Using machine learning and quantum chemistry descriptors to predict the toxicity of ionic liquids

被引：89

作者：

Cao, Lingdi ^{[1
]}

Zhu, Peng ^{[2
,3
]}

Zhao, Yongsheng ^{[2
,3
]}

Zhao, Jihong ^{[4
,5
]}

机构：

[1] Forschungszentrum Julich, Helmholtz Inst Erlangen Nurnberg Renewable Energy, Egerlandstr 3, D-91058 Erlangen, Germany

[2] Shanghai Jiao Tong Univ, Dept Micro Nanoelect, Key Lab Thin Film & Microfabricat, Minist Educ, Shanghai 200240, Peoples R China

[3] Univ Calif Santa Barbara, Dept Chem Engn, Santa Barbara, CA 93106 USA

[4] Collaborat Innovat Ctr Environm Pollut Control &, Zhengzhou 450001, Henan, Peoples R China

[5] Xuchang Univ, Xuchang 461001, Henan, Peoples R China

来源：

JOURNAL OF HAZARDOUS MATERIALS | 2018年 / 352卷

基金：

中国博士后科学基金;

关键词：

Toxicity; Ionic liquids; Quantitative structure-activity relationship; Extreme learning machine; Quantum chemistry descriptors; OXYGEN-REDUCTION; IMIDAZOLIUM; CAPTURE; BIODEGRADABILITY; GRAPHENE; SOLVENTS; DATABASE; IMPACTS;

D O I：

10.1016/j.jhazmat.2018.03.025

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

Large-scale application of ionic liquids (ILs) hinges on the advancement of designable and eco-friendly nature. Research of the potential toxicity of ILs towards different organisms and trophic levels is insufficient. Quantitative structure-activity relationships (QSAR) model is applied to evaluate the toxicity of ILs towards the leukemia rat cell line (ICP-81). The structures of 57 cations and 21 anions were optimized by quantum chemistry. The electrostatic potential surface area (S-EP) and charge distribution area (S sigma-profile) descriptors are calculated and used to predict the toxicity of ILs. The performance and predictive aptitude of extreme learning machine (ELM) model are analyzed and compared with those of multiple linear regression (MLR) and support vector machine (SVM) models. The highest R-2 and the lowest AARD% and RMSE of the training set, test set and total set for the ELM are observed, which validates the superior performance of the ELM than that of obtained by the MLR and SVM. The applicability domain of the model is assessed by the Williams plot.

引用

页码：17 / 26

页数：10

共 54 条

[51] Predicting H2S solubility in ionic liquids by the quantitative structure-property relationship method using Sσ-profile molecular descriptors [J].