In the DXP pathway (Figure 1), pyruvate (PYR) and glyceraldehyde 3-phosphate (GAP) are first condensed by dxs with thiamine to produce 1-deoxy-D-xylulose 5-phosphate (DXP) [4]. DXP is then reduced and isomerized by a single enzyme dxr with NADPH to form 2C-methyl-D-erythritol 4-phosphate (MEP) [4]. MEP reacts with CTP in the presence of ispD to produce 4-diphosphocytidyl-2C-methyl D-erythritol (CDP-ME) [4]. CDP-ME is phosphorylated by an ATP dependent kinase ispE to form 4-diphosphocytidyl-2C-methyl D-erythritol 2-phosphate (CDP-MEP) [4]. CMP is eliminated from CDP-MEP and the molecule is cyclized by ispF to form 2C-methyl-D-erythritol 2,4-diphosphate (MEC) [4]. The ring structure of MEC is opened and reduced by an iron-sulfur cluster containing enzyme ispG by a yet to be fully characterized mechanism to form hydroxylmethylbutenyl diphosphate (HMBPP) [16]. HMBPP is further reduced by another iron-sulfur cluster containing enzyme ispH, to produce a mixture of isopentenyl diphosphate (IPP) and dimethylallyl diphosphate (DMAPP) [17]. Unlike the mevalonate pathway, all the DXP intermediates are phosphorylated and highly acidic. This unique physicochemical property allowed a single step purification of all these metabolites using anionic SPE.

Attempts were initially made to quantify the DXP pathway intermediates by gas chromatography mass spectrometry (GC-MS) after derivatization with trimethylsilyl (TMS). DXP and MEP were readily detected (limit of detection at least 9 pmol per injection). However, all other DXP intermediates were not detectable, likely to be due to the low volatility of the TMS derivatives (File S1). We next explored ultraperformance liquid chromatography mass spectrometry (UPLC-MS) for the quantification of the DXP pathway intermediates.

A time-of-fight mass spectrometry was selected because it has the highest scan speed and excellent mass accuracy as compared to other types of mass spectrometry [18]. A range of mass-to-charge ratio (m/z) was scanned in the negative mode and synthetic standards were characterized. All DXP pathway intermediates can be detected and their m/z were unambigously determined (Table 1). Separation of the DXP pathway intermediates was then optimized on a UPLC C18 column (1.7 µm particle size). Ion pairing with tributylamine was found to be an ideal ion-pair reagent allowing excellent resolutions of the various intermediates rapidly (10 mins per sample; Table 2; Figure 2).

Solid phase extraction (SPE) has been widely used to isolate analytes in various biological samples [19], [20], [21]. It is rapid and can enrich analytes under mild conditions without the need for solvent evaporation from the extracts [15]. As all the DXP intermediates of interest are phosphorylated (Figure 1), we explored the use of anion exchange SPE [22]. The direct SPE recoveries of all the intermediates were >40% as compared to the initial concentrations of standards used (File S2). It is worthy to note that the LC-NH2 resin used in this study was superior in performance when compared to other similar supports (data not shown) [22].

To examine the linearity, dynamic range and limit of quantification (LOQ) of the SPE UPLC-MS analysis for the DXP pathway intermediates in cell extracts, mixture of DXP, MEP, CDP-ME, CDP-MEP (in house synthesized), MEC, and HMBPP were spiked into 10 mL of cell extracts to final concentrations ranging from 2 µM to 0.01 µM. The extracts were then loaded onto an SPE cartridge and eluted in ammonium hydroxide. The results showed that the UPLC-MS signals of all intermediates were linearly correlated with the initial concentrations in cell extracts (R²>0.99). In addition, the method demonstrated the LOQ (LOQ≤0.1 µM), intraday variation and interday variations (CV<12%) allowing precise quantification of the DXP pathway intermediates in biological samples (Table 1).

With the developed method, though LOQ of CDP-MEP (0.1 µM) was much higher than that of the other metabolites examined (0.01 µM), it was still considerably more sensitive than reported for the quantification of mevalonate metabolites (a similar class of compounds to DXP metabolites) at LOQ of 4.17 µM [15]. CDP-MEP was found to be co-eluted with many major cellular phospho-compounds, which is likely to result in lower signal due to the phenomenon of ion suppression (File S3). Nonetheless, most these intermediates were readily detected in the genetically modified strains relevant to metabolic engineering of the DXP pathway.

Lycopene is an antioxidant isoprenoid and the production in E. coli is known to be enhanced by overexpression of four enzymes in the DXP pathway (dxs, idi, and ispDF) under non-induced conditions [11]. Consistent with previous studies [3], [8], the strong overexpression of four enzymes (dxs, idi, ispD and ispF) resulted in the inhibition of lycopene production (Figure 3 B). To analyze the profiles of DXP pathway intermediates under this condition, cells were harvested in the exponential phase and the metabolites were quantified. Four intermediates (DXP, MEP, CDP-ME and MEC) were detected in all treatments, and the concentrations increased in parallel to the amounts of inducers, IPTG (Figure 3 C). Interestingly, a significant decrease of intracellular MEC concentration was observed with 0.1 mM IPTG induction (Figure 3 C). Further analysis detected the accumulation of large amount of MEC in the growth medium, greater than the total amount found in the cellular fraction (Figure 3 D). This was an unexpected and intriguing observation as highly charged, phosphorylated compounds, are not known to passively diffuse across intact cell membrane. Similar growth curves were observed with or without 0.1 mM IPTG induction (Figure 3 A), indicative that the viabilities of the cells were not observably different. The high accumulation of MEC in the broth thus could be selectively effluxed from the cells. Preliminary studies showed that the fsr efflux pump may be involved in this process (File S4). It is then not unreasonable to speculate that MEC accumulates to an intracellular threshold concentration (∼30 µmol/L, Figure 3 C) resulting in cellular stress response, as suggested by a recent study of MEC in response to oxidative stress [23]. This may in turn result in the efflux of MEC so as to prevent further intracellular accumulation of this metabolite.

Although the exogenous addition of MEC to levels similar to the amounts effluxed did not affect cell growth and lycopene production (File S5), efflux of MEC itself may have diverted carbon source away from biosynthesis of isoprenoid products resulting in the decrease in isoprenoid biosynthesis. The good inverse correlation between lycopene production and the concentration of extracellular MEC at various IPTG inductions was consistent with this suggestion (Figure 3 B and D).

To test whether lycopene production inhibition was related to MEC efflux, the strain was engineered to co-overexpress ispG (with dxs-idi-ispDF), the enzyme utilizing MEC (Figure 1). In the strong induction condition (0.1 mM IPTG), where lycopene production was severely inhibited and MEC efflux was high (Figure 3 B and D), co-overexpression of ispG indeed concurrently increased lycopene production (Figure 4 A) and reduced efflux of MEC (Figure 4 B). The concentration of intracellular MEC was found to be increased with ispG overexpression, a result supporting the proposal of an intimate relationship between ispG and intracellular MEC. HMBPP (a product of ispG, Figure 1) was also readily detected inside the cells overexpressing ispG (HMBPP was not detectable in the parental strain expressing dxs-idi-ispDF, Figure 4 D), consistent with the above proposal that with higher ispG more MEC was consumed for isoprenoid biosynthesis. In order to gain an insight into the profiles of efflux pumps in these strains, all the 20 known efflux pump operons in E. coli [24] were analyzed at the transcription level. The expression levels of these pumps were not regulated by ispG overexpression (Figure 5). Taken together, overexpression of the metabolic enzyme ispG reduced the amount of MEC efflux possibly by shuttling it directly to the downstream products, e.g. lycopene.

To demonstrate the broader utility of the method developed here, measurements of the DXP metabolites were conducted in other bacteria. Besides E. coli, other bacteria have also been used for the production of isoprenoids [25]. The DXP metabolites of two gram negative strains (Chromobacterium violaceum [26] and Pseudomonas aeruginosa [27]) and one gram positive strain (Bacillus subtilis [25]) were characterized. A gram positive strain (Staphylococcus aureus [28]) that utilize the MVA pathway but not the DXP pathway was also included as a negative control. Analysis of the cells harvested in the exponential growth phase (OD595 = 2–3) indeed showed that intracellular DXP pathway intermediates can be detected in all strains except Staphylococcus aureus (Figure 6). The four bacteria used in this study were all wild types, where the DXP pathway genes were not genetically overexpressed. The level of the DXP pathway intermediates in these strains was expectedly lower than that in engineered E. coli, yet the developed method here has the sensitivity to measure these intermediates. None of the DXP pathway intermediates were detected in the broth supernatant of these strains (data not shown), suggesting that no DXP intermediates were effluxed from these cells under the conditions.

In this study, an anion exchange solid phase extraction was developed to efficiently and selectively purify all the DXP pathway intermediates from biological samples simultaneously. UPLC-MS (TOF) was then optimized to reliably quantify the purified intermediates with good sensitivity. The method allows the direct monitoring of DXP metabolites in cells for the production of isoprenoids, an invaluable tool for rational engineering of the pathway which is currently not available.

E. coli BL21-Gold (DE3) (Stratagen) [E. coli B F⁻ ompT hsdS (r_B⁻ m_B⁻) dcm⁺ Tet^r gal λ(DE3) endA Hte] was used for lycopene production with pACLYC [31]. pET-SIDF (named as p20T7MEP in [3]) was transformed into BL21-Gold (DE3) harboring pACLYC. IspG was amplified by polymerase chain reaction with the extracted E. coli genomic DNA. Primers XhoI-RBS-ispG F and ispG-BamHI R were used (primers used in this study are summarized in File S6). The purified PCR product was ligated into pET-SIDF which contained XhoI site and BamHI site. The resulting plasmid was termed as pET-SIDFG, which was subsequently transformed into BL21-Gold (DE3) with pACLYC.

E. coli DH5α (Invitrogen) [F- φ80lacZΔM15 Δ(lacZYA-argF)U169 recA1 endA1 hsdR17(rk⁻, mk⁺) phoA supE44 thi-1 gyrA96 relA1 λ⁻] was used for genomic DNA extraction. E. coli XL10-Gold (Stratagene) [Tet^r Δ(mcrA)183 Δ(mcrCB-hsdSMR-mrr)173 endA1 supE44 thi-1 recA1 gyrA96 relA1 lac Hte [F′ proAB lacI^qZΔM15 Tn10 (Tet^r) Tn5 (Kan^r) Amy]] with pACLYC was used for production of recombinant ispE enzymes. IspE was amplified by polymerase chain reaction with the extracted E. coli genomic DNA. Primers SacI-ispE F and ispE-XhoI R were used (File S6). The purified PCR product was ligated into a modified pBAD-B (Invitrogen) which contained six histidine tag, SacI site and XhoI site. The resulting plasmid was termed as pBAD-ispE, which was subsequently transformed into E. coli XL10-Gold with pACLYC.

Wild type Bacillus subtilis (BGSC 1A1) was requested from BGSC. Wild type Chromobacterium violaceum, Pseudomonas aeruginosa and Staphylococcus aureus were gifts from Prof. Yew Wen Shan (Department of Biochemistry, NUS).

Standards of all the DXP pathway intermediates are commercially available (Echelon) except CDP-MEP which was synthesized in house as described in this session. Recombinant ispE was purified from E. coli XL10-Gold containing pBAD-ispE and pACLYC. A colony was picked from agar plate, inoculated into 2xPY medium (20 g/L peptone, 10 g/L yeast extract and 10 g/L NaCl, pH = 7) containing 34 µg/mL chloramphenicol and 100 µg/mL ampicillin, and incubated overnight. Five hundred microliter aliquots of cell culture grown overnight were inoculated into 25 mL 2xPY medium in 250 mL shake flask. Cells were grown at 37°C/300 rpm until OD595 reached between 0.5∼1.0. The cells were then induced with 10 mM L-arabinose and grown at 20°C for 24 hours. The cell pellets were collected and resuspended in 1 mL B-PER II reagent (Pierce) and homogenized on Mini-Beadbeater-16 (Biospec) with 200 µL glass beads for 1 min. The cell lysates were centrifuged for 10 min at 4°C and the supernatant was diluted with 20 mL NPI-10 (50 mM Na₂HPO₄, 300 mM NaCl and 10 mM imidazole, pH = 8) and incubated with 200 mg Ni-NTA micro beads (USB) for 1 h at room temperature. The beads were washed with 40 mL NPI-10 and eluted with 300 µL NPI-250 (50 mM Na₂HPO₄, 300 mM NaCl and 250 mM imidazole, pH = 8).

In a 50 µL reaction, 1.25 mM CDP-ME was converted into CDP-MEP with 10.5 µg recombinant ispE in the presence of 40 mM Tris (pH = 6), 2.5 mM MgCl₂, 50 mM β-mercaptoethanol and 10 mM ATP. The reaction was incubated at 37°C for 15 h and terminated with 450 µL acidic extraction solution (acetonitrile/methanol/water 40∶40∶20+0.1 M formic acid). CDP-MEP was confirmed by mass spectrometry and the concentration was estimated by measuring consumed CDP-ME in the reaction.

A colony was picked from agar plate, inoculated into 2xPY medium containing 34 µg/mL chloramphenicol and 100 µg/mL ampicillin, and incubated overnight. Fifty microliter aliquots of cell culture grown overnight were inoculated into 5 mL 2xPY medium in 50 mL Falcon tube. Cells were grown at 37°C/300 rpm until OD595 reached between 0.5∼1.0. The cells were then induced with IPTG at the indicated concentrations and grown at 28°C for the given time periods prior to collection for metabolic extraction or lycopene assays.

Fifty microliters of cell suspension was sampled at 24 h after induction, and the OD595 was recorded. The cells were centrifuged for 2 min and resuspended in 200 µL of acetone. Resuspended cells were vortexed for 10 min and centrifuged at 3,000 g for 2 min. One hundred microliters of supernatant was mixed with equal volume of ethanol and transferred to 96 well optical bottom plate (NUNC). Lycopene content was determined by interpolating from a standard dilution of lycopene (Sigma) based on absorbance at 472 nm (Spectra Max 190, Molecular Devices).

Cell suspension equivalent to 6 mL OD595 = 1.0 cells were withdrawn. The cells were centrifuged for 5 min. The cell pellets were resuspended in 10 mL acidic extraction solution (acetonitrile/methanol/water 40∶40∶20 +0.1 M formic acid) [32] for intracellular metabolite extraction. One hundred microliter supernatant was diluted with 100 µL ddH2O and 800 µL modified acidic extraction solution (acetonitrile/methanol 50∶50 +0.125 M formic acid) for extracellular metabolite extraction. The resuspended cell pellets in acidic extraction solution was incubated at −20°C for 60 min with periodic shaking. Following centrifugation, the supernatant was purified through a LC-NH2 resin (Sigma). Diluted broth supernatant was also purified by LC-NH2 resin in the same way. The cartridge was eluted with 400 µL 1% NH₄OH solution after centrifugation at 3,000 g for 2 min and pH of eluate was subsequently adjusted to acidic (pH = 5) by 3 µL acetic acid.

A LC-MS/MS method was developed for phosphorylated sugars with HPLC MS/MS [14]. The method was modified for DXP intermediates with UPLC (Waters ACQUITY UPLC) – (TOF)MS (Bruker micrOTOF II) platform. In brief, aqueous solution containing 15 mM acetic acid and 10 mM tributylamine and methanol were used as mobile phase with a UPLC C18 column (Waters CSH C18 1.7 µm 2.1×50 mm). The elution was done at 0.15 mL/min (Table 2). Electrospray ionization was used and mass spectrometry was operated to scan 50–800 m/z in negative mode with −500 V end plate voltage and 4500 V capillary voltage. Nebulizer gas was provided in 1 bar, drying gas temperature was 9 mL/min, and dry gas temperature was 200°C. Sample injection volume was 5 µL.

A range of m/z typically with 0.06 m/z width (the average m/z distribution width with the used MS instrument) was extracted from the acquired data (50–800 m/z) for each intermediate. The range of m/z was determined with 50 µM standards of each intermediate prepared individually in water except CDP-MEP which was in elution solution of SPE. At the assay condition, all the intermediates were detected in the form [M-H]⁻. Retention time was subsequently determined for each intermediate with the same 50 µM standards and the set m/z extraction range. The peak area was calculated with the software provided by the manufacturer. Based on the peak area, concentrations of the DXP pathway intermediates were determined from calibration curves constructed by using synthetic standards prepared in biological matrix (cell extracts or broth supernatant).

Linearity of the assays was determined with cell extracts containing DXP, MEP, CDP-ME, CDP-MEP, MEC and HMBPP in concentration of 2 µM, 1 µM, 0.5 µM, 0.25 µM, 0.1 µM, 0.05 µM, 0.02 µM and 0.01 µM. Intraday/interday variations were determined with indicated number of replicates and sample concentration as Table 1.

Cell suspension equivalent to 0.1 mL OD595 = 1.0 cells was sampled at 4 h after induction. Gene transcription was quantified as described in [11], where cysG, idnT and hcaT were used as reference genes. Primers used were summarized in File S6.

Fosmidomycin was added into the cell in the final concentration of 25 µg/mL at 4 h after the IPTG induction. Intracellular and extracellular metabolites were analyzed at 2 h after the fosmidomycin inhibition.

Glycerol stocks of Bacillus subtilis, Chromobacterium violaceum, Pseudomonas aeruginosa and Staphylococcus aureus were directly inoculated into 2xPY and incubated at 37°C overnight. Cell pellets of cells grown overnight were resuspended in 10 mL 2xPY (OD595 = 0.2) in 50 mL Falcon tube. Cells were grown at 37°C/300 rpm until OD595 reached between 2 and 3, when cells were collected for metabolite quantifications.