Two chromosomal insertion inactivated mutants for the phzA1-G1 and phzA2-G2 gene clusters were constructed respectively in Pseudomonas sp. M18 and designated as M18ΔP1 and M18ΔP2 (Figure 1A). We first investigated the relationship between the expressions and regulation of two phz gene clusters by quantification analysis of cell growth and PCA production in the wild type strain M18 and the two mutant strains as shown in Figure 1B & 1C. The results indicated that M18ΔP1 and M18ΔP2 mutants experienced slight increases in the cell growth, as compared with the wild type strain M18. During the stationary phase, the cell growth of the phzA2-G2 inactivated mutant M18ΔP2 was the fastest among the three strains tested, while the phzA1-G1 mutant M18ΔP1 exhibited more rapid growth than the wild type strain M18, suggesting the possibility of a toxic inhibition effect on the cell growth created by certain PCA concentrations and the different amounts of PCA produced in these strains (Figure 1B). The PCA toxic effect on cell growth was confirmed when we quantified PCA production from the three strains, as shown in Figure 1C. It was found that PCA production from wild type strain M18 was almost 4-fold higher than that from the phzA1-G1 inactivated mutant M18ΔP1 and PCA production from the phzA2-G2 inactivated mutant M18ΔP2 was abolished completely, suggesting that PCA could not be produced from the gene cluster phzA1-G1 in the absence of PCA molecules produced from the phzA2-G2 gene cluster. Specifically, 20 mg/L PCA was found to be produced by the mutant M18ΔP1, which was only one-quarter of the PCA production detected from the strain M18, suggesting that the gene cluster phzA2-G2 could only produce a small amount of PCA and that the majority of PCA molecules were produced from the phzA1-G1 gene cluster in the strain M18. These results suggested that PCA molecules produced from the phzA2-G2 gene cluster could activate the expression of phzA1-G1 gene cluster to produce more PCA molecules in Pseudomonas sp. M18. We deduced that the expressions of the two phz gene clusters may represent a feedback amplification pattern.

Therefore, experiments were further carried out using the addition of exogenous PCA into cultures to confirm the above findings. As shown in Figure 1B, supplementing the cultures with exogenous PCA resulted in significantly inhibited growth of the three strains, especially for the wild type strain during the growth phase, indicating a toxic effect of PCA on cell growth. On the other hand, the addition of exogenous PCA could induce the two mutant strains to produce more PCA and stimulated the wild type strain M18 to produce a large amount PCA of 220 mg/L (Figure 1C). Taken together, our results suggested that there exists a PCA auto-induction regulatory mechanism involving expression of the phzA2-G2 gene cluster and an activation mechanism involving expression of the phzA1-G1 gene cluster. The increase of PCA production with exogenous PCA at 160 mg/L in M18ΔP2 and 70 mg/L in M18ΔP1 indicated a higher efficiency induction for phzA1-G1 cluster and a relatively lower efficiency induction for phzA2-G2 cluster, which again supported the function of a positive feedback loop involved in PCA production in Pseudomonas sp. M18 strain.

The activating function of PCA as a signaling molecule was examined in regard to its effect on which one transcriptional activity of the two phz gene clusters Total phz transcriptional level was measured and compared to the levels of phzA1-G1 and phzA2-G2, respectively, in the presence or absence of exogenous PCA by using quantitative real time PCR (QRT-PCR) method. As shown in Table 1, the relative phz gene expression levels obtained from the three strains without addition of exogenous PCA were much lower than those obtained with exogenous PCA addition, which verified the transcriptional induction function of PCA molecules for the expressions of the two phz gene clusters. Notably, the relative expression activities of phzA1-G1 and phzA2-G2 increased by 18.4- and 5.7- fold when the two M18ΔP2 and M18ΔP1 mutants were incubated in the presence of exogenous PCA, indicating a higher transcriptional potential of the phzA1-G1 gene cluster and a more robust transcriptional response for this gene cluster to the PCA molecules, when compared with that of phzA2-G2 cluster. Compared with the M18ΔP1 mutant, the phzA2-G2 transcript level could be induced to a much less extent with the addition of exogenous PCA molecules, suggesting the lower transcriptional potential of the phA2-G2 gene cluster and less robust auto-induction efficiency of this cluster. It could be deduced that the PCA produced from the phzA2-G2 cluster plays a signaling role to induce the expression of itself in a relatively less efficient manner, however to activate the expression of phzA1-G1 gene cluster more efficiently.

The different transcription activity and induction efficiency of the two phz gene clusters by PCA molecules instigated us to make a further investigation on the regulation of two gene clusters at a post-transcriptional level. The transcriptional start sites of each gene cluster, phzA1-G1 and phzA2-G2, were determined by a rapid amplification of 5′-cDNA element (5′-RACE) method and a long non-coding region of 338 bp and 201 bp was found between the transcriptional start point and the predicted translation start point in the two gene clusters, respectively (Figure 1A). Two transcriptional fusions, phz1‘-’lacZ and phz2‘-’lacZ, were constructed in pME6522, and called as pMP1C and pMP2C (Figure 2A). The β-Galactosidase activities from the two transcriptional fusions were measured both in wild type strain M18 and the two M18ΔP1 and M18ΔP2 mutants, respectively (Figure 2C). It was evident that β-Galactosidase activity from the phz1‘-’lacZ transcriptional fusion was much higher than that from the phz2‘-’lacZ whether in the wild type strain M18 or in the two phz mutants. Also, the phz1‘-’lacZ transcriptional activity was higher in the M18ΔP1 mutant than that in M18ΔP2, though much less than that in wild type strain M18. In contrast, the phz2‘-’lacZ transcriptional fusion expressed at a relatively lower level and did not show significant differences among the three strains. These data indicated that the phzA2-G2 gene cluster was transcribed less efficiently than phzA1-G1 gene cluster and the endogenous PCA produced from the phzA2-G2 gene cluster could induce the expression of phzA1-G1 gene cluster more efficiently at the transcriptional level. Moreover, phzA1-G1 gene cluster could be induced and expressed by some other unknown factor(s) in the M18ΔP2 mutant in the absence of endogenous PCA molecules.

The results were consistent with findings obtained from quantitative phz transcript analysis by QRT-PCR, but were not consistent with the PCA quantity produced in wild type strain M18 or in the two mutants, suggesting a repression mechanism involved in the phzA1-G1 transcript and not in the phzA2-G2 transcript exists at the post-transcriptional levels in strain M18. The two translational fusions of phz1‘-’lacZ and phz2‘-’lacZ named as pMP1L and pMP2L were further constructed in pME6015 (Figure 2B) and introduced into wild type strain M18 and the two phz mutants of M18ΔP1 and M18ΔP2, respectively. The β-Galactosidase activities from the two translational fusions were measured in the three strains, respectively, as shown in Figure 2D. As expected, the β-Galactosidase activity from pMP2L translational fusion was much higher in comparison with that from pMP1L translational fusion either in the wild type strain or in the M18ΔP1 and M18ΔP2 mutants, indicating that the phzA2-G2 transcript could be expressed efficiently at the translational level and activated less efficiently by endogenous PCA produced from phz gene cluster or the unknown factor(s) besides PCA molecules. However, the β-Galactosidase activity from translational fusion pMP1L was nearly completely blocked in the three strains, indicating that the efficiently transcribed phzA1-G1 transcript was poorly translated, even under the conditions of endogenous PCA induction in the wild type strain M18 and the mutant M18ΔP1. This finding suggested that there exists a powerful negative cis control mechanism located in the non-coding region of phzA1-G1, rather than in the phzA2-G2 transcripts, which could act as a repressor to block the translation from the phzA1-G1 transcripts.

The above results forced us to construct another three transcriptional fusions, pMP1aC pMP1bC and pMP1cC in pME6522 (Figure 3A), and to investigate the transcriptional activities of these fusions in the wild type and the two phz mutants. As shown in Figure 3B, when a region of 90 bp in length was recovered into the 5′-untranslated region (UTR), the β-Galactosidase activity resulting from the transcriptional fusion pMP1aC was 5-fold less than that from the transcription fusion pMP1C in the wild type strain. When a region of 337 bp in length was recovered into the 5′-UTR, the β-Galactosidase activity from pMP1cC fusion was 6-fold less than that from pMP1bC in the wild type M18, indicating that two negative control elements from +1 to +90 nt and from +255 to +337 nt were contained in the 5′-UTR of the phzA1-G1 transcript. The same trend was found for the expressions of all the transcriptional fusions in M18ΔP1 and M18ΔP2; however, when compared to that in the wild type strain, only about half of the β-Galactosidase activity from the transcription fusion pMP1C was detected in the M18ΔP1 and one-quarter in M18ΔP2, suggesting that some other unknown factor(s) in the mutants, besides PCA molecules, may be involved in the post-transcriptional or translational regulation of the phzA1-G1 transcript. The β-Galactosidase activities of pMP1aC and pMP1cC in strain M18ΔP1 increased 14.4-fold and 1.5-fold, respectively, compared with that in strain M18ΔP2, suggesting that PCA produced from the phzA2-G2 cluster was able to induce phzA1-G1 expression mainly through a mechanism involving the 5′-UTR regions from +1 to +90 nt; although the precise mechanism(s) by which the two cis-element domains regulate the phzA1-G1 expression flexibly at the post-transcriptional level remains unknown.

We predicted the secondary structures of the 5′-UTR from the phzA1-G1 gene cluster (Figure 4A). In order to find the conserved secondary structures with more accuracy, the 5′-UTRs of phzA1-G1 and phzA2-G2 in M18 genome with that in an outlier strain genome of P. aeruginosa PA7, were aligned using the blastn algorithm [35], revealing that the DNA sequence similarities were 79% and 84%, respectively. Using the RNA fold [36] web server, the base pairing probabilities were calculated and annotations with different colors as shown in Figure 4. The 5′-UTR folding free energy in the phzA1-G1 gene cluster was determined to be −109.7 kcal/mol. Furthermore, in order to show the 5′-UTR dynamics, three suboptimal local structures from +230 to +337 nt were also predicted (Figure 4B). The free energies for these three structures were found to be very close, which would be expected to introduce only a small energy barrier between alternate structures. The above results indicated that the 5′-UTR from +230 to +337 nt of phzA1-G1 may be a potential riboswitch and could change its structures easily to response to various environmental cues. The detailed mechanism(s) will be further investigated in future, by which the riboswitch variants in 5′-UTR of phzA1-G1 control self-expression.

We have previously reported that PCA production was negatively controlled by the global regulator GacA [27], [34]. To extend our investigations, here, we sought to determine whether PCA repression occurred at both of the two phz gene clusters or only at one of them by exploiting the known GacA function. The double inactivated mutants of gacA and phzA1-G1 or phzA2-G2 gene cluster were constructed in wild type strain M18 and designated as M18ΔGΔP1 and M18ΔGΔP2. PCA production and cell growth were measured in the two double mutants and the single gacA mutant M18ΔG (Figure 5A). Contrast with growth curves obtained for the three strains revealed that different amounts of PCA were produced in each, and that PCA production was completely abrogated in the M18ΔGΔP2 mutant. Interestingly, an almost parallel PCA level of 300 mg/L accumulated in both mutants of M18ΔGΔP1 and M18ΔG, indicating that the negative control of gacA on PCA synthesis occurred in the phzA2-G2 cluster, and not the phzA1-G1 cluster.

To identify whether the negative control capability of GacA activity on the expression of phzA2-G2 gene cluster occurred at the transcriptional or translational level, both the transcriptional fusion pMP2C and translational fusion pMP2L were delivered into the inactivated gacA mutant M18ΔG and the wild type strain M18. The transcriptional fusion level of the pMP2C was almost the same in the two mutants, while the translational fusion level of pMP2L in the gacA inactivated mutant M18ΔG was 2-fold higher than that in the wild type strain M18 (Figure 5B & 5C), indicating that the negative control of GacA activity on phzA2-G2 expression occurred at the post-transcriptional level.

As summarized in Figure 6, our overall findings describe a correlation between the expressions of two phz gene clusters and the negative control on phzA2-G2 expression by gacA activity in Pseudomonas sp. strain M18. It could be concluded that the concerted expressions of two phz gene clusters involves PCA induction and are regulated both at the transcriptional and post-transcriptional level by a feedback loop involving sequences in the 5′-UTR.

The bacterial strains and plasmids used in this study are listed in Table 2. E. coli were grown in Luria-Bertani (LB) medium. Pseudomonas sp. M18 and its derivatives were grown in King's medium B (KMB) containing peptone 20 g, glycerol 15 ml, K₂HPO₄ 0.392 g, MgSO₄ 0.732 g per litre, and pigment-producing medium (PPM) with peptone 22 g, glucose 20 g, KNO₃ 5 g per litre was used for PCA production. The antibiotics added in media were at the following concentrations (µg/ml): ampicillin (Ap) 100, spectimycin (Sp) 100, genamycin (Gm) 50, tetracycline (Tc) 120 for pseudomonads and Ap100 and Tc15 for E. coli. Routine incubation temperature was 37°C for E. coli and 28°C for Pseudomonas sp. M18 and its derivatives.

Restriction endonucleases, Taq, LA-Taq and Pfu DNA polymerase, DNA molecular mass markers, and other associated products, were used as recommended by the respective manufacturer (TaKaRa; MBI; Fermentas). Plasmid DNA was prepared on a small-scale using the MiniBEST plasmid purification kit, version 2.0 (TaKaRa). Genomic DNA was extracted and purified from Pseudomonas sp. M18 using an EZ spin column genomic DNA isolation kit (Bio Basiv, Inc). Restriction enzyme digestions, ligations and agarose gel electrophoresis were performed using standard methods. Restriction fragments were purified from agarose gels by DNA gel extraction kit (Axgen). The chemically-synthesized oligonucleotide primers used in this study were listed in Table 3.

Rapid amplification of 5′-cDNA element (5′-RACE) was performed to identify the transcriptional start sites for the two phz clusters by using Invitrogen's 5′-RACE system. Briefly, total RNA was isolated at the early exponential phase (OD₆₀₀ = 1.5) from Pseudomonas sp. M18 cultures using the Nucleospin RNAII kit (Macherey-Nagel) and treated with RQ1 RNase-free DNase (Promega). Gene specific primers P1GSP1 and P2GSP1 were designed and first strand cDNA were synthesized using RevertAid™ first strand cDNA synthesis kit (Fermentas); a homopolymeric tail was then added to the 3′-cDNA using terminal deoxynucleotidyl transferase (TdT) and dCTP. PCR was accomplished using nested gene-specific primers P1GSP2 and P2GSP2, a novel deoxyinosine-containing abridged anchor primer (AAP), and the poly(C) tailed cDNA as template. The 5′-RACE products were analyzed, purified and placed into individual pMD18T vectors (TaKaRa) to determine the transcriptional start sites of the two phz clusters by direct sequencing, respectively.

Two primer pairs, P1U-P1D and P2U-P2D (Table 3), were designed according to the nucleotide sequences located between the coding regions of phzA1 and phzB1 or phzA2 and phzB2 in the two phz gene clusters in Pseudomonas sp. M18. A 2.2 kb and a 1.7 kb DNA fragment was PCR amplified from strain M18 genomic DNA and confirmed by direct sequencing. After SacI-PstI digestion, the fragments were cloned into pEX18, a conjugatable counter-selective suicide plasmid to obtain recombinant plasmid pEX18P1 and pEX18P2 in E. coli SM10.

A 0.8 kb SmaI fragment containing the gentamycin (Gm) resistance cassette from pUCGm was inserted into the SmaI trimmed site of phzA1 and phzA2 gene for both plasmids pEX18P1 and pEX18P2, resulting in the recombinant constructs pEX18P1Gm and pEX18P2Gm, respectively, in E. coli SM10; the constructs were ultimately mobilized into Pseudomonas sp. M18 by biparental mating. The clones in which a double crossover had occurred were selected on plates containing Gm50, Sp100 and 5% (w/v) sucrose. The phzA1-G1 and phzA2-G2 chromosomally inactivated insertion mutants of M18ΔP1 and M18ΔP2 were selected for Gm-resistant (Gm^r) colonies followed by Tc-sensitive (Tc^s) screening and confirmed by PCR and sequencing.

All the primers used in the construction were listed in the Table 3. A 341 bp PCR fragment from −340 to +1 (relative to the transcriptional start point) containing the phzA1-G1 gene cluster promoter region and a 345 bp PCR fragment from −344 to +1 containing the phzA2-G2 promoter region was amplified respectively from strain M18 genomic DNA using two primer pairs, P1CU-P1CD and P2CU-P2CD. The products were then cloned into EcoRI-PstI digested pME6522 respectively to generate two transcriptional fusions of pMP1C and pMP2C. A 691 bp PCR fragment (from −340 to +351 which contained the promoter region and partially encompassed the phzA1 gene) and a 572 bp PCR fragment (from −344 to +228 which contained the promoter region along with a portion of the phzA2 gene) were amplified using two primer pairs, P1LU-P1LD and P2LU-P2LD. The products were then cloned into EcoRI-PstI digested pME6015 to generate two translational fusions of pMP1L and pMP2L.

Using the primer pairs P1CU-P1aCD, P1CU-P1bCD and P1CU-P1cCD, three fragments of 430 bp, 595 bp and 677 bp (from −340 to +90, +255 and +337, respectively) were PCR amplified and cloned into pME6522 to generate transcriptional fusion pMP1aC, pMP1bC and pMP1cC. All PCR fragments were amplified from strain M18 genome DNA and confirmed by direct sequencing.

Pseudomonas sp. M18 and its derivatives, M18ΔP1 and M18ΔP2, were grown in PPM medium to an OD₆₀₀ of 2.0–2.5 (exponential phase) and 3.5–4.0 (stationary phase). Total RNA was extracted from the cell pellet using a Nucleospin RNAII kit (MN), according to the manufacturers' instructions and including the optional DNase treatment step. The extracted RNA was used as template for cDNA generation, which was next applied to a random primed reverse transcriptase reaction (Fermentas, MBI) following the manufacturer's protocol and then used as template for quantitative PCR (Rotor-Gene 6000; Corbett Life Sciences) by means of the SYBR Green I detection system. The signal was standardized to rpoD (a house keeping gene) using the following equation: relative expression = 2^{−Δ(ΔCTsample-ΔCTstandard)}, where CT (cycle threshold) was determined automatically by the Rotor-Gene 6000 PCR software. Primers for QRT-PCR were designed using Primer5 software. Criteria for primer design were: a melting temperature of 58°C, primer length of 20 nt, and an amplified PCR product of about 200 bp. Samples were assayed in triplicate.

Two primer pairs, PA1U-A1D and PA2U-PA2D, were designed and based on distinctive sequence in the phzA1 and phzA2 genes in Pseudomonas sp. M18. The total transcriptional level of the two phz gene clusters was determined using the primer PCU-PCD designed from phzC, the phzA1 and phzA2 gene transcription level as representatives of the phzA1-G1 and phzA2-G2 transcripts, respectively, in Pseudomonas sp. M18. The constitutively expressed gene rpoD was used as the internal control to verify the absence of significant variation in cDNA levels for all samples. RealMasterMix (SYBR Green I; Tiangen, China) was used to carry out real-time PCR. PCRs were run with following program: one step of 1 min at 94°C, 40 cycles of 94°C for 15 s, 58°C for 20 s, and 68°C for 30 s. PCR analyses for each strain were repeated three times. The amount of target gene phzC, phzA1 and phzA2, normalized to the level of the reference rpoD and calibrated relative to the lowest of them, was calculated as a 2^−ΔΔCT.

After 12 h culture, during the exponential phase (OD₆₀₀ = 2.0∼2.5), purified PCA compound (20 mM dissolved in ethanol) was added to attain a final concentration of 0.1 mM; the analytical pure ethanol solvent was used as control. Following PCA addition, the culture was further incubated for approximately 60 h until the decline phase (OD₆₀₀ = 5.5∼6.5).

Extraction and quantification of PCA from the culture suspension were performed using the described methods [48]. β-Galactosidase assays were carried out according to the method of Miller [49]. All experiments were performed in triplicate.

The 5′-UTRs of phzA1-G1 and phzA2-G2 were aligned with the outlier P. aeruginosa strain PA7 genome using the blastn algorithm [35]. Then, the conserved RNA secondary structures were predicted using the RNA fold [36] web server (http://rna.tbi.univie.ac.at/cgi-bin/RNAfold.cgi), and the base pairing probabilities were calculated. Subsequently, portions of the 5′-UTR of phzA1-G1 were taken to predict three suboptimal structures, and the free energies of optimal and suboptimal structures were calculated with mfold [50].