Spiroplasma melliferum KC3 and Acholeplasma laidlawii PG-8A were kindly provided by Prof. G. Wroblewsky of the University of Rennes, France. The Mycoplasma gallisepticum S6 strain was provided by Prof. S.N. Borkhsenius, Institute of Cytology,St. Petersburg, Russian Academy of Science. S. melliferum was grown in SP4 medum without any specific aeration and with mixing at 30°C for 20 hours after 1∶10 dilution, as described earlier [14]. Acholeplasma laidlawii PG-8A and Mycoplasma gallisepticum S6 were grown in a modified Edward's medium (Tryptose 20 g/L, NaCl 5 g/l, NaOAc 5 g/l, KCl 1.3 g/l, Tris 3 g/l, yeast dialysate 5%, horse serum 6%, glucose 0.5%, pH 7.6) at 37°C for 20 hours after 1∶100 dilution [15]. Bacteria were cultured in covered flasks, and the time of growth and the pH of the solution were controlled [11]. Bacteria were harvested by centrifugation (10 min, 16,000 g) in the log phase, which was determined by pH values (6.5–6.6 for both, S. melliferum and M. gallisepticum). The metabolic profiles were obtained from cultures grown from a single clone for less than five passages. Each metabolome experiment was independently repeated at least seven times; 50 ml cultures from the same strain and with the same sample preparation procedure were used for each experiment.

We used the “color test” method to determine whether Mollicutes survive in acidic conditions and to estimate the critical pH value for each species. Aliquots of M. gallisepticum, A. laidlawii and S. melliferum culture were exposed to decreased pH (hydrochloric acid was added) in steps of ΔpH = 0.1 for 1 hour starting at pH 7.5. Each aliquot was then subjected to a series of dilutions (up to 10⁹) in medium (pH 7.5) containing pH indicator (Phenol Red), and the presence of living cells was detected by the medium color change. The tolerated acidity was defined as the minimum acidity at which 10% of cells survived.

The following chemicals were used as standards: sodium pyruvate (100 mg/ml, disodium salt hydrate), D-fructose 6-phosphate, hydrate of sodium phospho(enol)pyruvate (97% purity, enzyme quality), dehydrated disodium salt of D-ribose 5-phosphate, di-glyceraldehyde 3-phosphate (46.1 mg/ml). Purified (98%) amino acids, nucleotides, nucleosides (adenosine, deoxyadenosine, inosine, cytosine monophosphate, and thymidine) from Sigma-Aldrich (USA) were used as standards as well. The following reagents were used for extraction and solution preparation: absolute methanol (HPLC grade) from Biosolve (The Netherlands), ammonium acetate (ultra clean grade) from Helicon (Russia), formic acid (98–100%) from Riedel-de Haen (Germany), ammonium hydroxide solution (29.73%) from Fisher Scientific (USA), water (HPLC-MS) and acetonitrile (HPLC-MS) from Panreac (Spain).

For metabolite analysis, S. melliferum, M. gallisepticum, or A. laidlawii (50 ml) were grown in a liquid medium. Cells were harvested by centrifugation at 16,000 g at 20°C for 10 min and washed with the washing solution (150 mM NaCl/50 mM Tris). The pH of the washing solution was 6.5 (the acidity in the logarithmic phase of Mycoplasma growth), while for acid stress studies the pH of washing solution was about 5.5 (depending on the type of culture and the selected conditions of acid stress). Thus, the culture was under the influence of selected acidity conditions during the washing procedure. The cell pellet was resuspended in 3 ml of washing solution (the pellet volume was 30 µl) and precipitated again. Then cells were washed twice with 150 µl of washing solution.

The metabolism was rapidly quenched by cold methanol extraction. A cold methanol extraction method was developed on the basis of a previously reported cold methanol extraction protocol [16], [17] as described below. The metabolites were extracted by adding 1000 µl of methanol (−77°C) to 75 ul of the resuspended cell pellet; the sample was vigorously shaken (1 min) and then kept at −77°C for 15 min. The sample was warmed for 3 min and then thoroughly shaken again. The resulting sample was centrifuged for 30 min at 16,000 g at 4°C. The supernatant was separated into aliquots and lyophilized. The dry extract was kept no longer than 4 days prior to analysis. The dry extract was dissolved in a mixture consisting of 20% acetonitrile and 80% water and analyzed immediately.

Until recently there was no published record of an LC-MS method of metabolome analysis of the studied bacteria (S. melliferum, M. gallisepticum, and A. laidlawii). Pre-testing a few other options (such as extraction by acetonitrile, methanol/water, acetonitrile/water/acid and others), we have chosen the cold methanol extraction method, as it has been demonstrated to be the most effective. The cold methanol extraction protocol described in [16] is the basis of the protocol used here. A similar modification has been successfully used recently for M. pneumoniae studies [18].

Mass spectrometry analysis was performed on a Q-TOF 6520 series time-of-flight mass spectrometer (Agilent Technologies). The flow from the analytical column was introduced directly into the electrospray ion source of the mass spectrometer. Prior to the experiment, the mass spectrometer was calibrated to 2 ppm accuracy of the m/z value. The ionizing spray voltage was 3500 V in both positive and negative ionization modes. Nitrogen of various degrees of purity was used as a dry gas at a pressure of 20 psi with a flow rate of 6 l/min and as a gas in the collision cell. The temperature of the quartz capillary was 325°C. HPLC-MS and HPLC-MS/MS analyses were carried out using the series 1200 high performance liquid chromatograph (Agilent Technologies), coupled with the mass spectrometer. The following chromatographic analytical column was used in the study: Zorbax RX-SIL Narrow-Bore (150 mm×2.1 mm×5 µm) from Agilent Technologies. To protect the separating phase of these highly effective analytical columns from chemical damage, as a safety cartridge we used the Zorbax RX-SIL 4-Pack analytical guard column (4.6 mm×12.5 mm×5 µm) purchased from Agilent Technologies.

Chromatographic analysis was performed with the following parameters: auto-sampling temperature, 8°C; analytical column temperature, 18°C; injection volume, 2 µl; solvent flow rate, 50 µl/min. The following solvents were used as eluting solutions: eluent A was 20 mM ammonium acetate/0.25 mM ammonium hydroxide in water/acetonitrile mixture of 95∶5 ratio, pH 8.02; eluent B was pure acetonitrile. The gradient of the solvent transition was as follows: for positive ionization mode t = 0, 100% B; t = 30 min, 0% B; t = 32 min, 0% B; t = 35 min, 100% B; t = 60 min, 100% B. In negative ionization mode t = 0, 100% B; t = 30 min, 0% B; t = 32 min, 0% B; t = 35 min, 100% B; t = 60 min, 100% B. Metabolite identification was confirmed by fragmentation spectra of the detected ions. The collision energy was fixed at 20 eV, and MS/MS spectra were recorded in the range of 30–1000 m/z with the minimal width of the ion isolation window at 1.3 m/z.

mzXML spectra results are available at: https://dl.dropboxusercontent.com/u/73633783/Spectra.rar

Metabolite search and data processing were performed using the Metabolomic Analysis and Visualization Engine (MAVEN) [19] software and the Trans-Proteomic Pipeline (TPP) resource available online, where the data were converted into the mzXML format (MAVEN compatible). S. melliferum, M. gallisepticum, and A. laidlawii metabolites were identified using the list of all possible metabolites for these bacteria, garnered from all the protein annotation data that were previously reported [3], [11]. A list of all theoretically possible metabolites of S. melliferum, M. gallisepticum, and A. laidlawii was prepared in accordance with the KEGG database [20] and contained all the metabolites associated with the proteins that were annotated for these bacteria. The following parameters were used for the search: range of m/z values (extraction window), 15 ppm m/z; minimum intensity of peak, 1000 a.u.; minimum value of baseline signal intensity ratio, 10. If an identified metabolite was detected in at least five MS runs out of seven in specie one, while in specie two it was not detected, or it was detected only once, we attributed this metabolite to be present in the first species and to be absent in the second one.

A pairwise sample comparison of metabolomic data for three species was performed using the XCMS online service, providing a direct comparison of two sample groups [21]. From the resulting features of every compared pair of oganisms, we selected only those with a p value≤0.05 in order to state that compound concentration is different in two species. Additionally these compounds were analyzed manually by counting the metabolite identifications among the seven repetitions of every species for both acquisition modes. The quantification of an identified metabolite is possible only if it was detected at least three times in each species. In the case a compound was detected less than three times of seven, only a qualitative comparison in the pair was possible, based on the detection of MS counts for this compound in the pair.

Bacteria were cultivated in liquid media to more easily determine the growth phase. Bacteria were harvested in the logarithmic growth phase, which was determined based on the culture duplication time (see “Bacteria strain and growth conditions”). Cold methanol extraction was used to instantly quench the metabolism [16]. The high effectiveness of this method and its low loss of compounds has been demonstrated previously [22]. Metabolite detection was carried out using HPLC analysis in combination with electrospray ionization quadrupole time-of-flight mass spectrometry (HPLC-MS Q-TOF). The parameters of the chromatographic method, as well as the mass spectrometric peak recording, were optimized using standards to obtain the most reliable data (see “Materials and Methods” section). Metabolites were initially identified using the Metabolomic Analysis and Visualization Engine (MAVEN) software [19]. The metabolite identity was then confirmed by analysis of the detected parent ions fragmentation spectra using targeted mass spectrometry [23].

There were seven independent repeats for metabolite detection for each of the three studied bacterial species. Usually one LC-MS analysis run produces ∼120 peaks in which the m/z values are close to the exact metabolite m/z values (deviating by less than 10 ppm). However, in MS acquisition, some compounds show unstable signals and display low reproducibility; their peak intensities are comparable to the noise level. Each compound was considered to be present in bacteria if it was observed at least three times (in seven runs) in any of the ionization modes (positive or negative) and the intensity of the corresponding peak was significantly higher than that of the background. List of identified metabolites is shown in Table 1.

Fragmentation spectra were obtained for most of the detected metabolites using targeted mass spectrometry. The fragmentation spectra were compared with standard fragmentation spectra, which were obtained under similar ionization conditions (polarity of ionization and collision energy values were taken into account) and provided by the Metlin MS/MS Spectrum Match service [24], [25], [26]. Figure S1 shows an example of the metabolite identification as provided by the MS/MS. Interestingly, all fragmentation spectra confirmed the primary identification of the compounds based on the m/z values alone. There were no compounds whose fragmentation spectra contradicted the identification based on the m/z values. The provided m/z values usually did not deviate from the theoretical value by more than 10 ppm (see Table 2). Among the detected metabolites, there were several compounds that presented a relatively large deviation from their theoretical ion m/z values (up to 15 ppm m/z). Nevertheless, MS/MS fragmentation spectra render the unambiguous identification of such compounds possible.

The strategy for metabolome analysis includes the following steps: 1) Metabolic map reconstruction; 2) Prediction of all possible metabolism intermediates; 3) Comparison of metabolic enzymes of Mollicute species; 4) Experimental MS detection and mapping of the detected compounds on the metabolic map for each specie; 5) Juxtaposition of the metabolome data to enzyme differences between three Mollicute species.

We manually reconstructed the metabolic network of M. gallisepticum, S. melliferum, and A. laidlawii in order to fill the network with the detected intermediates. To build a comprehensive metabolic network for each species, we used the Kyoto Encyclopedia of Genes and Genomes database and UniprotKB proteogenomic annotation data provided earlier by our lab [3], [11], [27]. For enzymes that could carry out more than one reaction, we removed the reactions that were decoupled from pathways and those for which the substrate was unavailable (i.e. there is no way for substrate synthesis and transport into the cell according to the proteogenomic annotation). The final result is a map without gaps, isolated reactions, or open metabolic loops for each species (Figures 1–3, see text S1 and Figures S2, S3).

For each species a list of predicted metabolism intermediates was formed. The map includes all compounds, which serve as substrates and products for all enzymes and transporters predicted by the proteogenomic annotation. The metabolic database for raw MS data analysis by MAVEN includes all metabolism intermediates predicted for the three species. This database contains 500 items and is suitable for the analysis of each species. The database used is wider than the list of possible metablolites for each species. It therefore permits detection of metabolites produced by putative uncharacterized enzymes.

Metabolic pathways were reconstructed with all the identified metabolites of S. melliferum, M. gallisepticum and A. laidlawii positioned in the maps (Figures 1–3). The metabolome predicted by proteogenomic annotation consists of 323 metabolites for A. laidlawii, 225 for M. gallisepticum, and 361 for S. melliferum. We have identified 75, 74 and 74 metabolites for each species, respectively. Accordingly, we were able to detect 20 to 33% of the predicted metabolites by LC-MS using HILIC chromatography (Figure 4 and Table 1).

Reconstruction of the three species' metabolic maps reveals many pathways with enzymatic gaps in the middle. For pathways in which only one enzyme is missing, the gap can be filled by adding an unassigned reaction as performed earlier for another Mycoplasma species, M. pneumoniae [23]. Alternatively, for a missing enzymatic reaction, a bypass can be found by the manual analysis of the known enzyme's side activities.

One example is the link between pentoses and hexoses (the pentose phosphate pathway) in Mollicutes. This link is omnipresent in living cells, although in many organisms, including mycoplasmas, only its non-oxidative branch is annotated. Two enzymes, transketolase (tktA) and transaldolase (tal), act in this branch of the pentose phosphate pathway (Figure 5). Transketolase transforms two pentoses, xylulose-5-phosphate and ribose-5-phosphate, into the seven-carbon product sedoheptulose-7-phosphate and the three-carbon glyceraldehyde-3-phosphate. To produce the hexose, fructose 6-phosphate, and glyceraldehyde-3-phosphate and to finish the pentose phosphate pathway, the same enzyme uses the four-carbon erythrose-4-phosphate and the pentose xylulose-5-phosphate. A key enzyme, transaldolase, acts to link these two transketolase reactions; it removes three-carbon fragment from sedoheptulose-7-phosphate and condenses it with glyceraldehyde-3-phosphate, forming the fructose 6-phosphate and the erythrose-4-phosphate [28].

Annotation of genome sequence shows that Mollicutes lack transaldolase, and this obviously creates a gap in the metabolic branch. Nevertheless, we detected a unique intermediate of transketolase reaction, sedoheptulose-7-phosphate, in all three species studied (along with less specific intermediates). It suggests that the pentose phosphate pathway is functional. The connection of the glycolytic pathway with a functional pentose phosphate pathway was earlier demonstrated for M.pneumoniae as ¹³C-6 glucose carbons were detected in ribose 5-phosphate using mass spectrometry [23].

Database search for transaldolase-like proteins in all other Mollicute genomes produces a negative result. Therefore we believe that transaldolase activity is absent in this genus. To fill the gap, it is possible to postulate the presence of aldolase activity by an unknown mycoplasma protein. The other way is to find a bypass of this reaction performed by other known mycoplasma enzymes. The literature shows that sedoheptulose-7-phosphate can act as acceptor for 6-phosphofructokinase; fructose-bisphosphate aldolase can bind with sedoheptulose-1,7-bisphosphate and decompose it to glycerone phosphate and erythrose-4-phosphate (see Figure 5) [29]. Glycerone phosphate can be isomerized to glyceraldehyde-3-phosphate by triosephosphate isomerase [28].

The proposed modifications in the pentose phosphate pathway make it possible to utilize ribose as an energy source despite the lack of transaldolases. The described pathway is reversible in S. melliferum, and A. laidlawii. The first reaction, phosphorylation of sedoheptulose-7-phosphate, catalyzed by 6-phosphofructokinase, is irreversible; however, dephosphorylation of sedoheptulose-1,7-bisphosphate can be carried out by fructose -1,6-bisphosphatase [30], annotated in S. melliferum [11].

Fructose 1,6-bisphosphatase is not annotated in A. laidlawii, and eritrose-4-phosphate, formed as a result of the transketolase reaction between fructose-6- phosphate with glyceraldehyde-3- phosphate, must be utilized in some other way. Eritrose-4-phosphate may be utilized in phenylalanine synthesis, as all enzymes of phenylalanine biosynthesis are annotated in A. laidlawii [3]. A lack of fructose-1,6-bisphosphatase, as well as the absence of transaldolase activity in M. gallisepticum, was experimentally shown by J.D. Pollack and M.V. Williams [31]. We assume that the resultant eritrose-4-phosphate in M. gallisepticum is utilized by D-fructose-6-phosphate D-erythrose-4-phosphate-lyase; this enzyme is not annotated for M. gallisepticum, but it is annotated for another Mycoplasma species (M. fermentans). We believe that this activity should be assigned for M. gallisepticum. This is a way to implement the nonoxidative reactions of the pentose phosphate pathway for M. gallisepticum.

Among the detected metabolites we found compounds that participate in the main metabolic pathways, such as glycolysis, amino acid, sugar, and amino sugar metabolism, synthesis of terpenoids, riboflavines, purine and pyrimidine metabolism, etc. We used the LC-MS/MS method to analyze 95 compounds (see Table 1), representing a substantial fraction of the >500 compounds of the total metabolome of three Mollicute species, M. gallisepticum, S. melliferum, and A. laidlawii. These compound were predicted by protein annotation, and performed by our lab in previous studies [3], [11]. In particular, the purine and pyrimidine metabolism maps were the most uniformly and densely filled maps with the identified metabolites (see Figures 1–3). We detected a variety of purine and pyrimidine metabolism products: nitrogenous bases- adenine, thymine, guanine, xanthine, hypoxanthine, uracil, cytosine; their nucleosides and deoxynucleosides and some of their mono-, di-, triphosphate nucleotides and deoxyribonucleotides. It should be noted that we did not consider inosine mono- and dinucleotide, as according to V.M. Boer et al., this compound is not detectable, as it can be confused with peak interference of ADP and AMP [32]. Expression of the annotated proteins that are functionally associated with the metabolism of purine and pyrimidine was demonstrated in our previous studies [3], [11]. In the S. melliferum metabolome, we did not detect deoxyuridine, dTDP, XTP, xanthosine, 2-deoxyinosine 5-phosphate; however, these compounds have been detected in M. gallisepticum and A. laidlawii. Among M. gallisepticum and A. laidlawii metabolites, we did not identify inosine and dTTP, respectively.

There are many nutrient carriers in the Mycoplasma proteome, so the description of membrane fluxes and the discovery of exogenous metabolites acquired by the membrane transport is an important issue in metabolome research. Carbohydrates and their derivatives (such as glycolysis metabolites; see Figures 1–3) including sedoheptulose-7-phosphate, D-ribose-5-phosphate, D-mannitol 1-phosphate/D-sorbitol 1-phosphate, fructose-1,6-bisphosphate, deoxy-D-ribose-1-phosphate, 5-phospho-alpha-D-ribose-1-diphosphate, 3-phospho-D-glycerate, phosphoenolpyruvate, and n-acetyl-D-galactosamine-6-phosphate/n-acetyl-D-glucosamine-6-phosphate/N-Acetyl-D-mannosamine 6-phosphate were detected in all three species. We detected deoxy-D-ribose-1-phosphate in M. gallisepticum and A. laidlawii metabolome, while the peak of this compound was considered to be peak interference according to V.M. Boer et al. [32]. We detected n-acetyl-D-galactosamine-6-phosphate and beta-D-fructose-1–6-bisphosphate in the A. laidlawii metabolome, while 3-phospho-D-glycerate is a characteristic feature of the M. gallisepticum metabolome. The latter compound was also detected in M. pneumoniae [18]. Detection of phosphorylated sugar products (mannitol 1-phosphate) is in good agreement with proteogenomic annotation [3], [11] (PTS system mannitol-specific (MtlA)-like IIB domain protein MGA_1283) and with the identification of phosphorylated sugars in M. pneumoniae [18].

In all three bacteria, using both positive and negative ionization modes, we detected non-phosphorylated forms of mannitol/sorbitol/galactitol (sugars and some amino acids like leucine/isoleucine isomers cannot be differentiated using the HPLC-MS method, since they have particularly identical fragmentation spectra and retention times) and alpha-alpha-trehalose/maltose/cellobiose/sucrose/lactose.

Sugars are the most important energy source for the Mollicutes; their import in the cytoplasm is usually coupled with phosphorylation [11]. Here we directly demonstrate that mycoplasmas contain non-phosphorylated sugars. It was assumed that non-phosphorylated forms of carbohydrates can be accumulated from media or adsorbed to the cell surface [1], [33], [34], [35], [36]. Sugar ABC transporter systems which are not associated with phosphorylation were also annotated (MGA_1076, MGA_1077, MGA_1078 for M. gallisepticum, SPM_2645 S. melliferum). It cannot be ruled out, but it does seem unlikely that mycoplasmas store sugars to consume them during possible carbohydrate starvation.

We detected 17 of the 20 amino acids in the three Mollicute species. Their presence in the metabolome can be attributed to their exogenous nature and the fact that they are actively imported into the cells through specific transporters (permeases), since no amino acid synthesis enzymes have been annotated in these organisms [11]. Peaks in the MS spectra that corresponded to amino acids have the highest intensity. Only asparagine, alanine, and valine were not detected. In experiments employing the same equipment and another bacteria (not shown), we were able to detect these three amino acids. This suggests that the concentration of the three amino acids, which were not found in S. melliferum, M. gallisepticum and A. laidlawii total metabolome, was significantly lower than the concentration of the seventeen detected amino acids. Of note, in M. pneumoniae these three amino acids were detected [18]. Alanine is the most abundant amino acid in proteins and its absence in the metabolome could be explained by its rapid involvement into protein synthesis through aminoacyl-tRNA synthetase.

In M. pneumoniae riboflavin was detected by LC-MS [18]. We have detected intermediates of riboflavin biosynthesis, 5-amino-6-(5-phospho-D-ribitylamino)uracil, 5-amino-6-(5-phosphoribosylamino)uracil, FMN and FAD. Among the explored three species, only A. laidlawii proteogenomic annotation contains proteins responsible for the diaminohydroxyphosphoribosylaminopyrimidines conversions in addition to the bifunctional FAD synthetase/riboflavin kinase. However, in the S. melliferum and M. gallisepticum metabolomes 5-amino-6-(5-phosphoribosylamino) uracil mass-spectral peaks were reliably detected with a high intensity. This finding can indicate activity of a metabolic branch responsible for FMN biosynthesis from GTP in S. melliferum and M. gallisepticum.