文献类型：期刊文献

英文题名：Insights into pesticide toxicity against aquatic organism: QSTR models on Daphnia Magna

作者：He, Lujue[1,2];Xiao, Keya[1];Zhou, Cong[1,2];Li, Guanglong[1];Yang, Hongbin[2];Li, Zhong[1];Cheng, Jiagao[1,2]

机构：[1]East China Univ Sci & Technol, Sch Pharm, Shanghai Key Lab Chem Biol, POB 544,130 Meilong Rd, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Sch Pharm, Shanghai Key Lab New Drug Design, Shanghai 200237, Peoples R China

年份：2019

卷号：173

起止页码：285

外文期刊名：ECOTOXICOLOGY AND ENVIRONMENTAL SAFETY

收录：;WOS:【SCI-EXPANDED(收录号:WOS:000463462800032)】；

基金：We thank for the financial supports from the National Key Research and Development Plan (2017YFD0200300), the National Natural Science Foundation of China (21572059), and Innovation Program of Shanghai Municipal Education Commission (201701070002E00037).

语种：英文

外文关键词：Pesticide; Aquatic toxicity; Daphnia magna; Quantitative structure toxicity relationship (QSTR); Machine learning

摘要：The toxicities of agrochemicals to non-target aquatic organisms are key items in chemical ecological risk assessment. However, it is still an urgent need to develop new tools to assess the agrochemical aquatic toxicity efficiently and accurately. In this work, QSTR studies were performed on a data set containing 639 diverse pesticides with measured EC50 toxicity against Daphnia magna, by using five machine learning methods combined with seven fingerprints and a set of molecular descriptors. The imbalance problem of the data set was successfully solved by clustering analysis. The top-10 QSTR models displayed greater predicative abilities than ECOSAR. The optimal model, Ext-SVM, showed the best performance in 10-fold cross validation (Q(high) = 0.807, Q(moderate) = 0.806, Q(low) = 0.755, Q(total) = 0.794), and also in the test set verification (Q(high) = 0.865, Q(moderate) = 0.783, Q(low) = 0.931, Q(total) = 0.848). The relevance of the key physical-chemical properties with the toxicity was also investigated, in which the MW, a_np, logP(o/w), GCUT_SLOGP_1, chilv and SMR_VSA7 values displayed positive correlation with Daphnia magna toxicity, whereas the logS and a_don showed negative correlation. The robust QSTR models provided efficient tools for assessing agrochemical aquatic toxicity, and the revealed different physical-chemical properties between the high and low toxic compounds might be useful in the discovery and design of low aquatic toxic pesticides.