Thiacetazone, an antitubercular drug that inhibits cyclopropanation of cell wall mycolic acids in mycobacteria

Abstract

Background: Mycolic acids are a complex mixture of branched, long-chain fatty acids, representing key components of the highly hydrophobic mycobacterial cell wall. Pathogenic mycobacteria carry mycolic acid sub-types that contain cyclopropane rings. Double bonds at specific sites on mycolic acid precursors are modified by the action of cyclopropane mycolic acid synthases (CMASs). The latter belong to a family of S-adenosyl-methionine-dependent methyl transferases, of which several have been well studied in Mycobacterium tuberculosis, namely, MmaA1 through A4, PcaA and CmaA2. Cyclopropanated mycolic acids are key factors participating in cell envelope permeability, host immunomodulation and persistence of M. tuberculosis. While several antitubercular agents inhibit mycolic acid synthesis, to date, the CMASs have not been shown to be drug targets.

Methodology/principle findings: We have employed various complementary approaches to show that the antitubercular drug, thiacetazone (TAC), and its chemical analogues, inhibit mycolic acid cyclopropanation. Dramatic changes in the content and ratio of mycolic acids in the vaccine strain Mycobacterium bovis BCG, as well as in the related pathogenic species Mycobacterium marinum were observed after treatment with the drugs. Combination of thin layer chromatography, mass spectrometry and Nuclear Magnetic Resonance (NMR) analyses of mycolic acids purified from drug-treated mycobacteria showed a significant loss of cyclopropanation in both the alpha- and oxygenated mycolate sub-types. Additionally, High-Resolution Magic Angle Spinning (HR-MAS) NMR analyses on whole cells was used to detect cell wall-associated mycolates and to quantify the cyclopropanation status of the cell envelope. Further, overexpression of cmaA2, mmaA2 or pcaA in mycobacteria partially reversed the effects of TAC and its analogue on mycolic acid cyclopropanation, suggesting that the drugs act directly on CMASs.

Conclusions/significance: This is a first report on the mechanism of action of TAC, demonstrating the CMASs as its cellular targets in mycobacteria. The implications of this study may be important for the design of alternative strategies for tuberculosis treatment.

Figure 1. Structures and occurrence of mycolic acid sub-types in mycobacterial species presented in this study.

* proximal position of oxygenated mycolates is unsaturated .

Figure 2. Structures of chemical analogues of thiacetazone and their corresponding minimum inhibitory concentrations (MICs) in M. tb H37Rv.

MICs were determined by BACTEC 460 radiometric assay. *Data from MABA assay.

Figure 3. Inhibition of mycolic acid biosynthesis in M. bovis BCG by treatment with TAC or its analogue SRI-224.

Exponentially-growing cultures were treated with the drugs for 18 h and labeled by adding ¹⁴C-acetate for another 8 h. Fatty acid methyl esters (FAMEs) and mycolic acid methyl esters (MAMEs) were then extracted and separated by TLC on 10% silver nitrate-impregnated plates prior to exposure to a film overnight. All extracts were loaded equally for 100,000 cpm on silica plates impregnated with 10% silver nitrate. The autoradiographs show FAMEs, MAMES, oleic acid methyl esters (OAMEs), α- and keto-mycolates (k) and the lipids X and Y as indicated by arrowheads. (A) 1D TLC analysis using petroleum ether and diethyl ether (17∶3, v/v) as solvents. Drug concentrations employed are indicated in µg/ml. (B) 1D TLC profile of MAMEs extracted from cells treated with low concentrations of SRI-224 for either 1 day or over a period of 5 days, as indicated. (C) Extracts prepared after delipidation of the cells to remove the free and loosely bound lipids, while retaining the covalently bound mycolates. Extract from cells treated with SRI-224 but not subjected to delipidation is included to identify the lipids X and Y by comparison with extracts from delipidated cells that were either untreated (c) or treated with 5 µg/ml of the indicated drug for 24 h. (D) 2D TLC analysis on silica plates impregnated with 10% silver nitrate. Extracts were separated in the first direction by using two developments with hexane/ethyl acetate (19∶1, v/v) and in the second direction by using a triple development with petroleum ether/diethylether (17∶3, v/v). (E) Extracts from cells radiolabeled with [methyl-¹⁴C]-methionine are compared with those from cells radiolabeled with ¹⁴C-acetate.

Figure 4. Structural determination of lipids X and Y.

Lipids X and Y were purified from cell wall extract of M. bovis BCG Pasteur culture, following treatment with SRI-224 (5 µg/ml) for 24 h. (A) Conventional TLC showing purity of the samples containing lipids X and Y, that were used for structural analyses, as seen by staining with phosphomolybdic acid and charring. (B) m/z values from MALDI-TOF-MS spectra correspond to [M+Na]⁺ adducts of a family of methylated keto-mycolates and α-mycolates for purified lipids X and Y, respectively. (C) For ¹H-NMR analysis, protons are labelled (a to h) according to their respective positions in functional groups. Relative integrations of protons have been normalized according to the number of ethylenic protons (2 for X and 4 for Y) and are indicated in brackets. *stands for proton ¹H signals of contaminant ethanol present in the NMR tubes.

Figure 5. Inhibition of synthesis of cell wall mycolic acids in different mycobacterial species by treatment with TAC or its analogue SRI-224.

Autoradiogram of FAMEs and MAMEs extracted from exponentially growing cells that were radiolabeled in vivo with ¹⁴C-acetate. Drug concentrations are indicated in µg/ml. The different mycolates are indicated by arrows. Mycolic acid profiles from M. marinum (A) and from M. chelonae (B). All other details are as in Figure 3.

Figure 6. In vivo identification and relative quantification of cis-cyclopropanes by ¹H HR-MAS NMR.

(A) Detail of ¹H HR-MAS spectrum of control whole cells of M. bovis BCG. (B) Unidimensional selective COSY spectrum after irradiation of Ha signal showing ³ J and ² J connectivities of cis-cyclopropyl ring Hb and Hc protons to Ha as depicted in (C). (D) Relative quantification by ¹H HR-MAS NMR of cis-cyclopropanes based on differential integration of the Ha signals in control untreated cells (c) or cells treated with TAC-treated (1 µg/ml) (TAC) or SRI-224-treated (1 µg/ml) (224). Results are representative of two independent experiments.

Figure 7. Partial recovery of mycolic acid synthesis in the presence of TAC or SRI-224 in strains overexpressing the CMAS genes.

Autoradiogram of FAMEs and MAMEs extracted from exponentially growing cells that were radiolabeled in vivo with ¹⁴C-acetate. (A) M. bovis BCG or (B) M. marinum containing the plasmid vector pMV261 or the same vector carrying cmaA2, mmaA2 or pcaA of M. tb H37Rv. Extracts were obtained from untreated control cells (c) or cells treated with 5 µg/ml of either TAC or SRI-224 as indicated. All other details are as in Figure 3.

Figure 8. Proposed mechanism for generation of mycolic acid sub-types by the action of CMAS enzymes (A) and inhibition by TAC/SRI-224 (B).

The generation of α- and the oxygenated mycolic acids is considered to follow to two independent pathways. A common, di-unsaturated precursor, Y, is envisaged for the two pathways. Y is subsequently transformed into α-mycolic acids by the action of the MmaA2 and PcaA that modify the distal or proximal double bond, respectively. Action of MmaA4 commits Y to the pathway for the oxygenated mycolic acids, by producing the precursor X. MmaA3, which is required for generation of methoxy-mycolic acids in M. tb is inactive in M. bovis BCG Pasteur due to the presence of a point mutation . The proximal double bond is modified by the CmaA2 (and MmaA2) or PcaA to generate trans- or cis-cyclopropanated derivatives, respectively. In the presence of TAC, all the CMASs mentioned above are inhibited, except for MmaA4. Due to inhibition of MmaA2, excess of Y is diverted to MmaA4 leading to generation of X, which accumulates due to lack of activities of CmaA2 and MmaA2. SRI-224 appears to affect MmaA4 to a certain degree, leading to accumulation Y in addition to X. (For simplicity, only the meromycolyl moiety of mycolates has been depicted).