An QSAR Model for Predicting PBDEs Toxicity Established Based on Ridge Regression

Yu Li; Long Jiang; Xiao Li Li; Jing Ya Wen

doi:10.4028/www.scientific.net/AMR.663.922

Paper Titles

Study on the Adsorption Effect of Active Carbon of Various Compozitions in Polytetrahydrofuran Waste Water
p.894

Ultrasound-Assisted Emulsiﬁcation Microextraction-Solvent Floating Solidification-Pre-Column Derivatization for the Determination of Estrogens in Water Samples
p.899

Construction of Emission Reduction Potential Model on Refinery and Chemical Enterprises
p.905

First Record of the Harmful Raphidophyte Chattonella marina Bloom in Rushan Coast, China in 2008 after the Occurrence of the Green Tide
p.911

An QSAR Model for Predicting PBDEs Toxicity Established Based on Ridge Regression
p.922

Joint Toxicity of Multiple Heavy Metal Compounds to Photobacterium phosphoreum
p.926

Application of Shiono and Knight Method to Compound Open Channel Flow with One-Line Emergent Vegetation
p.930

An IFP Model for Carbon Footprint in Low-Carbon Urban Agglomeration under Uncertainty
p.936

Allocation Model of Total Energy Consumption and Pollutant Emission Control Based on Low-Carbon Economy and its Significance
p.941

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 663An QSAR Model for Predicting PBDEs Toxicity...

An QSAR Model for Predicting PBDEs Toxicity Established Based on Ridge Regression

Abstract:

In this paper, the ridge regression (RR) method was employed to establish the quantitative structure-activity relationships (QSAR) model for predicting toxicity with 15 polybrominated biphenyl ethers (PBDEs) and their 27 kinds of quantum descriptors. Quantum descriptors used to establish the QSAR model were filtrated out based on correlation analysis and variables importance of project (VIP) supported by partial least squares (PLS). The multicollinearity among the descriptors was removed during the calculation of RR method in order to ensure the validation of the final regression equation. The research showed that descriptors of Δα, αxx, αxy, αxz, αyz, βxxy and βyyy had significant effect on toxicity. The model with the simulation efficiency coefficient of 0.916 could be used to predict the toxicity of the unchecked PBDEs and as a preliminary analysis for environmental risk of organic compounds.