Developing random forest based QSAR models for predicting the mixture toxicity of TiO2 based nano-mixtures to Daphnia magna

Abstract

During emission, TiO₂ nanoparticles (NPs) might meet various chemicals, including metal ions and organic compounds in aquatic environments (e.g., surface water, sediments). At environmentally safe concentrations, combinations of both TiO₂ NPs and those chemicals might cause cocktail effects (i.e., mixture toxicity) to aquatic organisms. Previous models such as concentration addition and independent action require dose-response curves of single components in the mixtures to predict the mixture toxicity. Structure-activity relationship (QSAR) models might predict the toxicity of nano-mixtures without dose-response curves of single components in the mixtures. However, current quantitative structure-activity relationship (QSAR) models are mainly focused on predicting cytotoxicity (i.e., cell viability) of heterogeneous metallic TiO₂ nanoparticles (NPs) or mixtures of TiO₂ NPs and four metal ions (Cu²⁺, Cd²⁺, Ni^2+, and Zn²⁺). To minimize the experimental cost of nano-mixture risk assessment, in this study, we developed novel nano-mixture QSAR models to predict i) EC₅₀ of 76 nano-mixtures containing TiO₂ NPs and one of eight inorganic/organic compounds (i.e., AgNO₃, Cd(NO₃)₂, Cu(NO₃)₂, CuSO₄, Na₂HAsO₄, NaAsO₂, Benzylparaben and Benzophenone-3), to Daphnia magna(D. magna), and ii) immobilization of D. magna exposed to one of 98 mixtures containing TiO₂ NPs and one of eleven inorganic/organic compounds (i.e., AgNO₃, Cd(NO₃)₂, Cu(NO₃)₂, CuSO₄, Na₂HAsO₄, NaAsO₂, Benzylparaben Benzophenone-3, Pirimicarb, Pentabromodiphenyl Ether and Triton X-100). The nano-mixture QSAR models were developed with mixture descriptors (D_mix) combing quantum descriptors of mixture components (e.g., TiO₂ NPs and its partners) by using different machine learning techniques (i.e., random forest, neural network, support vector machine, and multiple linear regression). Nano-mixture QSAR models built with the random forest algorithm and proposed mixture descriptors exhibited good performance for predicting logEC₅₀ (Adj.R²_test = 0.955 ± 0.003, RMSE_test = 0.016 ± 0.002, and MAE_test = 0.008 ± 0.001) and immobilization (Adj.R²_test = 0.888 ± 0.011, RMSE_test = 11.327 ± 0.730, and MAE_test = 5.933 ± 0.442). The models developed in this study were implemented in a user-friendly application for assessing the aquatic toxicity of TiO₂ based nano-mixtures.

Keywords: Daphnia magna; Machine learning; QSAR; TiO(2) nano-mixture; Toxicity.