Random forest algorithm-based accurate prediction of chemical toxicity to Tetrahymena pyriformis

被引：28

作者：

Fang, Zhengjun ^{[1
]}

Yu, Xinliang ^{[1
]}

Zeng, Qun ^{[2
]}

机构：

[1] Hunan Inst Engn, Hunan Prov Key Lab Environm Catalysis & Waste Reg, Coll Mat & Chem Engn, Xiangtan 411104, Hunan, Peoples R China

[2] Xiangtan Cent Hosp, Dept Neurosurg, Xiangtan 411100, Hunan, Peoples R China

来源：

TOXICOLOGY | 2022年 / 480卷

关键词：

Molecular descriptor; QSTR; QSAR; Random forest; Tetrahymena pyriformis; Toxicity; APPLICABILITY DOMAIN; QSAR MODEL; VALIDATION; POLLUTANTS; ERROR; QSTR;

D O I：

10.1016/j.tox.2022.153325

中图分类号：

R9 [药学];

学科分类号：

1007 ;

摘要：

The random forest (RF) algorithm, together with ten Dragon descriptors, was used to develop a quantitative structure-toxicity/activity relationship (QSTR/QSAR) model for a larger data set of 1792 chemical toxicity pIGC(50) towards Tetrahymena pyriformis. The optimal RF (ntree =300 and mtry =3) model yielded root mean square (rms) errors of 0.261 for the training set (1434 chemicals) and 0.348 for the test set (358 chemicals). Compared with other QSTR models reported in the literature, the optimal RF model in this paper is more accurate. The feasibility of applying the RF algorithm to predict chemical toxicity pIGC(50) towards Tetrahymena pyriformis has been verified.

引用

页数：6

共 30 条

[1] Exploring QSTR analysis of the toxicity of phenols and thiophenols using machine learning methods [J].

Asadollahi-Baboli, M. .

ENVIRONMENTAL TOXICOLOGY AND PHARMACOLOGY, 2012, 34 (03) :826-831

[2] Quantitative structure-toxicity relationship (QSTR) studies on the organophosphate insecticides [J].

Can, Alper .

TOXICOLOGY LETTERS, 2014, 230 (03) :434-443

[3] The determination of toxicities of sulphonylurea and phenylurea herbicides with quantitative structure-toxicity relationship (QSTR) studies [J].

Can, Alper ;

Yildiz, Ilkay ;

Guvendik, Gulin .

ENVIRONMENTAL TOXICOLOGY AND PHARMACOLOGY, 2013, 35 (03) :369-379

[4] Prediction of acute toxicity of phenol derivatives using multiple linear regression approach for Tetrahymena pyriformis contaminant identification in a median-size database [J].

Dieguez-Santana, Karel ;

Hai Pham-The ;

Villegas-Aguilar, Pedro J. ;

Huong Le-Thi-Thu ;

Castillo-Garit, Juan A. ;

Casanola-Martin, Gerardo M. .

CHEMOSPHERE, 2016, 165 :434-441

[5] A review of the electrophilic reaction chemistry involved in covalent protein binding relevant to toxicity [J].

Enoch, S. J. ;

Ellison, C. M. ;

Schultz, T. W. ;

Cronin, M. T. D. .

CRITICAL REVIEWS IN TOXICOLOGY, 2011, 41 (09) :783-802

[6] A new semi-automated workflow for chemical data retrieval and quality checking for modeling applications [J].

Gadaleta, Domenico ;

Lombardo, Anna ;

Toma, Cosimo ;

Benfenati, Emilio .

JOURNAL OF CHEMINFORMATICS, 2018, 10

[7] QSAR with quantum topological molecular similarity indices: toxicity of aromatic aldehydes to Tetrahymena pyriformis [J].

Kar, S. ;

Harding, A. P. ;

Roy, K. ;

Popelier, P. L. A. .

SAR AND QSAR IN ENVIRONMENTAL RESEARCH, 2010, 21 (1-2) :149-168

[8] Risk assessment of organic aromatic compounds to Tetrahymena pyriformis in environmental protection by a simple QSAR model [J].

Keshavarz, Mohammad Hossein ;

Shirazi, Zeinab ;

Sheikhabadi, Parvin Kiani .

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION, 2021, 150 :137-147

[9] Consensus QSAR modeling of toxicity of pharmaceuticals to different aquatic organisms: Ranking and prioritization of the DrugBank database compounds [J].

Khan, Kabiruddin ;

Benfenati, Emilio ;

Roy, Kunal .

ECOTOXICOLOGY AND ENVIRONMENTAL SAFETY, 2019, 168 :287-297

[10] Quantitative structure toxicity analysis of ionic liquids toward acetylcholinesterase enzyme using novel QSTR models with index of ideality of correlation and correlation contradiction index [J].

Kumar, Ashwani ;

Kumar, Parvin .

JOURNAL OF MOLECULAR LIQUIDS, 2020, 318

← 1 2 3 →