Bismuth antimicrobial drugs serve as broad-spectrum metallo-β-lactamase inhibitors

Abstract

Drug-resistant superbugs pose a huge threat to human health. Infections by Enterobacteriaceae producing metallo-β-lactamases (MBLs), e.g., New Delhi metallo-β-lactamase 1 (NDM-1) are very difficult to treat. Development of effective MBL inhibitors to revive the efficacy of existing antibiotics is highly desirable. However, such inhibitors are not clinically available till now. Here we show that an anti-Helicobacter pylori drug, colloidal bismuth subcitrate (CBS), and related Bi(III) compounds irreversibly inhibit different types of MBLs via the mechanism, with one Bi(III) displacing two Zn(II) ions as revealed by X-ray crystallography, leading to the release of Zn(II) cofactors. CBS restores meropenem (MER) efficacy against MBL-positive bacteria in vitro, and in mice infection model, importantly, also slows down the development of higher-level resistance in NDM-1-positive bacteria. This study demonstrates a high potential of Bi(III) compounds as the first broad-spectrum B1 MBL inhibitors to treat MBL-positive bacterial infection in conjunction with existing carbapenems.

Fig. 1

CBS inhibits the in vitro activity of MBLs. a Basic dimeric unit of CBS. b, c Representative heat plots of microdilution checkerboard assay for the combination of MER and CBS against NDM-HK (b) and NDM-HK PCV (c). d Time kill curves for MER and CBS monotherapy and combination therapy against NDM-HK during 24 h incubation. The concentrations of MER and CBS are 24 μg mL^-1 and 64 μg mL^-1, respectively. e Inhibition profiles for MBLs by CBS with IC₅₀ values of 2.81, 3.54, and 0.70 µM for NDM-1, VIM-2, and IMP-4, respectively. Mean value of three replicates are shown and error bars indicate the standard deviation (SD). f Isobolograms of the combination of MER and CBS against different MBL-positive bacterial strains. The gray line indicates ideal isobole, where drugs act additively and independently. Data overlapping with this line indicate additive effects. Data points below this line indicate synergism

Fig. 2

Bi(III) compounds inhibit the activity of MBLs via a unique metal replacement mechanism. a Different UV-vis spectra of apo-NDM-1 upon addition of 0.2–1.5 molar equivalents of Bi(NTA). The inset shows the changes of absorbance at 340 nm. b Normalized residual activity of wild-type (WT) NDM-1 and a variant of NDM-1-C208A in the absence or presence of CBS at IC₅₀. c Cellular thermal shift assays showing the binding of Bi(III) to NDM-1 in E. coli as judged from the shift of NDM-1 melting temperature from 50.1 °C to 48 °C for control and CBS-treated group, respectively. Mean value of three replicates are shown and error bars indicate SD. d The substitution of Zn(II) in NDM-1 by CBS as determined by ICP-MS. e Restoration of activity of NDM-1 upon supplementation of various ratios of Zn(II) to apo-NDM-1 and Bi-NDM-1. Mean value of three replicates are shown and error bars indicate SD. f The Lineweaver Burk plot shows that Bi(III) (as Bi(NIT)₃) inhibited NDM-1 via either a non-competitive or an irreversible inhibition mode

Fig. 3

Crystallographic analysis reveals the binding mode of Bi(III) in the active site of NDM-1 a Superimposition of Bi-bound NDM-1 (cyan) with native Zn-bound NDM-1 (orange). Structural alignment was done over C_α residues using SSM algorithm in Coot and the images were generated using PyMOL. The two structures can be superimposed well with a rmsd value of 0.18 Å. b The active site of Bi-bound NDM-1 with the anomalous density peak of Bi shown in purple mesh contoured at 15.0σ. c The active site of native Zn-bound NDM-1 with two Zn(II) ions shown as gray spheres and the bridging hydroxyl nucleophile as a red sphere. d An overlay image comparing the relative position of Bi(III) (purple sphere) with the two Zn(II) ions (gray spheres). Bi(III) is located in between the two Zn(II) ions slightly closer to Zn₁

Fig. 4

CBS suppresses the evolution of NDM-1 and boosts the antimicrobial activity of MER for the treatment of NDM-1-positive bacterial infection. a, b Heat plot visualizing the mutation frequency of (a) NDM-HK and (b) NDM-HK PCV exposed to MER in the presence of increasing concentrations of CBS. c Bar chart showing MPC values of MER in the presence of increasing concentration of CBS against NDM-HK and NDM-HK PCV. d Resistance acquisition curves during serial passage with the subinhibitory concentration of MER or combination of MER and CBS against NDM-HK. MIC test was performed every four passages. The inset shows the normalized expression level (by Western blot) of NDM-1 in the WT NDM-HK, 20^th passage of NDM-HK selected by MER or by combination of MER and CBS. Original western blots is shown in Supplementary Figure 10. e Bar chart showing associated-bacterial load in the in vitro infection model. The concentrations (μg mL⁻¹) used are 8, 16, and 32 μg mL⁻¹ for MER and 32 μg mL⁻¹ for CBS. f Survival curves showing efficacies in a murine peritonitis infection model with the use of mucin. BALB/c mice were infected by a lethal dose of NDM-HK via intraperitoneal injection. Four groups of mice were treated with vehicle control, monotherapy of MER (5 mg kg⁻¹), CBS (20 mg kg⁻¹), or combination therapy of MER and CBS. P < 0.001, Mantel–Cox test, significant difference from the vehicle control. Eight mice per group were used in vehicle control, monotherapy of MER, or CBS and 12 mice per group in the combination therapy