Chemometric modeling of acute toxicity of diverse aromatic compounds against Rana japonica

Abstract

Chemicals used in our daily life show different toxic effects to the aquatic and terrestrial species and thus hamper the ecological balance. In the present time, amphibians are one of them, which are threatened to be extinct. Quantitative structure-activity relationship (QSAR) is an useful tool for prediction involving less time, money and manpower without requiring any animal experiments to assess the unavailable acute toxicity data for the untested molecules. In this study, we have developed QSAR models for ecotoxicity of some waterborne diverse aromatic compounds on an amphibian species Rana japonica (Japanese brown frog) employing Genetic Algorithm (GA) for variable selection followed by Partial Least Squares (PLS) regression method following recommendations of the Organization for Economic Co-operation and Development (OECD) for QSAR model development. Double cross-validation (DCV) followed by Best Subset Selection (BSS) were employed to select suitable models. The models displayed promising statistical quality in terms of R2 (= 0.837–0.841), Q2LOO (= 0.782–0.787), R2pred or Q2F1 (= 0.802–0.82) and some other internal and external validation metrics for tadpoles of Rana japonica (NTraining = 44, NTest = 14). These models can be applied for data gap filling for a new untested compound falling within the applicability domain (AD) of the models.