To characterize the PAP2 enzymes from H. pylori (LpxE, HP0350, HP0851 and LpxF), the corresponding genes were cloned on the pTrcHis30 expression vector under the control of a strong IPTG-inducible promoter (Table 1). The recombinant N-terminally His-tagged proteins were overproduced in E. coli C43(DE3) cells. The integral membrane proteins were extracted from membranes via their solubilization with n-dodecyl-β-D-maltoside (DDM) detergent and the PAP2 proteins were purified by affinity chromatography using Ni²⁺-NTA agarose beads (Materials and Methods). Due to the difficulty in getting high expression levels of these membrane proteins in E. coli, they could not be purified to homogeneity. Nevertheless, LpxE, HP0350 and HP0851 were enriched to a high level as judged from SDS-PAGE analysis (Fig 1A), while LpxF could not be visualized by Coomassie blue staining. However, LpxF was in the purified samples as confirmed by western blot analysis (Fig 1B). We then measured the UppP activities present in these purified solutions. Considering the niche of H. pylori, which ranges from the human stomach with an acidic pH to the epithelial interphase with a neutral pH, we measured enzymatic activities on a large range of pHs (Fig 1C).

The uncharacterized HP0350 protein did not catalyze C₅₅-PP dephosphorylation even under prolonged incubation time and high protein concentration. LpxE displayed an UppP activity of 900 nmol/min/mg at an optimal pH of 7.4, while HP0851 exhibited a 6.7-fold higher UppP activity of 6039 nmol/min/mg at an optimal pH of 5. LpxE displayed UppP activity in vitro in addition to its role as lipid A 1-phosphate phosphatase [19]. Considering the highest activity of HP0851, this protein may account for a large part of C₅₅-P (re)generation in vivo. LpxF was shown to act as a lipid A 4’-phosphate phosphatase [19]. In this study, we also detected a low UppP activity for LpxF (Table 2 and Fig 1C). This activity is unlikely to arise from contaminants since HP0350, which was purified using the same methodology, exhibited no activity as compared to LpxF.

To further address the contribution of each PAP2 protein in the global UppP activity in H. pylori, we generated the four corresponding single mutants in H. pylori N6. All four mutants were readily obtained showing that none of these proteins is essential for survival of H. pylori in vitro. We prepared DDM-solubilized membrane extracts from exponentially growing wild-type and mutant cells and we measured the residual UppP activity present in these extracts (Fig 2). The UppP activities present in membranes of hp0350, lpxE and lpxF single mutants and wild-type strain were very similar. In contrast, the UppP activity decreased in hp0851 membranes to about 10% of residual activity as compared to the wild-type. Thus, these data confirmed the major contribution of HP0851 in C₅₅-PP recycling in C₅₅-P.

The simultaneous inactivation of bacA, pgpB and ybjG is lethal in E. coli. The BWTsbacA strain is a thermosensitive conditional triple mutant (ΔbacA, ΔybjG, ΔpgpB) containing an ectopic copy of bacA on a plasmid whose replication is impaired at 42°C [7]. This mutant accumulates soluble PGN precursors and lyses after a shift from 30°C to 42°C, due to the depletion of the pool of C₅₅-P that arrests cell-wall synthesis. The ability of the PAP2 proteins from H. pylori to restore the growth of BWTsbacA at the restrictive temperature was tested using the pTrcHis30-based plasmids previously used for protein purification (Table 3). The hp0350 gene was unable to complement BWTsbacA strain even in the presence of 1 mM IPTG. The lpxF gene was also unable to complement in the absence of inducer and was found to be toxic in the presence of IPTG as no growth was observed either at 30°C or at 42°C. In contrast, lpxE and hp0851 genes complemented BWTsbacA without the need of inducer, indicating that a basal level of the corresponding proteins allows a supply of C₅₅-P that is appropriate for optimal growth of E. coli. The overproduction of LpxE and LpxF in E. coli, due to the addition of IPTG, was lethal possibly due: 1) to interference with LPS biosynthesis, since the modifications they catalyze do not normally exist in E. coli and likely generate cytotoxicity, and/or 2) to accumulation of large amounts of membrane proteins. These complementation assays perfectly corroborate the previous biochemical data, further demonstrating that LpxE and HP0851 act as the major and perhaps the sole C₅₅-PP phosphatases in H. pylori. Hence, we renamed HP0851 to HupA (Helicobacter UppP and PGPase A).

To address whether LpxE and HupA are the only C₅₅-PP phosphatases in H. pylori, we attempted to construct a lpxE/hupA double mutant. However, we failed to generate this strain suggesting that co-inactivation of both genes is lethal. We then performed transformation efficiency assays to test the capacity of each PAP2 from H. pylori to complement this apparent lethality. We generated four strains deleted for hupA and carrying a copy of one PAP2 encoding gene under the control of an IPTG-inducible promoter on the pILL2150 vector. We then transformed these cells with the Topo TAΔlpxE plasmid in order to replace lpxE by a gentamycin resistance cassette. The transformed H. pylori population was diluted and spread on normal (total number of bacteria) or selective (ΔlpxE recombinants) plates to measure the transformation efficiency expressed in cfu/μg of Topo TAΔlpxE plasmid (Table 4). LpxF and HP0350 were unable to complement the lpxE/hupA double mutant as no recombinant was obtained even in the presence of IPTG. In contrast, LpxE and HupA complemented the double mutant in the presence of IPTG. These data excluded LpxF and HP0350 as bona fide UppP and confirm that only LpxE and HupA are major UppPs in H. pylori.

H. pylori infects the stomach and persists in the mucosa during years due to the expression of multiple virulence factors. Persistence also requires a resistance towards CAMPs, which are secreted by the host [22]. To evaluate the involvement of PAP2 proteins in CAMPs resistance, we used polymyxin B as a surrogate for CAMPs [23]. The modifications generated by LpxE and LpxF through their lipid A 1- and 4’-phosphate phosphatase activities promote resistance to different CAMPs and they further confer host innate immune system evasion [19]. We confirmed the increased sensitivity already described in [19] for the lpxE and lpxF mutants (32- and 128-fold, respectively, Table 5). The hp0350 mutant did not show any increase of polymyxin B sensitivity, while the sensitivity of hupA mutant increased by four-fold as compared to the wild-type strain. The polymyxin B sensitivity of hupA mutant was fully restored upon complementation with an ectopic copy of hupA gene.

As already mentioned, LpxE and LpxF modify lipid A structure in H. pylori. We then investigated whether the four-fold decrease in polymyxin B resistance of hupA mutant was a consequence of an altered lipid A structure. LpxE exhibits UppP activity while also acting as a lipid A 1-phosphate phosphatase. We hypothesized that, in the absence of HupA, LpxE has to cope with this very low UppP activity. This hypothesis predicted the presence of a mixture of lipid A species in hupA mutant with lipid A 1-phosphate together with the usual lipid A 1-PE. The resulting rise in net negative charges at the outermost surface of the bacterium could then account for the increased sensitivity towards polymyxin B.

To test this hypothesis, the lipid A from wild-type, hupA mutant and hupA mutant transformed with pILL2150 hupA plasmid were extracted and analyzed by mass spectrometry. As shown in Fig 3A–3C, the main form of lipid A present in wild-type strain was the tetra-acylated lipid A with a PE group at position 1 and no phosphate group at position 4’, as described [19]. Two additional minor species were observed, a penta-acylated lipid A with PE at position 1 and no phosphate at position 4’ and a hexa-acylated lipid A with PE at position 1 and with phosphate at position 4’. In hupA mutant and its complemented derivative, the lipid A profiles were very similar to that of the wild-type strain. We then concluded that the moderate decrease in polymyxin B resistance in hupA strain was independent of the lipid A structure. In parallel, we confirmed the roles of LpxE and LpxF (Fig 3E and 3F) while we show that HP0350 is not involved in lipid A modifications (Fig 3D).

The maximal UppP activity of LpxE was reached at pH 7.4 (Fig 1) and all complementation assays were performed at neutral pH. H. pylori resumes growth in acidic media only after buffering the environment to a pH above 6 thanks to the urease enzyme [24], which precludes any assays at acidic pH. However, in mouse colonization, the natural environment of H. pylori is mainly acidic, ranging from 2 in the lumen to 5–6 in the mucus layer. But at low pH, we noticed that the in vitro activity of LpxE drastically decreased by 43-fold (from 900 to 21 nmol/min/mg), while that of HupA increased by 1.7-fold (from 3493 to 6039 nmol/min/mg) (Table 2). Therefore, LpxE may be unable to fully complement the reduced UppP activity in the hupA mutant in an acidic environment. This issue was then addressed by mouse colonization assays. The ΔhupA mutation was first introduced into the mouse-adapted strain H pylori X47 and the kinetics of colonization of wild-type and hupA strains was followed by sacrificing mice after 1, 4, 7, 15 and 32 days after bacterial inoculation. Seven mice per group were sacrificed in two independent experiments and Fig 4 illustrates the CFU/g of stomach in a time course. The hupA mutant was unable to colonize the stomach neither at early or later stages after inoculation, showing therefore that HupA is absolutely essential for viability of H. pylori in vivo, in sharp contrast to in vitro where neither of the four PAP2 mutants was affected in growth (Fig 5).

HupA is an orthologue of PgpB from E. coli, which is a bifunctional enzyme acting as a minor UppP and being largely involved in phospholipid biosynthesis through the dephosphorylation of PGP in PG. In E. coli, the latter activity is also provided by two other integral membrane proteins named PgpA and PgpC, which are unrelated to the PAP2 superfamily [10,11,25]. One putative gene encoding a PgpA homolog was identified in the genome of H. pylori, hp0737, while no PgpC encoding gene was found. The hp0737 was cloned on a pTrcHis30 vector and the N-terminal-His tagged protein was expressed in E. coli C43(DE3) cells and purified from membranes to high homogeneity in DDM micelles (S1A Fig). In contrast to the PAP2 enzymes, PgpA enzymes are Mg²⁺-dependent, which was confirmed for HP0737 that presented an optimal Mg²⁺ concentration of 6 mM (S1B Fig). Its PGP phosphatase activity was then fully confirmed in vitro with a specific activity of 1138 ± 174 nmol/min/mg. Noticeably, HP0737 did not display any significant UppP activity and the plasmid carrying hp0737 gene did not restore the growth of E. coli BWTsbacA strain at 42°C. Considering the activity of HP0737 both in vivo and in vitro, this protein was renamed PgpA. The pgpA null mutant was readily generated by replacement with a resistance cassette (Table 1). These disagree with a previous study in which pgpA was described as an essential gene [26]. Our data further suggested the existence of one or several other PGP phosphatases.

We then assessed whether the PAP2 proteins from H. pylori are also involved in the synthesis of PG. DDM-solubilized membrane extracts obtained from wild-type and mutant cells (lpxE, hp0350, hupA, lpxF and pgpA) were assayed for their PGP phosphatase activity. This activity was measured in the absence and presence of 6 mM Mg²⁺ (Fig 6A). A drastic decrease of the PGP phosphatase activity in the hupA mutant as compared to the wild-type strain was observed, while the other mutants displayed similar activities as the control. Under these conditions, HupA accounted for 98% of the PGP phosphatase activity in the membrane of H. pylori.

To further confirm the involvement of HupA in the biosynthesis of PG, we also performed complementation assays using the conditional BWPGPTs E. coli strain and the different pTrcHis30-based plasmids. Like the BWTsbacA strain, the BWPGPTs is a thermosensitive triple mutant (ΔpgpA, ΔpgpB, ΔpgpC) containing an ectopic copy of pgpB on a plasmid whose replication is impaired at 42°C. LpxE, HupA and PgpA fully restored the growth at 42°C of this thermosensitive strain without IPTG, while LpxF and HP0350 were unable to complement (Table 6). Thus, LpxE, HupA and PgpA carry enough of PGP phosphatase activity to support growth of the BWPGPTs strain.

The apparent PGP phosphatase activity of HupA and LpxE in vivo could explain why pgpA inactivation did not lead to a lethal phenotype. To further decipher the role of PAP2 enzymes in the biosynthesis of PG in H. pylori, we tried to generate mutant strains inactivated for hupA and pgpA but we failed, while a double mutant lpxE/pgpA was readily obtained. These results suggest that HupA and PgpA are the only PGP phosphatases able to sustain growth of H. pylori in vitro.

Since the HupA and LpxE accept very dissimilar lipidic substrates in vivo, we further analyzed the substrate specificity of PAP2 enzymes in vitro (Fig 6B). Again, HP0350 had no visible phosphatase activity on any of the tested substrates. HupA was the most active phosphatase using all substrates tested except phosphatidic acid and the highest activity was by far obtained with the C₁₅-PP substrate. Structural and topology analyses of integral membrane PAP2 enzymes revealed that their active site residues are oriented towards the periplasm, which is likely the same for HupA. Small molecules such as C₁₅-PP are never exposed at the periplasmic site, therefore the C₁₅-PP should not be a natural substrate in vivo. Nevertheless, this analysis demonstrates that HupA accepts a large range of pyro- and monophosphate substrates, in particular C₅₅-PP and PGP. Noticeably, HupA and PgpA displayed very similar activities towards PGP. LpxE had similar substrate specificity as HupA, except for C₅-PP, and much lower activities were found. In contrast, LpxF only showed very low activity towards C₁₅-PP and PGP.

Since HupA showed broad substrate specificity, we wondered whether the polymyxin B sensitivity could be related to a general membrane permeability defect of the hupA mutant. We measured the MIC of the wild-type strain and its four PAP2 mutants to four different antimicrobial, one clinically relevant CAMP, colistin, and three large antibiotics, vancomycin, teicoplanin and daptomycin that do not cross the outer membrane. Table 7 illustrates the MICs to the four antimicrobials.

Absence of HupA, LpxE and LpxF affected specifically resistance to CAMPs without affecting the resistance to large antimicrobials suggesting that these three PAP2 only affect overall membrane charge and not permeability. Given the specific effect on CAMPs resistance and the broad substrate specificity of HupA, we next analyzed the phospholipid composition of the hupA mutant. As illustrated in S2 Fig, the wild-type N6 and its four PAP2 mutants showed a similar phospholipid profile.

Since, HupA and LpxE are functional in E. coli, we tested if the PAP2/BacA enzymes from E. coli are also functional in H. pylori. We performed complementation assays as previously described by measuring the transformation rate of lpxE inactivation in hupA mutant containing different plasmids encoding PAP2/BacA from E. coli. We then generated eight strains deleted for hupA and carrying a plasmid (pILL2150 or pILL2157 vector) bearing one of the four E. coli genes (bacA, pbpB, ybjG and lpxT) placed under the control of an IPTG-inducible promoter. The transgene is under control of a promoter from H. pylori in pILL2157, while it is under control of an E. coli promoter in pILL2150. Consequently, the transgenes in pILL2157 are likely more expressed in H. pylori as compared to those in pILL2150. Moreover, the pILL2157 promoter was previously found to be leaky in contrast to that of pILL2150 vector [27]. The transformation rates are summarized in Table 8. As expected, LpxT was unable to complement the lack of UppP activity in H. pylori whatever the expression level. At a moderate expression level (i.e. in pILL2150), only PgpB was able to complement the double lpxE/hupA mutant (1.08 × 10⁻⁵ transformants/cfu/μg DNA topoTAΔlpxE) in the presence of IPTG. In contrast, at a higher level of expression (i.e. in pILL2157), BacA, PgpB and YbjG were able to complement the double mutant both in the presence and in the absence of inducer. Therefore, even though BacA does not belong to the PAP2 super-family, and H. pylori does not possess UppP of the BacA type, this enzyme was functional in H. pylori.

Animal experiments were done according to European (Directive 2010/63 EU) and French regulation (Décret 2013–118) under the authorized protocol CETEA 2014–072 reviewed by the Institut Pasteur Ethical Committee (registered as number 89 with the French Ministry of Research). The experimental protocol was also approved by the French Ministry of Research under the number APAFIS#11694–2017100510327765 v2.

The bacterial strains and plasmids used in the study are summarized in Table 1. Precultures of H. pylori were started from glycerol stocks routinely stored at -80°C, plated onto 10% horse blood agar medium supplemented with an antibiotic-antifungal mix [19] and incubated at 37°C for 24 h in a microaerobic atmosphere (6% O₂, 10% CO₂, 84% N₂). The glycerol storage media is composed of 25% glycerol, 38% Brain Heart Infusion liquid (BHI) (Oxoid) and 37% sterilized water. Amplification of the preculture was performed in the same conditions as precultures in new plates at 37°C for 24 h in a microaerobic atmosphere. Liquid precultures were started from amplification plates and inoculated into BHI (Oxoid) supplemented with 10% fetal bovine serum (FBS) incubated at 37°C overnight in a microaerobic atmosphere. Liquid cultures of H. pylori were started from overnight liquid culture and inoculated into BHI (Oxoid) supplemented with 10% fetal bovine serum. In general, liquid cultures of H. pylori were grown to an OD_600nm of ~1.0 at 37°C under microaerobic conditions with shaking. Otherwise indicated, E. coli was routinely grown at 37°C in 2YT broth using standard conditions.

A non-polar kanamycin cassette was digested out of plasmid pUC18-Km2 [30] using BamHI and KpnI and ligated into the PCR products of the 5’and 3’ flanking regions of genes lpxE, hp0350, hupA, lpxF and pgpA using standard cloning techniques. The oligonucleotides used for the PCR amplification are described in S1 Table. The generated plasmids, TopoTA ΔlpxE:kan, TopoTA Δhp0350:kan, TopoTA ΔhupA:kan, TopoTA ΔlpxF:kan and TopoTA ΔpgpA:kan were used to create the corresponding null mutants in H. pylori N6 and/or X47 by natural transformation. Similarly, a non-polar gentamycin cassette was digested out of plasmid pUC18-Gm [31] using BamHI and KpnI to generate TopoTA ΔlpxE:Gm.

For the expression of PAP2, BacA and PgpA encoding genes from E. coli or H. pylori, the genes were amplified by PCR using appropriate primers (S1 Table) and cloned into the pILL2150 or pILL2157 vectors (for expression in H. pylori) or in pTrcHis30 vector (for expression in E. coli).

E. coli C43(DE3) cells carrying pTrcHis30-based plasmids were used for the overproduction of N-terminal His₆-tagged proteins. Cells were grown in 1 liter 2YT-ampicillin at 37°C until the A_600nm reached 0.9, when the expression was induced by the addition of 1 mM IPTG and the growth was continued for 3 h at 37°C. Cells were harvested by centrifugation at 4°C for 20 min at 4000 × g, were washed and finally resuspended in buffer A (20 mM Tris-HCl pH 7.4, 400 mM NaCl, 10% glycerol) before disruption by sonication with a Vibracell 72412 sonicator (Bioblock). The suspension was centrifuged at 4°C for 1 h at 100,000 × g to harvest the membranes, which were washed three times in buffer A. The membranes were finally resuspended in buffer A supplemented with 2% DDM for solubilization at 4°C for 2 h with gentle agitation. Solubilized membranes were loaded on nickel-nitrilotriacetate agarose (Ni²⁺-NTA-agarose, Qiagen) equilibrated in buffer A supplemented with 0.2% DDM and 10 mM imidazole. The column was washed with increasing imidazole concentration using the same buffer and the elution was performed with 2 ml of buffer A supplemented with 0.2% DDM and 200 mM imidazole. Desalting of samples was carried out using PD-10 desalting columns (GE Healthcare) and buffer A supplemented with 0.1% DDM. Protein concentrations were determined with the QuantiProBCA assay kit (Sigma) or by densitometry analysis of the gel when appropriate.

H. pylori wild-type and single mutant strains were grown at 37°C in BHI medium (200 ml culture) up to exponential phase. Cell free extracts, membrane free cytosol, and washed membranes were prepared as previously described [22]. Cells were harvested by centrifugation, washed and finally resuspended in 20 mM Tris-HCl, pH 7.4, 200 mM NaCl (buffer B). After disruption by sonication, membranes were pelleted by centrifugation at 177 420 × g and resuspended in buffer B supplemented with 2% DDM for solubilization during 1.5 h in the cold. The solubilized proteins were recovered by centrifugation at 177 420 × g and conserved at -20°C before activity measurement.

H. pylori wild-type and four single mutant strains were grown at 37°C in BHI medium (50 ml culture) up to exponential phase. Lipid extraction was performed using a new protocol (Nozeret K et al. manuscript submitted). For thin-layer chromatography (TLC) analysis of phospholipids, the dried lipid extracts and controls were dissolved respectively in 500μl and 350μl of chloroform. 10μl of the solution was spotted onto a TLC silica gel 60 plate. The TLC plate was developed in tanks equilibrated with dichloromethane- methanol-water (65:28:4 [vol/vol]). After drying the plate, phospholipids were visualized with molybdenum blue reagent (Sigma).

The C₅₅-PP and PGP phosphatase assays were carried out in a 10 μl reaction mixture containing 20 mM Tris-HCl, pH 7.4, 10 mM β-mercaptoethanol, 150 mM NaCl, 0.2% DDM, 50 μM [¹⁴C]C₅₅-PP or 50 μM [¹⁴C]PGP (900 Bq) and enzyme. MgCl₂ was added at 6 mM in the reaction mixture when PgpA activity was measured. Appropriate dilutions of purified phosphatases, or of membrane extracts, were used to achieve less than 30% substrate hydrolysis. The reaction mixture was incubated at 37°C for 10 to 30 min and the reaction was stopped by freezing in liquid nitrogen. The substrates and products were then separated and quantified by thin layer chromatography (TLC) analysis, as previously described for C₅₅-PP [5] and PGP [11] hydrolysis. When the phosphatase activity was investigated at various pH values, buffering was achieved in sodium acetate (pH 3–7), Tris-HCl (pH 7–9) or sodium carbonate buffer (pH 9–11).

The phosphatase activity towards other non-radiolabeled substrates: C₅-PP, C₁₅-PP, diacyl(C8) glycerol-PP (DGPP) and phosphatidic acid (PA), was determined by measuring the amount of released inorganic phosphate during catalysis. The reaction mixture was as described above with 50 μM substrate in a final volume of 50 μl. After 10 min of incubation at 37°C, the reaction was stopped by the addition of 100 μl of Malachite green solution (Biomol green, Enzo Life Sciences), and the released phosphate was quantified by measurement of the absorbance at 620 nm.

The E. coli thermosensitive strains BWTsbacA and BWPGPTs, carrying multiple chromosomal gene deletions and harboring a bacA- or pgpB-expressing plasmid, respectively, whose replication is impaired at 42°C, have been previously described [7]. These strains were transformed by the pTrcHis30-based plasmids encoding the different H. pylori PAP2 and PgpA encoding genes. Isolated transformants were subcultured at 30°C in liquid 2YT medium supplemented with 100 μg/ml ampicillin and, when the absorbance of the culture reached 0.5, the cell suspension was diluted to 10⁻⁵ in 2YT medium and 100 μl aliquots were plated onto two ampicillin-containing 2YT agar plates which were incubated at either 30°C or 42°C for 24 h. The colony forming units (CFU) were numerated on each plate and the functional complementation of the thermosensitive mutants was evaluated by the capacity of the transformants to equally grow at both temperatures.

Precultures of H. pylori were started from glycerol stocks routinely stored at -80°C, plated onto 10% horse blood agar medium and incubated at 37°C for 24 h in a microaerobic atmosphere (6% O₂, 10% CO₂, 84% N₂). Amplification of the pre-culture was performed in the same conditions such as pre-cultures in new plates at 37°C for 24 h in a microaerobic atmosphere. 50 μl of suspension in BHI at OD_600nm = 20 were made until the amplification plate and mixed with 10 ng of Topo TAΔlpxE plasmid. The whole mixture was put on a non-selective plate onto 10% horse blood agar medium and incubated at 37°C for 24 h in a microaerobic atmosphere. The transformation spot was then diluted (10⁻¹ to 10⁻⁸). 50 μl of the non-diluted suspension and 10 μl of the 10⁻¹ to 10⁻⁴ dilutions were spread on 10% horse blood agar medium supplemented with chloramphenicol (4 μg/ml), kanamycin (20 μg/ml) and gentamycin (5 μg/ml) ± IPTG 1mM to estimate the number of transformants. The 10⁻⁵ to 10⁻⁸ dilutions were spread on non-selective plates containing 10% horse blood agar medium supplemented with chloramphenicol (4 μg/ml), kanamycin (20 μg/ml) ± IPTG 1mM to estimate the total number of bacteria. The CFU of all plates incubated at 37°C for 5 days in a microaerobic atmosphere were enumerated. The transformation rate was expressed by the number of transformants/total cfu/μg of DNA TopoTAΔlpxE.

Strains were grown routinely on amplification plates. Two ml of suspension in 0.9% NaCl at OD_600nm = 0.75 were made from the amplification plates and spread by inundation onto Mueller Hinton medium (Difco) supplemented with 10% of FBS and 2,3,5-triphenyltetrazolium chloride (TTC, Sigma) (40 μg/ml). Polymyxin B was diluted by serial dilutions of two (16384 μg/ml down to 0.5 μg/ml). Once the square plates with bacterial lawns were dried, 10 μl of each dilution of polymyxin B was dropped on and allowed to dry. All plates were then incubated at 37°C for 3 days in a microaerobic atmosphere. TTC is a non-toxic dye which colors in red the alive bacteria. MICs were determined as the lowest concentration of polymyxin B leading to a clear halo of inhibition.

Strains were grown routinely on amplification plates. Two ml of suspension in 0.9% NaCl at OD_600nm = 0.75 were made from the amplification plates and spread by inundation onto 10% horse blood agar medium. Once the square plates with bacterial lawns were dried, Etes, Biomérieux, with different antibiotics targeting the cell wall (Vancomycin, Teicoplanin, Daptomycin and Colistin) were put on plate and incubated at 37°C for 48 h in a microaerobic atmosphere. MICs were determined as the lowest concentration of antibiotics leading to a clear halo of inhibition.

OF1 female mice purchased from Charles River Laboratories aged 5 weeks were infected by gavage with feeding needles with X47 strain (2 × 10⁸ bacteria per mouse). Colonization rates were determined after 1, 4, 7, 15 and 32 days by enumeration of CFU per gram of stomach. Mice were euthanized with CO₂ and the stomachs were ground and homogenized in peptone broth. The samples were then diluted and spread on blood agar plates supplemented with 10 μg/ml of nalidixic acid, to inhibit the growth of resident bacteria from the mouse forestomach and 20 μg/ml of kanamycin for hupA mutant strain. The CFU were enumerated after 5 days of incubation under microaerobic conditions. The results of two independent colonization experiments (seven mice by cage) were pooled and a one tailed Mann-Whitney test was used to determine statistical significance of observed differences (GraphPad Prism v5.0 GraphPad Software, CA).

For isolation of lipid A, H. pylori cultures were grown to an OD₆₀₀ of ~0.6. Lipid A chemical extraction was carried out after mild acidic hydrolysis of LPS as previously described [32,33]. For visualization of lipid A by mass spectrometry, lipids were analyzed using MALDI-TOF (ABI 4700 Proteomic Analyzer) in the negative-ion linear mode similar to previously described [34,35]. Briefly, lipid A samples were dissolved in a mixture of chloroform-methanol (4:1, vol/vol), with 1 μL of sample mixed with 1 μL of matrix solution consisting of 5-chloro-2meracaptobenzothiazole (CBMT) (20 mg/mL) resuspended in chloroform-methanol-water (4:4:1, vol/vol/vol) mixed with saturated ammonium citrate (20:1, vol/vol), and 1 μL of sample-matrix mixture was loaded on to MALDI target plate.