-DBP)。由于化学物质的多样性、复杂的背景信号以及 HRMS 固有的分析波动，传统的同位素模式 ( ³⁷ Cl/ ³⁵ Cl)、质量缺陷和直接分子式 (MF) 预测不足以准确识别不同的 Cl -真实环境样品中的 DBP。这项工作提出了一种基于机器学习识别含氯化学品的新策略。我们的分层机器学习框架有两个基于随机森林的模型：第一层是用于识别含 Cl 化学品的二元分类器，第二层是用于注释存在的 Cl 数量的多类分类器。该模型使用来自 PubChem 的约 140 万个独特的 MF 进行训练。通过对来自 NIST20 的 14,000 多个独特 MF 进行评估，该机器学习模型在识别含 Cl MF (Cl-MF) 方面实现了 93.3% 的准确率，在注释 Cl-MF 的 Cl 数量方面实现了 92.9% 的准确率。此外，训练后的模型被集成到 ChloroDBPFinder（一个独立的 R 软件包）中，用于简化 LC-HRMS 数据的处理并注释已知和未知的含氯化合物。我们的 ChloroDBPFinder 对与自来水中阿斯巴甜氯化相关的现有 Cl-DBP 数据集进行了测试，有效提取了 159 个含 Cl-DBP 特征，并通过分子网络初步注释了 10 个 Cl-DBP 的结构。在氯化腐殖质的另一项应用中，ChloroDBPFinder 提取了 79 种高质量的 Cl-DBP，并初步注释了 6 种化合物。总之，我们提出的机器学习策略和开发的 ChloroDBPFinder 提供了一种先进的解决方案，可以在水样的非靶向分析中识别含氯化合物。它可以在 GitHub (https://github.com/HuanLab/ChloroDBPFinder) 上免费获得。

"点击查看英文标题和摘要"

ChloroDBPFinder: Machine Learning-Guided Recognition of Chlorinated Disinfection Byproducts from Nontargeted LC-HRMS Analysis

High-resolution mass spectrometry (HRMS) is a prominent analytical tool that characterizes chlorinated disinfection byproducts (Cl-DBPs) in an unbiased manner. Due to the diversity of chemicals, complex background signals, and the inherent analytical fluctuations of HRMS, conventional isotopic pattern (³⁷Cl/³⁵Cl), mass defect, and direct molecular formula (MF) prediction are insufficient for accurate recognition of the diverse Cl-DBPs in real environmental samples. This work proposes a novel strategy to recognize Cl-containing chemicals based on machine learning. Our hierarchical machine learning framework has two random forest-based models: the first layer is a binary classifier to recognize Cl-containing chemicals, and the second layer is a multiclass classifier to annotate the number of Cl present. This model was trained using ∼1.4 million distinctive MFs from PubChem. Evaluated on over 14,000 unique MFs from NIST20, this machine learning model achieved 93.3% accuracy in recognizing Cl-containing MFs (Cl-MFs) and 92.9% accuracy in annotating the number of Cl for Cl-MFs. Furthermore, the trained model was integrated into ChloroDBPFinder, a standalone R package for the streamlined processing of LC-HRMS data and annotating both known and unknown Cl-containing compounds. Tested on existing Cl-DBP data sets related to aspartame chlorination in tap water, our ChloroDBPFinder efficiently extracted 159 Cl-containing DBP features and tentatively annotated the structures of 10 Cl-DBPs via molecular networking. In another application of a chlorinated humic substance, ChloroDBPFinder extracted 79 high-quality Cl-DBPs and tentatively annotated six compounds. In summary, our proposed machine learning strategy and the developed ChloroDBPFinder provide an advanced solution to identifying Cl-containing compounds in nontargeted analysis of water samples. It is freely available on GitHub (https://github.com/HuanLab/ChloroDBPFinder).

更新日期：2024-01-31

点击分享查看原文

点击收藏

阅读更多本刊新发论文本刊介绍/投稿指南