High-precision, in vitro validation of the sequestration mechanism for generating ultrasensitive dose-response curves in regulatory networks

Abstract

Our ability to recreate complex biochemical mechanisms in designed, artificial systems provides a stringent test of our understanding of these mechanisms and opens the door to their exploitation in artificial biotechnologies. Motivated by this philosophy, here we have recapitulated in vitro the "target sequestration" mechanism used by nature to improve the sensitivity (the steepness of the input/output curve) of many regulatory cascades. Specifically, we have employed molecular beacons, a commonly employed optical DNA sensor, to recreate the sequestration mechanism and performed an exhaustive, quantitative study of its key determinants (e.g., the relative concentrations and affinities of probe and depletant). We show that, using sequestration, we can narrow the pseudo-linear range of a traditional molecular beacon from 81-fold (i.e., the transition from 10% to 90% target occupancy spans an 81-fold change in target concentration) to just 1.5-fold. This narrowing of the dynamic range improves the sensitivity of molecular beacons to that equivalent of an oligomeric, allosteric receptor with a Hill coefficient greater than 9. Following this we have adapted the sequestration mechanism to steepen the binding-site occupancy curve of a common transcription factor by an order of magnitude over the sensitivity observed in the absence of sequestration. Given the success with which the sequestration mechanism has been employed by nature, we believe that this strategy could dramatically improve the performance of synthetic biological systems and artificial biosensors.

Figure 1. In vitro recreation of the sequestration mechanism.

Here we recapitulate in vitro the sequestration mechanism employed by nature to produce ultrasensitive outputs (steep input/output functions) in a number genetic regulatory networks. (a) In the sequestration mechanism low concentrations of a target molecule are “depleted” by binding to a high affinity non-signaling receptor that acts as a “sink” (the depletant). (b) Top, when the total target concentration surpasses the concentration of the depletant (the sink is saturated), a threshold response is achieved in which, upon the addition of any further target, the relative concentration of free target rises rapidly. Bottom, this threshold effect generates a “pseudo-cooperative” dose-response curve in which probe occupancy, and thus the output signal, arises much more rapidly than would occur in the absence of a depletant. (c) As a test bed to recapitulate and exploit this mechanism we have employed DNA molecular beacons, widely used probes for the detection of specific oligonucleotide sequences . Consisting of a stem-loop DNA modified with a fluorophore/quencher pair the affinities of molecular beacons can be tuned by changing the stability of their stems , thus rendering it easy to generate depletant (unlabeled molecular beacons) with almost any arbitrary affinity.

Figure 2. Ultrasensitivity is a strong function of the ratio [dep]/K_d^probe.

Using molecular beacons, we have recapitulated the sequestration mechanism in vitro and, in so doing, have vastly increased the sensitivity of this commonly employed biosensor. (Left) We find that ultrasensitivity is a strong function of the ratio [dep]/K_d^{prob e}, which measures the extent to which the concentration of the depletant rises above the affinity of the probe. (Here we are using a depletant/probe pair for which K_d^probe/K_d^dep  =  60). To quantify the sensitivity of these dose response curves we have fitted them to the Hill equation (dotted lines) to define pseudo-Hill coefficients. (Right) This pseudo-Hill coefficient increases monotonically as the [dep]/K_d^{prob e} ratio increases, reaching 9.4 at the highest ratios we have investigated. It is important to note, however, that although the Hill coefficient provides an easy way to compare sensitivity across different systems, the Hill equation is not a correct physical description of our system. Instead, the behavior of our system is described by the sequestration model as expressed in equation 2 (see text; see also Buchler et al., 2009). Using equation 2 and the previously determined dissociation constants of our probe and depletant , we can model the sensitivity of this system quantitatively (solid lines, left panel) without the use of any floating parameters. The theoretically modeled pseudo-Hill coefficient likewise describes our data quite well (solid line, right panel), deviating only slightly at our highest ratios we have investigated.

Figure 3. The relative affinities of the depletant and probe play a crucial role in generating ultrasensitivity.

For example, if, as is true here, [dep]/K_d^{pro be}  =  3.2, we only achieve significant sensitivity when the affinity of the depletant is at least 10 times greater than that of the probe. (Left) To demonstrate this we present here binding curves obtained with a medium affinity molecular beacon (2GC_probe, K_d^probe  =  310 nM) in the presence of depletants ranging in affinity from 5.2 nM to 3 µM (the depletants are, from right to left: 0GC_dep, 1GC_dep, 2GC_dep, 3GC_dep, 4GC_dep and 5GC_dep). Higher affinity depletants (0GC_dep, 1GC_dep), those with dissociation constants at least 10 times lower than that of the probe, produce clear, ultrasensitive responses. In contrast, depletants with affinities similar to (2GC_dep, 3GC_dep) or poorer than (4GC_dep and 5GC_dep) that of the probe produce little improvement in sensitivity. (Right) As demonstrated above the experimentally observed pseudo-Hill coefficients compare well with the theoretically modeled values (solid line). Again, the solid lines in these panels are not fits. Rather they are estimates taken directly from equation 2 (and using the known dissociation constants of the relevant probes and depletants) without the use of any fitted parameters.

Figure 4. Simulation of the sequestration mechanism.

A simulation of equations 1 and 2 illustrates the range of [dep]/K_d^probe and K_d^probe/K_d^dep over which pseudo-Hill coefficients above 2 (gray area) and above 4 (dark area) are obtained. Shown in boxes are some of the experimental pseudo-Hill coefficients we have observed (the horizontal and vertical lines of data were taken from figures 2 and 3 respectively).

Figure 5. Using the sequestration mechanism to steepen the binding-site occupancy curve of a transcription factor.

We have used the sequestration mechanism to steepen the concentration/occupancy curve of a common transcription factor by an order of magnitude over the sensitivity observed in the absence of sequestration. (left) As our read-out mechanism we have employed transcription factor beacons, a recently developed, high-precision reporter of transcription factor binding site occupancy analogous to molecular beacons (right). Using a transcription factor beacon directed against the target TATA binding protein as our probe and a 10-fold excess of a simple, higher affinity, double-stranded hairpin DNA as our depletant, we achieve an ultrasensitive dose-response curve with a pseudo-Hill coefficient of 4.3. This compresses the normal 81-fold dynamic range over which this binding site is occupied (the pseudolinear range between 10% and 90% of target occupancy) to only 4-fold, leading to a much more sensitive concentration-occupancy curve.