Support vector machine-based model for toxicity of organic compounds against fish.
作者： Xinliang Yu
DOI: 10.1016/J.YRTPH.2021.104942
关键词: Mathematics 、 Test set 、 Support vector machine 、 Fish <Actinopterygii> 、 Biological system 、 Toxicity 、 Molecular descriptor 、 Training set 、 Quantitative structure–activity relationship 、 Organic chemicals
摘要: Abstract Predicting the toxicity of chemicals to various fish species through chemometric approach is crucial for ecotoxicological assessment existing as well not yet synthesized chemicals. This paper reports a quantitative structure–activity/toxicity relationship (QSAR/QSTR) model pLC50 organic against species. Only six descriptors were used develop QSTR model, by applying support vector machine (SVM) together with genetic algorithm. The was trained and established on sufficiently large data set 840 compounds evaluated test (281 compounds). Compared other QSTRs reported in literature, optimal SVM produces better statistical results determination coefficients R2 above 0.70 both training set, although this work possesses fewer molecular descriptors. Applying algorithm successful.
sci-hub.st 参考文章(31)
Khadidja Bellifa, Sidi Mohamed Mekelleche, QSAR study of the toxicity of nitrobenzenes to Tetrahymena pyriformis using quantum chemical descriptors Arabian Journal of Chemistry. ,vol. 9, ,(2016) , 10.1016/J.ARABJC.2012.04.031
Sylvain Lozano, Elodie Lescot, Marie-Pierre Halm, Alban Lepailleur, Ronan Bureau, Sylvain Rault, Prediction of acute toxicity in fish by using QSAR methods and chemical modes of action Journal of Enzyme Inhibition and Medicinal Chemistry. ,vol. 25, pp. 195- 203 ,(2010) , 10.3109/14756360903169857
Villem Aruoja, Maikki Moosus, Anne Kahru, Mariliis Sihtmäe, Uko Maran, Measurement of baseline toxicity and QSAR analysis of 50 non-polar and 58 polar narcotic chemicals for the alga Pseudokirchneriella subcapitata Chemosphere. ,vol. 96, pp. 23- 32 ,(2014) , 10.1016/J.CHEMOSPHERE.2013.06.088
Christophe Leys, Christophe Ley, Olivier Klein, Philippe Bernard, Laurent Licata, Detecting outliers: Do not use standard deviation around the mean, use absolute deviation around the median Journal of Experimental Social Psychology. ,vol. 49, pp. 764- 766 ,(2013) , 10.1016/J.JESP.2013.03.013
Stefano Cassani, Simona Kovarich, Ester Papa, Partha Pratim Roy, Leon van der Wal, Paola Gramatica, Daphnia and fish toxicity of (benzo)triazoles: validated QSAR models, and interspecies quantitative activity-activity modelling. Journal of Hazardous Materials. ,vol. 258, pp. 50- 60 ,(2013) , 10.1016/J.JHAZMAT.2013.04.025
Chih-Chung Chang, Chih-Jen Lin, LIBSVM ACM Transactions on Intelligent Systems and Technology. ,vol. 2, pp. 1- 27 ,(2011) , 10.1145/1961189.1961199
Chun Wei Yap, PaDEL-descriptor: An open source software to calculate molecular descriptors and fingerprints Journal of Computational Chemistry. ,vol. 32, pp. 1466- 1474 ,(2011) , 10.1002/JCC.21707
Kunal Roy, Rudra Narayan Das, Pravin Ambure, Rahul B. Aher, Be aware of error measures. Further studies on validation of predictive QSAR models Chemometrics and Intelligent Laboratory Systems. ,vol. 152, pp. 18- 33 ,(2016) , 10.1016/J.CHEMOLAB.2016.01.008
Paola Gramatica, Stefano Cassani, Alessandro Sangion, Aquatic ecotoxicity of personal care products: QSAR models and ranking for prioritization and safer alternatives’ design Green Chemistry. ,vol. 18, pp. 4393- 4406 ,(2016) , 10.1039/C5GC02818C
Natalie Burden, Samuel K. Maynard, Lennart Weltje, James R. Wheeler, The utility of QSARs in predicting acute fish toxicity of pesticide metabolites: A retrospective validation approach. Regulatory Toxicology and Pharmacology. ,vol. 80, pp. 241- 246 ,(2016) , 10.1016/J.YRTPH.2016.05.032