Chemical similarity and machine learning-based approaches for the prediction of aquatic toxicity of binary and multicomponent pharmaceutical and pesticide mixtures against Aliivibrio fischeri.

Different classes of chemicals are present in the environment as mixtures. Among them, pharmaceuticals and pesticides are of major concern due to their improper use and disposal, and subsequent additive and non-additive effects. To assess the environmental risk posed by the mixtures of pharmaceuticals and pesticides, a quantitative structure-activity relationship (QSAR) model has been developed in this study using the pEC 50 values of 198 binary and multi-component mixtures against the marine bacterium Aliivibrio fischeri. The developed partial least squares (PLS) model has been rigorously validated and proved to be a robust and extremely predictive one. To address the chances of overestimation of validation metrics, three cross-validation tests (mixtures out, compounds out, and everything out) have been applied, and the results were satisfactory. The use of simple 2-dimensional descriptors makes the prediction much quick, and also makes the model easily interpretable. A machine learning-based chemical read-across prediction has also been performed to justify the effectiveness of selected structural features in this study. In a nutshell, this study proves QSAR and chemical read-across as effective alternative approaches for the toxicity prediction of pharmaceutical and pesticide mixtures and also approves the use of mixture descriptors for modelling mixtures successfully. [Display omitted] • We apply QSAR and chemical read-across for the toxicity prediction of binary and multi-component mixtures against Aliivibrio fischeri. • We apply mixtures out, compounds out, and everything out cross-validation. • We have used simple 2D structural descriptors for fast prediction, easy interpretability and transferability of the model. • These methods are the easy, fast, cheap, and ethically acceptable alternatives to the mixture's risk assessment. [ABSTRACT FROM AUTHOR]