Classification and regression machine learning models for predicting the combined toxicity and interactions of antibiotics and fungicides mixtures.

Antibiotics and triazole fungicides coexist in varying concentrations in natural aquatic environments, resulting in complex mixtures. These mixtures can potentially affect aquatic ecosystems. Accurately distinguishing synergistic and antagonistic mixtures and predicting mixture toxicity are crucial for effective mixture risk assessment. We tested the toxicities of 75 binary mixtures of antibiotics and fungicides against Auxenochlorella pyrenoidosa. Both regression and classification models for these mixtures were developed using machine learning models: random forest (RF), k-nearest neighbors (KNN), and kernel k-nearest neighbors (KKNN). The KKNN model emerged as the best regression model with high values of determination coefficient (R2 = 0.977), explained variance in prediction leave-one-out (Q2LOO = 0.894), and explained variance in external prediction (Q2F1 = 0.929, Q2F2 = 0.929, and Q2F3 = 0.923). The RF model, the leading classifier, exhibited high accuracy (accuracy = 1 for the training set and 0.905 for the test set) in distinguishing the synergistic and antagonistic mixtures. These results provide crucial value for the risk assessment of mixtures.

Toxic mechanism of three azole fungicides and their mixture to green alga Chlorella pyrenoidosa.

Currently, few studies have investigated the joint toxicity mechanism of azole fungicides at different exposure times and mixed at the relevant environmental concentrations. In this study, three common azole fungicides, namely, myclobutanil (MYC), propiconazole (PRO), and tebuconazole (TCZ), were used in studying the toxic mechanisms of a single substance and its ternary mixture exposed to ambient concentrations of Chlorella pyrenoidosa. Superoxide dismutase (SOD), catalase (CAT), chlorophyll a (Chla), and total protein (TP), were used as physiological indexes. Results showed that three azole fungicides and ternary mixture presented obvious time-dependent toxicities at high concentrations. MYC induced a hormetic effect on algal growth, whereas PRO and TCZ inhibit algal growth in the entire range of the tested concentrations. The toxicities of the three azole fungicides at 7 days followed the order PRO > TCZ > MYC. Three azole fungicides and their ternary mixture induced different levels of SOD and CAT activities in algae at high concentrations. The ternary mixture showed additive effects after 4 and 7 days exposure, but no effect was observed at actual environmental concentrations. The toxic mechanisms may be related to the continuous accumulation of reactive oxygen species, which not only affected protein structures and compositions but also damaged thylakoid membranes, hindered the synthesis of proteins and chlorophyll a, and eventually inhibited algal growth. These findings increase the understanding of the ecotoxicity of azole fungicides and use of azole fungicides in agricultural production.