A computational approach to evaluate the androgenic affinity of iprodione, procymidone, vinclozolin and their metabolites

Abstract

Our research is aimed at devising and assessing a computational approach to evaluate the affinity of endocrine active substances (EASs) and their metabolites towards the ligand binding domain (LBD) of the androgen receptor (AR) in three distantly related species: human, rat, and zebrafish. We computed the affinity for all the selected molecules following a computational approach based on molecular modelling and docking. Three different classes of molecules with well-known endocrine activity (iprodione, procymidone, vinclozolin, and a selection of their metabolites) were evaluated. Our approach was demonstrated useful as the first step of chemical safety evaluation since ligand-target interaction is a necessary condition for exerting any biological effect. Moreover, a different sensitivity concerning AR LBD was computed for the tested species (rat being the least sensitive of the three). This evidence suggests that, in order not to over-/under-estimate the risks connected with the use of a chemical entity, further in vitro and/or in vivo tests should be carried out only after an accurate evaluation of the most suitable cellular system or animal species. The introduction of in silico approaches to evaluate hazard can accelerate discovery and innovation with a lower economic effort than with a fully wet strategy.

Figure 1. 2D structures of the molecules used to build the test database.

The stereogenic centres are marked with an asterisk (*). Each molecule is marked by a letter: A = testosterone, B = dihydrotestosterone (DHT), C = 11-ketotestosterone, D = vinclozolin, E = vinclozolin_1, E = vinclozolin_2, F = vinclozolin_5, H = iprodione, I = iprodione_8, J = iprodione_13, K = iprodione_14, L = procymidone, M = procymidone_1, N = procymidone_2, O = procymidone_3, P = procymidone_4, Q = procymidone_5, R = procymidone_6, S = cyproterone acetate, T = flutamide, U = procymidone-NH-COOH, V = procymidone-3-Cl, W = cyclopropane-(COOH)₂.

Figure 2. Molecular surface of the binding site and filling dummy atoms in the zebrafish AR LBD model, side (A) and top (B) view.

Figure 3. Global alignment of the selected AR LBD: the residues of the binding sites are highlighted with the following color-code: red for human AR, green for rat AR, and yellow for zebrafish AR.

Figure 4. Box plot for all the calculated binding free energies.

The yellow boxes represent the binding free energies of the vinclozolin and its metabolites for each species. The red boxes represent the binding free energies of iprodione and its metabolites for each species. The blue boxes represent the binding free energies of procymidone and its metabolites for each species. Outliers are marked as circles. Binding free energies of the endogenous hormones are marked with continuous lines.

Figure 5. Best pose of iprodione complexed with the AR LBD in each species.

The ligand molecular surface is also rendered. A) Iprodione complexed with the human AR LBD, B) iprodione complexed with the rat AR LBD, and C) iprodione complexed with zebrafish AR LBD.

Figure 6. Low-mode molecular dynamics simulations.

Superposition of the starting conformation (helix 12) and the most energetically favoured open conformations for the agonist-bound LBD (A), the apo LBD (B), and the antagonist-bound LBD (C).

Figure 7. Hazard evaluation pipeline for putative androgen disruptors.

Step 1: database production; step 2: in silico binding assay; step 3 in vitro binding assay for the selected dataset; step 4: in vitro activity assays only for the high affinity molecules (positive hits); and identification of agonist (α = 1), partial agonist (1<α<0) and antagonist (α = 0) activity.