Hunan Provincial Key Laboratory of Environmental Catalysis & Waste Regeneration, College of Materials and Chemical Engineering, Hunan Institute of Engineering, Xiangtan, China.
Water Environ Res. 2021 Jun;93(6):934-939. doi: 10.1002/wer.1485. Epub 2020 Dec 18.
The rate constants (k ) of the reactions between organic micropollutants with hydroxyl radical (•OH) in aqueous systems are an important parameter to evaluate the persistence of organic compounds in the environment. In this paper, a support vector machine (SVM) model based on five descriptors was built to predict the reaction rate constants (log K = (log k )/M ). The quantitative structure-activity relationship (QSAR) model of log K was obtained from a training set (600 compounds) and validated with a test set (395 compounds). The coefficients of determination R of the training and test sets are 0.923 and 0.925, respectively. The results suggest that the SVM model developed in this work possesses satisfactory prediction ability. PRACTITIONER POINTS: The rate constants of the reactions of organic micropollutants with •OH in aqueous systems were investigated. SVM model was established for the reaction rate constants (log K = (log k )/M ). Only five molecular descriptors were used to predict 995 log K. A large data set was used for the test set (395 compounds).
在水相体系中，有机微污染物与羟基自由基（•OH）之间的反应速率常数（k）是评估有机化合物在环境中持久性的重要参数。本文基于 5 个描述符建立了一个支持向量机（SVM）模型，用于预测反应速率常数（log K =（log k）/M）。从训练集（600 种化合物）获得了 log K 的定量构效关系（QSAR）模型，并通过测试集（395 种化合物）进行了验证。训练集和测试集的决定系数 R 分别为 0.923 和 0.925。结果表明，本工作中开发的 SVM 模型具有令人满意的预测能力。
研究了有机微污染物与•OH在水相体系中的反应速率常数。建立了 SVM 模型来预测反应速率常数（log K =（log k）/M）。仅使用了 5 个分子描述符来预测 995 个 log K。使用了大量数据集作为测试集（395 种化合物）。
