Screening androgen receptor agonists of fish species using machine learning and molecular model in NORMAN water-relevant list.

Androgen receptor (AR) agonists have strong endocrine disrupting effects in fish. Most studies mainly investigate AR binding capacity using human AR in vitro. However, there is still few methods to rapidly predict AR agonists in aquatic organisms. This study aimed to screen AR agonists of fish species using machine learning and molecular models in water-relevant list from NORMAN, a network of reference laboratories for monitoring contaminants of emerging concern in the environment. In this study, machine learning approaches (e.g., Deep Forest (DF)), Random Forests and artificial neural networks) were applied to predict AR agonists. Zebrafish, fathead minnow, mosquitofish, medaka fish and grass carp are all important aquatic model organisms widely used to evaluate the toxicity of new pollutants, and the molecular models of ARs from these five fish species were constructed to further screen AR agonists using AlphaFold2. The DF method showed the best performances with 0.99 accuracy, 0.97 sensitivity and 1 precision. The Asn705, Gln711, Arg752, and Thr877 residues in human AR and the corresponding sites in ARs from the five fish species were responsible for agonist binding. Overall, 245 substances were predicted as suspect AR agonists in the five fish species, including, certain glucocorticoids, cholesterol metabolites, and cardiovascular drugs in the NORMAN list. Using machine learning and molecular modeling hybrid methods rapidly and accurately screened AR agonists in fish species, and helping evaluate their ecological risk in fish populations.

Norethindrone suppress the germ cell development via androgen receptor resulting in male bias.

Progestins are widely used and detected in surface waters, and can affect gonad development and sexual differentiation in fish. However, the toxicological mechanisms of sexual differentiation induced by progestins are not well understood. Here, we investigated the effects of norethindrone (NET) and androgen receptor (AR) antagonist flutamide (FLU) on gonadal differentiation in zebrafish from 21 dpf (days post-fertilization) to 49 dpf. The results showed that NET caused male bias, while FLU resulted in female bias at 49 dpf. The NET and FLU mixtures significantly decreased the percentage of males compared to the NET single exposure. Molecular docking analysis showed that FLU and NET had similar docking pocket and docking posture with AR resulting in competitively forming the hydrogen bond with Thr334 of AR. These results suggested that binding to AR was the molecular initiating event of sex differentiation induced by NET. Moreover, NET strongly decreased transcription of biomarker genes (dnd1, ddx4, dazl, piwil1 and nanos1) involved in germ cell development, while FLU significantly increased transcription of these target genes. There was an increase in the number of juvenile oocytes, which was consistent with the female bias in the combined groups. The bliss independence model analysis further showed that NET and FLU had antagonistic effect on transcription and histology during gonadal differentiation. Thus, NET suppressed the germ cell development via AR, resulting in male bias. Understanding the molecular initiation of sex differentiation in progestins is essential to provide a comprehensive biological basis for ecological risk assessment.