First, we established the single-cell dynamics of the progression toward spore formation by measuring the temporal profile of four sporulation components (Fig. 1A). Initiation of sporulation is controlled by a multicomponent phosphorelay including two phosphotransferases, Spo0F and Spo0B, and a transcription factor Spo0A [14], [19], [22], [23], [24], [25]. Spo0F protein senses and integrates a variety of inputs and as a result becomes phosphorylated [23], [24]. The phosphate group is subsequently transferred through Spo0B to Spo0A, a master regulator of sporulation, which upon phosphorylation directly controls expression of over 120 genes [20], [26], [27], including spo0F (in what constitutes a feedback mechanism [28], [29], [30]). Among these is the gene for SpoIIE, a protein phosphatase that is required for the activation of the forespore specific transcription factor (σ^F) and whose localization to the asymmetric septum is the first morphological marker for forespore formation [31], [32], [33], [34], [35]. Activation of σ^F in the forespore switches on the expression of SpoIIR, which in turn leads to the activation of σ^E, a transcription factor specific to the mother cell that switches on the expression of a large number of late sporulation genes [36], [37], [38]. At this point, the cell becomes irreversibly committed to sporulation [21], [37], [38], [39]. Using fluorescent reporter constructs, we quantified the activities of the Spo0A (P_spo0A), Spo0F (P_spo0F) and SpoIIR (P_spoIIR) promoters (Fig. 1A, top two rows). We also visualized SpoIIE protein localization by utilizing a functional translational fusion to SpoIIE (Fig. 1A, bottom row). Each sporulation reporter was simultaneously measured in combination with the P_spoIIR reporter. Measurement of these overlapping pair-wise combinations of reporters allowed us to establish a relative temporal profile for multiple sporulation steps with single-cell resolution (Fig. 1B and Supporting Fig. S1) that was consistent with the genetically established hierarchy within the sporulation circuit [14], [18], [22], [40], [41], [42] (Fig. 1C).

Single cell measurements of sporulation reporters revealed that progression to spore formation is comprised of reversible steps. During the early progression to spore formation, individual cells exhibited bursts of P_spo0A gene expression that did not result in spore formation (Fig. 2A). Activation of Spo0A during B. subtilis sporulation is known to be heterogeneous among single cells [43], [44]. However, spontaneous bursts of gene expression at single-cell level during sporulation have not been described to date. Bursts in gene expression were not limited to P_spo0A, but were also observed for P_spo0F (Fig. 2B). Given that P_spo0F is, as mentioned above, transcriptionally activated by phosphorylated Spo0A, the dynamics of that promoter is reporting the activity of Spo0A. Consequently, the observed bursts in P_spo0F indicate that not only the expression, but also the activity of the Spo0A master regulator exhibits bursts in single cells. In contrast, bursts of gene expression were not observed for the late stage sporulation reporter P_spoIIR (Fig. 2A–C): after the sharp signal increase observed for P_spoIIR, a spore is always formed (and thus the time traces shown in the plots cannot be continued). Gene expression bursts can introduce variability and reversibility during the early stages of the progression to spore formation, whereas the later stages do not appear to be subject to such stochasticity. Additionally, we observed reversible protein localization of SpoIIE in approximately 2±1% (SEM) of cells (Fig. 2C). Specifically, we observed transient localization events of the SpoIIE-YFP fusion protein to the asymmetric septum that did not give rise to spore formation. In these cells, SpoIIE either switched its localization between opposite poles, or completely delocalized and cells continued with cell division (Fig. 2C). Similar bursts of promoter activity and protein localization in single cells have also been reported in other systems, and have been attributed to the stochastic and reversible nature of the underlying biochemical reactions [43], [45], [46], [47], [48], [49], [50].

The single-cell reversibility observed here is distinct from what has been reported in population-level studies which showed that sporulation can be aborted upon transfer from stress to rich media conditions [21]. In contrast, the single-cell reversibility discussed here appears to be a cell autonomous behavior that occurs randomly without requiring a change in environmental conditions. Such cell autonomous and random sampling of heterogeneous behavior in single cells has also been observed in other systems where it may provide a fitness advantage, such as the generation of antibiotic resistant Escherichia coli persister cells [51] and the survival of Saccharomyces cerevisiae to cellular stress [50]. Together, our data reveal that the early steps of progression towards spore formation are subject to stochastic reversibility at the single-cell level, suggesting an adaptable progression to spore formation.

Detailed analysis of single cell dynamics revealed that the irreversible commitment for spore formation is executed within a narrow time window. Specifically, we find that P_spoIIR activation (which as mentioned above, denotes the sporulation commitment point) is switch-like (Fig. 2A–C, green line). This timing was quantified by using the morphological appearance of an actual spore (indicated by a phase bright spot in our single-cell movies) as a reference time point from which to measure commitment time (Fig. 3A). Analysis of single-cell data shows that the temporal distance between P_spoIIR activation and the formation of the morphologically visible forespore is tightly distributed (CV = 0.2, and 15% of median cell cycle duration) (Fig. 3B). These results show the precise timing of the irreversible decision and the completion of the spore formation process. Therefore, single cell measurements of sporulation dynamics exposed a precise cell intrinsic decision point in time that revealed switch-like dynamics of the commitment to spore formation. The temporal precision of this decision-making point was previously concealed in population measurements (see Fig. 1B) by the cell-to-cell variability in the reversible progression to spore formation.

Our measurements suggest that the decision to sporulate in B. subtilis is made in an irreversible all-or-none manner, following a reversible and gradual progression toward this decision point. Therefore, sporulation combines reversible and irreversible dynamics, two seemingly opposed decision mechanisms. In order to examine the potential advantages of this hybrid mechanism, we compared the response of three simplified models of cellular decision-making to a variable-stress environment. These models describe the dynamics of a population of cells progressing toward sporulation under stress, in terms of the number of cells existing at any given time in a given state along the progression, beginning with the vegetative state and ending in the spore state. The dynamics of cell populations in all these states is given by a set of coupled ordinary differential equations that are linear, and thus can be solved exactly (Supporting Text S1). The three models, shown schematically in Fig. 4A and described in detail in the Supporting Information (Supporting Text S1 and Supporting Fig. S2), involve either 1) a purely irreversible/all-or-none, 2) a purely reversible/gradual, or 3) a “hybrid” process that takes cells from their initial vegetative state to their final spore state. In the irreversible-only scheme, cells decide in a single step whether or not to sporulate, and the decision is irreversible. The reversible-only model takes cells gradually toward sporulation through multiple reversible intermediate states, without any irreversible commitment step taking place along the process. Only the ultimate transition to the spore state, taking place after the decision, is irreversible. Finally, the third “hybrid” model features the actual sporulation dynamics identified here for B. subtilis that combines a gradual progression through reversible intermediate states with an irreversible all-or-none decision prior to the spore transition.

We subjected the three models described above to a random variation of the environment, with alternation of a high and a low level of stress (insets in Fig. 4B and Supporting Fig. S3). For all models, the rates of progression toward/back from sporulation, growth and death rates are all coupled to the level of stress (Supporting Text S1). We then systematically varied the ratio of high stress to total cycle duration, which was kept constant. The relative fitness of the hybrid model with respect to the irreversible-only and reversible-only models was measured as the ratio of total cells in the population between the models (Fig. 4B, blue and red lines respectively).

Results of this analysis show that the survival rate of the different models depends on the stress profile. None of the models dominates over the entire range of environmental stress conditions, but the hybrid model performs best overall. For short phases of high stress, the hybrid outgrows the irreversible-only model (left half of main plot in Fig. 4B, blue line), since the latter is driven irreversibly to sporulation even for short stress periods. Under these conditions, the hybrid and reversible-only models perform similarly (red line) since in both models reversible progression delays sporulation. However, in the opposite limit where high stress durations approach the total duration (right half of main plot in Fig. 4B), the irreversible-only model outgrows the hybrid model, since responsiveness is a disadvantage. For such prolonged high stress durations, spores are at an advantage because non-spore cells have a higher death than growth rate under stress. In this limit, the hybrid model is in turn more reliable than the reversible-only model, since the reversible-only model is driven away from sporulation even by short intervals of rich phase. Parameter sensitivity analysis showed that these results hold over a range of parameter values (Fig. 4B, light blue and light red regions). Taken together, these results show that the hybrid model outperforms both the irreversible-only and reversible-only schemes over a broader range of randomly alternating stress profiles, given its responsiveness to the long-term recovery from stress and its reliability during short-term release of stress conditions.

This prediction was tested directly by subjecting all three models to random changes in the fraction of time spent in high stress. In these extended simulations cells were exposed to 100 random samplings of environmental stress ratios (part of an environmental profile is shown in Fig. 4C, inset). We then calculated the ratio of the total cell population of the hybrid model to that of the irreversible-only and reversible-only models averaged over the entire simulation, defining the relative fitness of each model (Fig. 4C). Our data demonstrate that the hybrid model has an overall higher fitness over both the irreversible-only and reversible-only models when populations are subjected to a randomly changing range of environmental conditions. Therefore, the combination of gradual progression toward an all-or-none decision in B. subtilis, as represented in the hybrid model and observed experimentally, enables the system to cope with a broader range of unpredictable stress conditions.

Bacillus subtilis strains used in the study are isogenic to wild-type B. subtilis PY79 strain and are listed in Supporting Table S1. Promoter – fluorescent proteins fusions were generated using fusion polymerase chain reaction and cloned into B. subtilis chromosomal integration vectors following standard protocols. The following B. subtilis chromosomal integration vectors were used: pSac-Cm, integrating into the sacA locus (constructed by R. Middleton and obtained from the Bacillus Genetic Stock Center) and pLD30 integrating into the amyE locus (kind gift from Jonathan Dworkin, Columbia University). We have also utilized the bifunctional cloning plasmid pHP13 carrying the replication origin of the cryptic B. Subtilis plasmid pTA1060 (5 copies per genome) [59]. Standard one-step transformation protocol was followed to transform B. subtilis with these constructs.

For imaging, B. subtilis cells were grown at 37°C in LB with the following concentrations of appropriate antibiotic: 5 µg/ml chloramphenicol, 5 µg/ml neomycin, 5 µg/ml erythromycin or 100 µg/ml spectinomycin. After reaching OD 1.8, the cells were resuspended in 0.5 volume of Resuspension Media (RM; see Supporting Text S2, Materials and Methods) supplemented with 0.02% glucose. The cells were incubated at 37°C for 1 hour, then diluted 10-fold in RM and applied onto a 1.5% low-melting agarose pad placed into a coverslip-bottom Willco dish for imaging.

Growth of microcolonies was observed with fluorescence time-lapse microscopy at 37°C with an Olympus IX-81 inverted microscope with a motorized stage (ASI) and an incubation chamber. Image sets were acquired every 20 min with a Hamamatsu ORCA-ER camera. The imaging time has been optimized in order to prevent phototoxicity [11]. Custom Visual Basic software in combination with the Image Pro Plus (Media Cybernetics) was used to automate image acquisition and microscope control.

Time-lapse movie data analysis was performed by custom software developed with MATLAB image processing and statistics toolboxes (The Mathworks) described in [60] and [11].

Extended description of the models and methods is available in Supporting Text S1, Mathematical Modeling.