1. IntroductionDental caries or tooth decay is defined as dissolution of tooth inorganic mineral components, primarily hydroxyapatite, by acid end-products from cariogenic bacteria, such as Streptococcus mutans (S. mutans), which results in the exposure of the organic dentinal collagen, primarily type I collagen. It has been suggested that dentinal collagen degradation due to proteolytic activity follows demineralization and complements the initial degradative effect of bacterial acids on the dentinal mineral structure, contributing to caries progression [1].Potential sources of proteolytic activities that could contribute to dentinal collagen degradation are endogenous dentinal proteases [2], the oral microflora [3,4], and neutrophils [5]. Previous studies focused mainly on the role of degradative activities from endogenous matrix metalloproteinases (MMPs) in the hydrolysis of dentinal collagen [1,2]. Studies have shown that activated MMPs are involved in caries formation [6] and collapse of adhesive interface [2,7,8]. However, the contribution of endogenous MMPs to dentin degradation is controversial due to their limited abundance within dentin and limited enzymatic activity compared with bacteria and neutrophils [9]. In addition, the enzymatic activity of dentinal MMPs is not defined [10].Bacterial proteolytic activities have been investigated because of their roles in bacterial invasion and tissue destruction in human diseases [11,12]. Human isolates of S. mutans have been shown to cause extensive bone loss and the breakdown of the periodontal ligament in gnotobiotic rats [13], which is suggested to be related to the bacteria’s proteolytic activity as demonstrated by their ability to degrade rat tail tendons [12]. The genes that encode S. mutans collagenolytic proteases have been identified by RNA sequencing and bio-informative methods from root caries [14]. Further, a MMP-like protein has been identified from Streptococcus mitis (S. mitis) [15]. However, none of these studies have directly linked the specific proteolytic activity of S. mutans to human dentinal collagen degradation, and there are no data related to where such bacterial collagenolytic/gelatinolytic protease activities reside: intracellular, excreted extracellularly, or in the bacterial membrane.

Hence, further exploration of the proteolytic activity of the cariogenic bacteria S. mutans on dentinal degradation and its potential impact on the pathogenesis of primary and secondary caries is warranted. The aim of the current study was to investigate the role of whole cell S. mutans’s and discrete fractions of this bacterium in the degradation of type I collagen and human dentin-derived collagen. The hypothesis is that S. mutans expresses proteolytic activities, located in defined cell extract fractions of the bacterium, that degrade purified type I collagen and dentinal collagen.

4. DiscussionBacterial proteolytic activities have been previously characterized [3] and studied in the context of nutrient acquisition as a primary mechanism for bacterial survival [23,24]. In addition, these activities have been linked to direct and/or indirect host tissue destruction as virulence factors in several oral diseases [11]. From the many bacterial species that colonize and persist in the oral cavity, S. mutans is one of the few that have been consistently linked to caries formation, due in part to its ability to form biofilms, produce acid, and tolerate acidic conditions [25]. The strain used in the current investigation, S. mutans UA159 is a clinical isolate that degrade restorative materials and as such may contribute to marginal deterioration and secondary caries development [26]. The current investigation is the first to report on the proteolytic activity of S. mutans and its discrete fractions, and their ability to degrade type I collagen and more importantly, demineralized human dentin collagen. On the basis of these findings, we accept the hypothesis that S. mutans, a major pathogen involved in the pathogenesis of dental caries, expresses proteolytic activities located in defined cell extract fractions of the bacterium that degrades type I and dentinal collagen. This notion suggests new possibilities for these proteolytic activities to provide an alternative cariogenic mechanism for S. mutans.The specificity and activity/efficiency of bacterial proteases vary towards different substrates [21]. Purified rat tail type I collagen is a relevant, reproducible and practical substrate to investigate the degradative activity of S. mutans towards dentinal collagen, since approximately 90% of the organic matrix in dentin is type I collagen [27]. Further, rat tail collagen has been used as substrate to investigate oral bacterial collagenolytic activity in previous studies [21,28,29,30]. The amino acid sequence of type I collagen comprises 33% glycine and also contains hydroxyproline and proline, which are important for the structure and function of collagen. Although bacterial collagenolytic enzymes cleave collagen at different sites and generate multiple degradation fragments, the release of hydroxyproline is a sensitive and reliable measure to estimate collagen degradation [4,31]. The results of the current investigation showed an important increase of hydroxyproline release from purified type I collagen in the presence of overnight and newly inoculated S. mutans cultures. As there was no detectable hydroxyproline release from media alone, we suggest that the bacterium is the sole source of this protease activity and can degrade type I collagen. This finding was supported qualitatively by CLSM, which also demonstrated the structural destruction of collagen gels after incubation with S. mutans cultures.In the current investigation, the higher degradation of type I collagen by O/N S. mutans cultures when compared with NEW cultures suggests a growth-phase dependency for the degradative capacity of the bacterium. This finding may be explained by the autolysis of S. mutans in its later growth stage, a condition that facilitates cell wall turnover, cell division, assembly of secretion systems, resuscitation of dormant cells, and micro fratricide [32]. As a result, more intracellular enzymes are released into incubation medium, contributing to enhanced collagen degradation. The increased collagen degradative activity for overnight cultures could also be explained by the increased production of selective proteases in the late growth stage of S. mutans, which is part of bacterial adaptation strategies, in which some oral pathogens may digest host tissue such as collagen in order to release amino acids as a nutrient source [33].When compared to rat tail type I collagen, human dentin collagen has a more complex structure at different hierarchical levels [34]. Cross-linked structures indicate the presence of collagen molecules that are more resistant to enzymatic degradation than collagen molecules found in other tissues [34,35]. Therefore, further experiments were carried out to verify the proteolytic activity of S. mutans towards demineralized human dentinal collagen. There was no hydroxyproline release from dentin or dentinal structural changes in samples treated with medium only in which dentinal MMPs were the only possible source of proteolytic activity. This finding supports the hypothesis that endogenous MMPs may exert relatively low effects on dentinal collagen degradation [36] due to the limited amount of MMPs in dentine and their inactive form [37]. In contrast, the marked increase of hydroxyproline release in samples treated with overnight (O/N) or fresh-inoculated (NEW) S. mutans confirmed the ability of these fractions to degrade demineralized human dentin, corroborating the results from rat tail type I collagen. This observation was also supported by the SEM analysis showed dentinal tubule structural disruption of these groups. In addition, the higher dentinal and type I collagen degradation by O/N S. mutans cultures than NEW cultures confirms that the degradative capacity of the bacterium is growth-phase dependent. The amount of hydroxyproline released from demineralized dentin was several-fold higher than that from type I collagen, which could be explained by the longer incubation times that were used with the dentin samples (14 days vs. 1-day). This finding suggests that these degradative proteases are stable to maintain their activity throughout extended incubation times. In addition, unlike the type I collagen degradation study, the O/N S. mutans had the highest hydroxyproline release for the dentinal collagen samples, which could be a result of the combined effects of growth-dependent selective enzymes production and increased release of intracellular enzymes by bacterial autolysis caused by the prolonged incubation and the accumulation of these enzymes.To locate the protease activity responsible more precisely for type I collagen and dentinal collagen degradation, discrete bacterial fractions and the incubation media were investigated. Both intracellular components and supernatants were capable of cleaving type I and dentinal collagen, releasing hydroxyproline and disrupting collagen structures. Supernatants from S. mutans O/N cultures showed higher degradative activity than intracellular components, suggesting that significant protease activity may be secreted or released extracellularly. This finding is supported by previous reports that most bacterial collagenases are extracellular proteins involved in bacterial invasion [38,39]. However, it cannot be assumed that the proteases were only secreted, since intracellular proteases may be released into the extracellular environment by S. mutans autolytic activity as mentioned above [40,41]. Autolyzed bacteria account for 30% to 40% of the population in S. mutans biofilm, and significantly contribute to extracellular/supernatant proteolytic activity [42]. In addition, the current results verified that an important proportion of these proteases are located intracellularly, a conjecture that is based on the high hydroxyproline release from type I collagen and dentin samples incubated with intracellular proteins of S. mutans.Bacterial collagenolytic proteases have a broad range of specificity, but their substrates are hydrolyzed at various specific peptide bonds [43]. The main source of knowledge of bacterial collagenases is based on multiple studies on the enzymes produced by C. histolyticum [44]. In the current study, purified collagenase from C. histolyticum was used as a positive control to analyze the degradative effects and patterns of proteases from S. mutans. As a baseline, type I collagen released from demineralized dentin incubated with PBS buffer were collected and were detected on SDS-PAGE gel as two distinct bands, indicating typical α1- and α2 chains of type I collagen. The absence of αA chains, which are the characteristic 3/4-cleavage products generated by mammalian interstitial collagenases, reinforces the limited effect of dentinal endogenous MMPs on dentinal collagen degradation [45]. The smear presented on SDS-PAGE gels of samples of demineralized dentin incubated with PBS buffer suggest that non-collagenous proteins were released after the demineralization procedure or were denatured collagen fragments. When comparing dentin specimens incubated with PBS control or extracted bacterial protein of S. mutans UA159, the collagen fragments degraded by S. mutans proteases were presented as multiple bands on SDS-PAGE gel.The different bands generated by S. mutans intracellular proteases and C. histolyticum collagenase indicate that the collagen cleavage sites generated by S. mutans proteases are different than those of C. histolyticum, and that different bacterial enzymes are likely responsible for the cleavage. The primary-structural analysis of two resultant collagen fragments derived from dentinal collagen upon digestion with S. mutans intracellular proteins confirmed the degraded peptides were from the α1 chain of type I collagen, suggesting that the enzymes might preferentially act on certain peptide sequences. Although not all of the possible cleavage sites in collagen were determined, several preferred amino acids were suggested as cleavage sites, including Lys, Gly, Ser and Arg, which have been reported for other bacterial collagenolytic proteases [39,46,47]. However, the proteases’ specificity cannot be definitively identified due to the combined effects of multiple proteases in the intracellular components. Therefore, specific collagenolytic/gelatinolytic proteases from S. mutans have been synthesized for more detailed investigation, to be reported on in a follow-up investigation.

Although the current definition of caries is still limited to demineralization of dental tissues due to the acid produced by sugar-fermenting microorganisms, the current investigation proposes that dentinal collagen may be degraded by extracellular and intracellular cariogenic bacterial proteases after demineralization, which further highlights the potential multifactorial contributions of S. mutans to primary and secondary caries formation and progression. Further characterization of the bacterium degradative activity and degradative mechanisms, and identification of specific proteases that are involved in this process, is needed.