Development of reliable quantitative structure-toxicity relationship models for toxicity prediction of benzene derivatives using semiempirical descriptors

Abstract

: Health and environmental hazards by benzene and nitrobenzene derivatives has remained topic of interest of researchers. In silico methods for prediction of toxicity of chemicals have proved their worth in accurate forecast of environmental as well as health toxicity and are strongly recommended by regulatory authorities. Two quantitative structure-toxicity relationship models explaining Scenedesmus obliquus toxicity trends among 39 benzene derivatives and Tetrahymena pyriformis toxicity of 103 nitrobenzene and 392 benzene derivatives are developed using semiempirical quantum chemical parameters. The best constructed QSTR models have good fitting ability (R2 =0.8053, 0.7591, 0.8283) and robustness (Q2 LOO =0.7507, 0.7227, 0.8194; Q2 LMO =0.7338, 0.7153, 0.8172). The external predictivity of all the models are quite good (R2 EXT =0.8256, 0.9349, 0.8698). Electronegativity, Cosmo volume, total energy and molecular weight are responsible for increase and decrease of toxicity of benzene derivatives against Scenedesmus obliquus while electronegativity, electrophilicity index, heat of formation, total energy, hydrophobicity and cosmo volume are responsible for modulation of toxicity of nitrobenzene and benzene derivatives towards Tetrahymena pyriformis. These models fulfill the requirements of all the five OECD principles.