A growing body of evidence supports the idea that even monospecies biofilms comprise phenotypically and genotypically heterogeneous populations [1], [2], [3], [4]. This heterogeneity suggests that the biofilm mode of growth prompts diversification of the bacterial population by promoting the emergence of variants, and indeed several bacterial species (e.g. Pseudomonas aeruginosa, Streptococcus pneumoniae and Staphylococcus aureus) have been shown to elaborate morphological variants during biofilm growth [1], [5], [6], [7]. This process is attributable, at least in part, to the increased genetic plasticity of bacterial biofilm populations, which exhibit enhanced mutability and recombination relative to their planktonic counterparts [3], [8], [9].

A subset of the variants arising during biofilm growth of bacterial pathogens may possess characteristics with relevance to our understanding and management of bacterial disease. For example, we and others have shown that antibiotic-resistant mutants arise with greater frequency in bacterial biofilms [3], [8], [9]. It has also been demonstrated that the biofilms of some species contain large subpopulations of small colony variants (SCVs) [10], [11]; such variants exhibit reduced susceptibility to a variety of antimicrobial agents [6], [12], and may play a key role in establishing chronic infection [13].

Here we investigated the emergence of variants during biofilm growth of the important human pathogen S. aureus, focussing on detection of morphological variants that could be visually distinguished from the parental strain. We report the identification of two types of morphological variant that represent major subpopulations of both static and continuous-flow biofilms. Based on their phenotypes, we propose that these subpopulations play important and distinct roles during staphylococcal infection.

Colonies exhibiting morphological variation were initially detected upon plating onto agar dilutions of S. aureus SH1000 biofilm cultures grown using the cellulose disk static (CDS) biofilm model. Two colony morphologies distinct from the parental strain were identified; nonpigmented colonies, which we designated white variants (WVs), and large pale variants (LPVs) (Figure 1).

Quantification of the occurrence of these variants in CDS biofilms of S. aureus SH1000 revealed their presence in both the adherent and nonadherent populations of the biofilm, with the majority present in the nonadherent phase (Figure 2A & 2B). After 144 hrs of biofilm growth, WVs were found to comprise 2% and 26% of the total cells of the adherent and nonadherent populations, respectively (Figure 2A). At the same time point, LPVs comprised 15% and 52% of the adherent and nonadherent populations, respectively (Figure 2B). WVs and LPVs were also detected in biofilms of S. aureus SH1000 grown for 96 hrs in a constant flow system, indicating that the appearance of LPVs and WVs is a general feature of staphylococcal biofilm growth, and is not uniquely associated with biofilms forming under static conditions. By contrast, WVs were not recovered from planktonic cultures after either standard (18 h) or extended (144 h) growth intervals; LPVs were not detected at 18 h planktonic growth but were present at low frequency (∼1% of the population) after 144 h growth.

Representative variants for each morphological type (WV1, WV2 and LPV1, LPV2) were selected for further characterization. Both the WV and LPV phenotypes were found to be stable upon subculture, even after multiple passages (>20), implying that the phenotypes were the result of stable genetic change(s).

In this study we have identified and characterized two distinct morphological variants that are not commonly present in planktonic cultures of S. aureus, but which represent major subpopulations of the staphylococcal biofilm.

WVs did not produce staphyloxanthin, had lost the ability to form biofilms and displayed increased proteolysis and haemolysis; all of these phenotypes could be attributed to loss-of-function mutations detected in sigB. Since SigB negatively regulates the activity of the agr system, loss of SigB activity in WVs results in enhanced agr activity [23], which in turn leads to upregulation of extracellular factors such as proteases, nucleases and haemolysins, and downregulation of adhesins [28]. The loss of biofilm-forming activity in WVs is presumably the result both of reduced adhesin production (resulting in reduced adherence), and increased degradation of extracellular factors involved in formation of an extracellular matrix (e.g degradation of proteinaceous components and extracellular DNA by proteases and nucleases, respectively [29], [30], [31]).

In contrast, LPVs retained the ability to form biofilms, and were non-haemolytic and deficient in colony spreading as a consequence of loss-of-function mutation in agrA. LPV2 also carried a missense mutation in the dihydropteroate synthase gene; however, the absence of mutation at this locus in LPV1 indicates that it is not a requirement for the LPV phenotype. Strains with a defective agr quorum sensing (QS) system are more prolific biofilm formers owing to reduced production of surfactants such as phenol soluble modulins [PSMs] [32], enhanced cellular aggregation as a consequence of elevated expression of protein A [33], and reduced extracellular protease production [30]. Indeed, in wild-type strains of S. aureus, repression of the agr system is required for protein-dependent biofilm formation [30].

A previous study reported the emergence of variants with altered haemolytic properties from the staphylococcal biofilm, including both non-haemolytic and hyper-haemolytic strains [7]. These variants are apparently distinct from those that we have described here; in contrast to the LPVs, the non-haemolytic variants previously reported displayed a non-pigmented phenotype when grown on complex medium, whilst in contrast to the WVs, the hyper-haemolytic variants were phenotypically unstable [7].

The high proportion of WVs and LPVs detected in our biofilm models indicates that these variants are under strong selection, but the circumstances driving their selection are not clear. One possibility is that WVs are favoured in the early stages of staphylococcal biofilm maturation because they overproduce α-haemolysin, a protein which has been shown to mediate cell-to-cell contact and is essential for staphylococcal biofilm formation [34]. Alternatively, WVs may become selected owing to their dissemination-inducing phenotype; dissemination appears to be important for bacterial populations during biofilm growth, enabling population dispersal and survival [35], and subpopulations exhibiting an enhanced detachment phenotype have been detected in the pseudomonal biofilm [11]. WVs appear to arise earlier and in greater number than LPVs in the biofilm (Figure 3), and we propose that it is the emergence of the former that drives the appearance of the latter. The presence of a large subpopulation of cells in the biofilm exhibiting enhanced activity of the agr system (WVs) will allow the emergence of ‘cheater’ cells (LPVs); a subpopulation of QS negative mutants that exploits the exoproducts of QS proficient cells, and thereby gains a competitive advantage through reduced energy expenditure. An analogous form of ‘cheating’ by QS negative mutants has been reported in strains of P. aeruginosa [36], [37], [38].

S. aureus strains with loss-of-function mutations in either sigB (WV) or agr (LPV) are known to be relevant in human infection, and both genotypes have been isolated from patients [39], [40]. The increased haemolytic and proteolytic activity in sigB mutants is likely to enhance virulence by increasing host cell lysis and tissue degradation. By contrast, agr-defective mutants show an enhanced ability to evade the host’s immune system during infection, presumably owing to a reduction in secreted virulence factors such as PSMs which strongly activate the immune response [41]. Indeed, persistent staphylococcal infections have, in some instances, been linked with strains exhibiting reduced expression of the agr system or defects in agr [42]. Our findings suggest that biofilms could potentially represent a rich source of both sigB and agr defective strains during infection, with important implications for chronic staphylococcal biofilm infections. The emergence within the biofilm of sigB deficient strains (WVs) could act to drive local disassembly of the biofilm, thereby facilitating release of cells from the biofilm and dissemination throughout the host. A hypervirulent subpopulation of cells released from the biofilm (WVs) may act to maximise host damage, whilst the agr defective cells (LPVs) emerging from the biofilm may facilitate the establishment of a persistent infection. Our concept for the emergence and release of sigB/agr mutants from the biofilm, and their contrasting roles in infection, is summarised in Figure 4. Future studies should confirm the presence of both subpopulations in biofilms formed in vivo during infection.