To date, most of the synthetic gene networks have been created for bacteria or for lower eukaryotes [1]–[7]. They were successfully employed to investigate different regulatory networks within these biological systems. A wealth of information could be provided by these studies. To facilitate systems biology based approaches for the elucidation of complex regulatory networks involved in immunology, developmental biology or infection, the development of appropriate synthetic modules as well as their establishment in mammalian cells and animals is indispensable. A thorough understanding and mathematical description of these modules in complex organisms would further pave the way to exploit such circuits within systems biology and also for applications in gene or cell therapy [8].

Pioneering studies demonstrated that the creation of synthetic gene circuits is feasible also in mammalian systems. The designed devices encompassed a toggle switch [9], a hysteretic switch [10] and a time-delay circuit [11]. A major limitation is that the manipulation of mammalian cells is tedious and time-consuming. Especially stable integration of synthetic gene circuits remains a challenge and is up to now only achieved in immortalized cell lines which usually do not or only partially reflect relevant properties of the cells they have been derived of. This can be partially attributed to the genetic changes which are required to provide unlimited cell growth. To implement synthetic cassettes in primary cells novel tools have to be developed.

Viruses have evolved strategies to efficiently transduce their genetic information to mammalian cells. In particular, adenoviruses, adeno-associated viruses and retroviruses were exploited for their potential to genetically modify mammalian cells [12], For this purpose, non-replicating viral vectors have been developed that can be transduced with the help of packaging cells [e.g. 13], [14]. While non-replicating extrachromosomal vectors (e.g. derived from adenoviruses) remain in an extrachromosomal state they lead to a transient expression in proliferating cells. Retroviral and especially lentiviral vectors are the optimal tools to provide stable integration of expression cassettes into the host's genome and thus guarantee the maintenance of the cassettes in replicating cells. Pseudotyping of lentiviral vectors allow to to transduce a broad range of different cell types from different species. Importantly, they are also capable of infecting slowly or non-proliferating cells and thus are preferential tools for many primary cells including stem cells.

Gene expression patterns in eukaryotes can be classified into two distinct types: graded and bimodal [15]. In the graded pattern, cells respond uniformly to increasing levels of the stimulant. In contrast, in the bimodal pattern, the level of the stimulant affects only the probability that a gene will be expressed in a given cell; this expression is always “maximal”. Bistable expression of metabolic genes such as those for galactose utilization in yeast [16] and lactose utilization in E.coli [17] have been shown to result from positive feedback. One prominent example for bistability in eukaryotes is the cell-cycle oscillator, a biochemical system that has been shown to promote irreversible transitions between distinct mitotic and interphase states [18]–[20]. But also in the immune system the T helper activation is governed by an bimodal expression of the transcription factor NFATc2 which integrates graded T cell receptor activation into a bimodal IL2 expression [21], [22].

The bimodal expression mode may lead to multimodal variation in the phenotype of an isogenic cellular culture and in organisms (i.e. differentiation). In genetic networks this confers a memory to past events or environmental changes. Thus, stochasticity is an important feature of many biological processes in mammalian cells. Several means have been described to achieve a bimodal expression pattern. Amongst them are positive feedback loops and mutual repression [23]. As an example, the latter can be accomplished using two interlinked negative feedback loops which create a toggle switch [4], [9]. This toggle switch setup was employed in another study as a memory subsystem. This was implemented and used for recording the outputs of a larger DNA-damage sensor network [24]. Bimodal expression was further achieved by employing two opposing transcriptional regulators [25]. Becskei et al. (2001) [26] finally proved that in yeast even a less complex network based on the tet-system can result in a bimodal expression pattern upon gradual increase of the inducer tetracycline.

The aim of this study was to provide and evaluate a strategy to efficiently implement a bimodal synthetic gene circuit in mammalian cells. For this purpose, three different methodologies were exploited. A synthetic positive feedback system resulting in binary expression response was transduced via lentiviral transduction. This combination ensures that the synthetic gene circuit can be installed a broad range of mammalian cells including primary cells. After stable integration into the host cell the synthetic gene circuit displayed a bimodal expression pattern and the resulting experimental data were used to construct a mathematical model. The model followed closely the observed in vivo data and predicted a strong hysteretic response of the positive feedback loop. The in silico data were experimentally verified demonstrating the value of this concerted approach.

A goal of synthetic biology is to describe and understand naturally occurring networks by constructing synthetic analogues. Mathematical modelling of such synthetic modules allows to describe and evaluate the installed networks. Further, predictions can be made which are subsequently experimentally verified. However, the installation of synthetic gene circuits in cells of higher eukaryotes is still not sufficiently solved. In particular, primary cells or even animals are so far not available for systems biology approaches. This is attributed not only to the genetic and phenotypic complexity of these natural systems but also to the lack of reliable methods to implement synthetic cassettes. Here, we show that expression cassettes conferring bimodal expression can be efficiently transduced with the help of lentiviral vectors. The results presented here were obtained with an immortalized cell line (NiH3T3 cells). However, the real strength of lentiviral transduction is that not only cell lines but also primary cells of different origin and from different species can be transduced. Preliminary data demonstrate that transduction of the synthetic gene regulation circuit is feasible and efficient also in primary cells, Importantly, the expression characteristics of the positive feedback loop are comparable to those observed in the NiH3T3 cells (data not shown). Establishing a mathematical model based on stochasticity we further describe and predict expression patterns.

Stochasticity is frequently encountered in biological systems. In particular, they contribute to transcriptional and translational processes [2], [35]–[38]. Generally, it would be expected that stochasticity would compromise the precise control of gene expression levels eventually with detrimental consequences. Indeed, this has been described for several situations [1], [16], [39]. However, stochasticity also provides a mechanism to generate certain diversification of individual cells within a population–and thus is advantageous under certain conditions, e.g. when the cell encounters stress conditions [40]. Different natural networks in which stochastic expression leads to a phenotypic heterogeneity of isogenic cells have been described [reviewed in 33]. This includes the lysogeny decision in phage lambda; here, an initially homogenous population is split due to molecular fluctuation [41]. Also, the HIV-1 Tat expression module gives rise to fluctuations that create distinct phenotypes from a single proviral integration [42].

In mammalian systems, stochasticity seems to play a particularly important role in development and differentiation processes such as hematopoiesis [43]. Such decisions are also encountered in networks governing apoptosis [44] and the cell cycle [34]. Also, stochasticity can be involved in diseases, in particular in those which arise from transcription factor haploinsufficiency; upon stochastic simulation evidence was given that haploinsufficient systems are more susceptible to disturbances in expression [45]. Experimental evidence confirmed this result, demonstrating a decreased probability of gene activation in haploinsufficient cells [46]. In summary, it seems that stochastic fluctuations, whilst problematic in a homeostatic context, may prove to be essential within the context of development and differentiation of cellular populations.

In previous studies it was demonstrated that a bimodal expression pattern was realized when a repressor and a transactivator compete for the same DNA binding site [25] by two interlinked negative feedback loops [4], [9] or by positive feedback and mutual expression [23]. Here, we show that a less complex network consisting of a transactivator and its responsive promoter is sufficient for provoking bimodal expression in a mammalian system. In this respect, the described positive feedback modules represent ideal building blocks to artificially provoke all-or-nothing-answers in mammalian cells.

The mathematical model predicts a hysteretic expression pattern from the synthetic positive feedback loop. This prediction was experimentally verified. Such a strong a strong hysteretic response is expected to occur only from strong positive feedback loops. The hysteretic response of feedback modules can be tuned by the strength of the positive feedback [34]. To achieve such a response with the synthetic modules presented here, transactivator mutants eliciting activation at different inducer levels [47] might be of benefit. Furthermore, the hysteretic response can be modulated to different strengths through the connection of a positive feedback loop with a transcriptional repressor [10].

This latter approach pinpoints that for the establishment of complex multigene networks, several non-interacting switches (transactivators) or relais (promoters) are needed. Progress has been made in the creation of independent gene regulation for mammalian systems [for review see 48]. The combination of different systems within single cells or animals would allow to differentially control distinct circuits. As exemplified by this study the lentiviral transduction of a synthetic positive feedback circuit proves useful. Exploiting this tool for transduction of independently regulated synthetic modules will allow to reliably install more complex networks in mammalian cells including primary cells. Thereby, it provides an important step to synthetically modify these systems for systems biology approaches.