Previously, in P. aeruginosa PAO1, we identified two types of mutants that resist infection by the dsDNA phage, PaoP5 (Figure 1A). One of these, PAO1r-1 has lost the O-antigen and can be easily identified via a brown colony phenotype caused by the accumulation of homogentisic acids (Shen et al., 2018). To attempt to identify a phage that bypasses this resistance mechanism, and was able to kill PAO1r-1, a panel of lytic phages was examined (Table 1). While PAO1r-1 was resistant to dsDNA phages, including PaP1 (Lu et al., 2013), PaoP5 (Shen et al., 2016), and PaP8 (Table 1), the dsRNA phage, phiYY, was able to lyse PAOr-1 and form clear plaques (Figure 1B).

As stated above, PAO1r-1 carries a deletion in galU and therefore lacks the O-antigen component of LPS, leaving the core oligosaccharides of LPS exposed on the cell surface (Choudhury et al., 2005; Le et al., 2014). Accordingly, phiYY is likely to utilize the LPS core oligosaccharide instead of O-antigen as the receptor to initiate infection (Figure 2). Because PAO1r-1 contains a large chromosomal deletion, a mutant containing a single-gene disruption of galU (PAO1ΔgalU), as well as complement strains restoring galU in both genetic backgrounds (PAO1r-1::galU and PAO1ΔgalU::galU), were examined for susceptibility to phiYY and PaoP5. As shown in Figure 1C, phiYY lysed PAO1r-1 and PAO1ΔgalU, but did not kill the galU complemented strains, indicating that loss of galU allows for phiYY infection. On the contrary, PaoP5 infected PAO1, PAO1r-1::galU and PAO1ΔgalU::galU, but not the PAO1ΔgalU mutant (Figure 1D), indicating that loss of galU prevents infection by PaoP5.

A phage adsorption assay was used to further investigate the binding of these phages to the bacterial strains. phiYY adsorbs to PAO1r-1 and PAO1ΔgalU with high efficiency, but cannot bind to PAO1 or the galU complement strains (Figure 1E). Meanwhile, phage PaoP5 efficiently adsorbs to PAO1 and the galU complement strains, but not PAO1r-1 or PAO1ΔgalU (Figure 1F). Together, these data strongly indicate that the receptor for phiYY is the core oligosaccharide, while the receptor for PaoP5 is O-antigen. Therefore, phiYY may infect P. aeruginosa mutants lacking an O-antigen that arise following infection by O-antigen-binding phages, such as PaoP5.

We previously identified PA1RG, a mutant of P. aeruginosa PA1, resistant to the dsDNA phage, PaP1, with a white colony phenotype (Li et al., 2018). This strain carries a C595T mutation in wzy, the B-band O-antigen polymerase, which results in a truncated O-antigen with only one copy of the normally-repeating sugar unit (Figure 2).

In this study, we isolated 5-phage-resistant PAO1 mutants with a white colony phenotype. Three out of these five isolates had mutations in wzy as detected by Sanger sequencing of the PCR fragment amplified from the isolates. Two mutants had a wzy C736G mutation and the third, designated PAO1w-1, contained a wzy C1075T mutation, which resulted in a premature stop codon.

PAO1w-1 was highly resistant to the phages PaP1, PaoP5, PaP8, and phiYY (Figure 3A). To attempt to isolate a mutant phage that is able to effectively infect PAO1w-1, 10⁷ plaque forming units (pfu) of PaoP5 was mixed with PAO1w-1, and dozens of mutant phages that overcame resistance and lysed PAO1w-1 were observed. Five mutant phages were selected, purified and sequenced (Table 2). All 5-phage isolates that broke resistance of PAO1w-1 contained a A715C mutation in orf75, which was likely to be responsible for the expanded host range (Figure 3B). orf75 is located between the tail fiber gene and the baseplate gene. Though it is not annotated by blastp, Orf75 was identified as a structural protein by SDS-PAGE and high-performance liquid chromatography – mass spectrometry (Shen et al., 2016). Thus, the product of orf75 is highly likely to be a receptor-binding protein that is associated with host range.

One of the 5 mutant phages, designated PaoP5-m1, was selected for further study. Interestingly, unlike its parent strain, PaoP5, which did not infect PAO1w-1 or a single-gene inactivation of wzy (PAO1Δwzy), PaoP5-m1 was able to adsorb and infect all of the PAO1-derived strains, regardless of the presence of full-length or truncated O-antigen (Figures 3C,D). To test the host range of PaoP5-m1 against a larger panel of PaoP5-resistant mutants, we selected 30 white colonies surviving PaoP5 infection across 3 biological replicates. Strikingly, PaoP5-m1 infected all white mutants collected (Figure 3E), indicating that PaoP5-m1 is an excellent phage to eliminate P. aeruginosa mutants with truncated O-antigen structures.

Interestingly, similar phage training was unable to generate a mutant phage that infected PAO1r-1, bearing a complete lack of O-antigen (data not shown). This is likely due to the fact that the structures of the O-antigen and core oligosaccharides are quite different, compared to the structural differences between the full-length and truncated O-antigen (Lam et al., 2011). Thus, although phage mutants can adapt rapidly to a truncated receptor structure, they cannot adapt to a completely novel receptor structure in such a short period of time (Schwartz and Lindell, 2017).

As the genotypes and phenotypes exemplified by PAO1r-1 and PAO1w-1 represented the two major types of resistant mutants which emerged following dsDNA phage treatment of P. aeruginosa, phiYY and PaoP5-m1 were included in a 5-phage cocktail we formulated to constrain the emergence of resistance during phage therapy of P. aeruginosa. In addition to phiYY and PaoP5-m1, the parent phage of PaoP5-m1, PaoP5, and 2 additional dsDNA phages with a wide host range (PaP1 and PaP8) were included in the phage cocktail. The effectiveness of this cocktail at killing P. aeruginosa was examined against a panel of strains that included the type strains PAO1 and PA1, the phage-resistant mutants PAO1-r-1 and PAO1-w-1, as well as 19 P. aeruginosa clinical isolates from seven Chinese hospitals (Yang et al., 2016). To maximize the diversity of the panel, the 19 clinical isolates were selected based on diverse Eric-PCR typing (Khosravi et al., 2016; Yang et al., 2016): two strains were selected from clusters 1, 4, and 5, while one strain was selected from each of the remaining 13 typing clusters (Figure 4).

The efficiency of plating (EOP) of each phage and the 5-phage cocktail was measured across the panel of 23 P. aeruginosa strains (Figure 4). EOP is more accurate than a simple dot plaque assay in determining phage sensitivity and host range, as the phage lysate is serially diluted to minimize the impact of other antimicrobial agents, such as lysin, within the lysate (Forti et al., 2018). Interestingly, phiYY was able to kill 12 of the strains on the panel, however the EOP was low. Each phage had a distinct host range, and no individual phage lysed all strains in the panel. As expected, the 5-phage cocktail had by far the widest host range and high EOP values.

To test the effects of the individual phages or the phage cocktail on a liquid culture of P. aeruginosa, and provide more detail regarding the lysis kinetics of each treatment, cultures of PAO1 or PA1 were infected with each phage or the cocktail, and the optical density (OD₆₀₀) was monitored over 5 h (Figure 5A). For PA1, which is sensitive to PaP1, the addition of PaP1 resulted in a decrease in the OD₆₀₀ of PA1 within 1 h after infection. Meanwhile, challenge with PaP8 did not significantly affect OD₆₀₀ compared to the no phage negative control, which is likely due to the low infection efficiency of PaP8 against PA1, as seen above in Figure 4. In PAO1, phage PaoP5 infection caused a decrease in OD₆₀₀ 1–2 h post-infection, and PaP8 could kill and inhibit PAO1 growth, as indicated by the relatively stable OD₆₀₀. When treated with the 5-phage cocktail, the OD₆₀₀ of both the PAO1 and PA1 cultures decreased about 1 h after phage infection, indicating that the phage cocktail was effective in lysing liquid cultures of both P. aeruginosa strains, and it did so in a similar timeframe as the challenge with the single, effective phages.

The capability of phages to reduce biofilms formed by P. aeruginosa PA1 or PAO1 was examined using crystal violet staining. Following 24 h of biofilm formation by P. aeruginosa strains on 96-well plates, phages were applied individually or in the 5-phage cocktail. Plates were incubated for 4 h, at which point the biofilms were stained with crystal violet. Challenge with the phage cocktail caused a significant reduction in the biofilm biomass of both PA1 and PAO1 (Figure 5B), and eliminated biofilms with a slightly higher efficacy compared to that of challenge using the single, effective phage.

To determine whether the 5-phage cocktail inhibits the emergence of phage-resistant mutants, P. aeruginosa PAO1 or PA1 was mixed with a single phage or the phage cocktail. When treated with a single phage, the OD₆₀₀ of PAO1 and PA1 suffered an initial decrease during the first few hours. However, both strains re-grew to high densities after 12–24 h of incubation, most likely due to the growth of phage-resistant mutants. On the other hand, when treated with the 5-phage cocktail, the OD₆₀₀ of both strains remained low even after 48 h of incubation (Figure 6). This data strongly indicates that the 5-phage cocktail not only efficiently kills P. aeruginosa, but also prevents the emergence of phage-resistant mutants in vitro.

To test whether resistance to the 5-phage cocktail emerged after a longer period of time, the P. aeruginosa PAO1 culture containing the phage cocktail was incubated for an additional 7 days without the addition of fresh growth media (Figure 7A). In all three replicates, bacterial density finally began to increase after around 5 days (OD₆₀₀ = 0.5∼1.1), indicating that resistance to the phage cocktail had developed. These cultures were plated on LB agar and two colonies were isolated from each plate (Table 3). The EOP of each selected mutant was examined, and all six isolates were indeed resistant to all phages in the cocktail as no plaques were formed. To determine a genetic cause of the phage resistance, these six isolates, and wild type PAO1, were subjected to whole genome sequencing. The sequencing data revealed that all 6 isolates contained mutations in both wzy and migA (Table 3).

Many P. aeruginosa simultaneously synthesize multiple forms of lipopolysaccharide (Figure 2). These include the capped core glycoforms O-antigen-specific (OSA) and common polysaccharide antigen (CPA), as well as the uncapped core. The enzyme encoded by migA is responsible for the transfer of an L-rhamnose to glucose II of the core polysaccharide, and is required for the synthesis of uncapped core. Thus, the migA mutant lacks the L-rhamnose residue on the uncapped cores (Kocincova et al., 2012), and the wzy mutant lacks the OSA and produces “core + 1” LPS (Li et al., 2018). The sequencing data presented here implies that mutations in both wzy and migA are required for phage cocktail resistance. As expected, although both PAO1Δwzy and PAO1ΔmigA were sensitive to PaoP5-m1, a PAO1ΔwzyΔmigA double mutant was resistant to PaoP5-m1 (Figure 7B). This data implies that PaoP5-m1 may use either core antigen or OSA as receptors.

Among the six selected isolates resistant to the 5-phage cocktail, four had additional mutations. These mutations were located in the genes gmd, rmd or PA5455 (Table 3), all of three of which are involved in CPA synthesis (Lam et al., 2011; Hao et al., 2013). These mutations are less likely to be involved in the resistance to the phage cocktail seen in these strains, as the PAO1ΔwzyΔmigA double mutation was sufficient to confer resistance to the phage cocktail.

The bacterial strains and phages in this work are listed in Table 1. P. aeruginosa strains were grown on Luria-Bertani (LB) broth at 37°C. When required, gentamicin (50 μg/ml), or tetracycline (35 μg/ml) were used at a final concentrations in LB broth as described below. To completely remove bacteria, dsDNA phages were treated with chloroform, while dsRNA phage was filtered multiple times through 0.22 μm filters (Millipore), because phiYY is chloroform sensitive. To generate the phage cocktail, 5-phages with the same titer were mixed to a final titer of 10⁹pfu/ml.

The process of isolating phage-resistant mutants and calculating the frequency of resistance has been described in detail previously (Shen et al., 2018). PAO1r-1 was previously isolated, tested and sequenced (Shen et al., 2018). To isolate a PAO1-derived white-phenotype mutant PAO1w-1, PAO1 was infected with PaoP5 and immediately plated on LB agar plates for 24 h. Then, the white mutants were isolated. The wzy gene was PCR amplified with primers listed in Table 2, and the PCR products were sequenced to identify the mutation site in wzy.

The knockout and complementation of galU and wzy were performed as previously described (Le et al., 2014; Li et al., 2018). Briefly, to complement galU in PAO1r-1 and PAO1ΔgalU, the galU gene was PCR amplified using primers galU–C-F and galU–C-R, and the PCR product was digested by BamHI/PstI, and cloned into the BamHI/PstI digested plasmid pUCP24 to generate pucp-galU. Then, pucp-galU was electroporated into PAO1r-1 or PAO1ΔgalU. The sample approach was applied to complement wzy in PAO1w-1 and PAO1Δwzy with primers Wzy–C-F and Wzy–C-R.

To make insertional deletion of wzy in PAO1 and PAO1ΔmigA, a fragment within wzy was amplified with primers Wzy-K-F and Wzy-K-R, and the PCR product was digested by BamHI/EcoRI, and cloned into the BamHI/EcoRI digested plasmid pEX18Gm to generate plasmid pEX-wzy. Then, pEX-wzy was electroporated into PAO1 or PAO1ΔmigA to generate insertional mutant.

A bacteriophage adsorption assay with various P. aeruginosa strains was performed according to a previously described protocol (Le et al., 2014). Briefly, the log phase bacterial cultures were harvested and resuspended in LB broth with an OD₆₀₀ of 0.5. Phage was then added at an MOI of 0.01, and the adsorption proceeded at 37°C for 5 min. Then, 1 ml samples were collected and centrifuged at 16,000 × g for 1 min. The supernatant was filtrated using 0.22-μm-pore-size filters (Millipore). Then, the phage titer in the supernatant (t1) and the original phage stock (t0) were determined using double-agar plating assays. The phage adsorption rate was calculated as (t0−t1)/t0. The values of adsorption rate shown in the bar graph are the means and standard deviations are the error bars from three biological replicates.

The EOP of each phage isolate and the 5-phage cocktail on P. aeruginosa strains was determined according to a previously described protocol (Forti et al., 2018). 5 μl of serial 10-fold dilutions of phage were spotted on double layer agar plates, on which a specific bacterial host was spread in the upper soft agar. The number of plaques observed after overnight incubation were compared to the number obtained on sensitive strain PAO1, PA1 or PAO1r-1. The phage spot assay is similar to the EOP assay. Mix 200 μl of bacterial culture with 4 ml of soft agar and pour in the agar plate. Then drop 1 μl of phage on the soft agar and observe the formation of plaque after overnight incubation.

The process of phage training to break resistance has been described previously (Le et al., 2013). Briefly, ∼10⁷ pfu of phage PaoP5 was mixed with 200 μl of log phase P. aeruginosa strain PAO1 (OD₆₀₀ = 0.5) and plated in a double-layer plate. Dozens of plaques appeared after overnight culture. Five clear plaques were randomly selected and transferred into the LB medium. After serial 10- fold dilutions, the plaque assay was repeated with 10 μl of each dilution to obtain well-separated plaques. The same procedure was repeated twice to purify each mutant phage. After purification of mutant phage, genomic DNA was extracted as previously described (Le et al., 2013). Subsequently, the whole region encoding the structural proteins (Orf62 to Orf 88) was amplified by PCR using the primers indicated in Table 2. PCR amplicons were then purified and sequenced using Sanger technology. The mutation site was determined by blast the sequencing data with PaoP5 genome (GeneBank accession number KU297675).

Crystal violet staining was used to monitor biofilm disruption (Forti et al., 2018). An overnight culture of P. aeruginosa was diluted to 0.02 OD₆₀₀ in LB broth in 96-well polystyrene microtiter plates, which were then incubated at 37°C for 24 h. The broth was removed and the wells were washed with 200 μl of LB. Then, 200 μl of LB or LB containing phage or phage cocktail was added, and incubated for 4 h at 37°C. Then, crystal violet staining was applied as previously described (Forti et al., 2018). Three biological replicates were performed.

100 μl of phage cocktail was added into 5 ml exponential phase PAO1 (OD₆₀₀ = 0.2). The culture was incubated at 37°C for 7 days with shaking, and the OD₆₀₀ was monitored.

Bacterial genomic DNA was extracted from six mutants which were resistant to the phage cocktail and wild type PAO1 using the UNlQ-10 Column Bacterial Genomic DNA Isolation Kit (Sangon Biotec), and then sequenced using an Illumina Hiseq 2500 platform (∼1 Gbp/sample). Fastp (Chen et al., 2018) was used for adapter trimming and quality filtering after de-multiplexing the raw reads. Mutations were identified in clean reads using Breseq (Barrick et al., 2014) with PAO1 (GenBank accession: NC_002516.2) as the reference genome. The sequence data is available in the NCBI Sequence Read Archive under SRA accession number PRJNA517283.

The statistical analysis was performed using One-way ANOVA or student’s t test. A P value < 0.05 was considered as statistically significant.