A high-throughput screen for synthetic riboswitches reveals mechanistic insights into their function

Abstract

Riboswitches are RNA-based genetic control elements that regulate gene expression in a ligand-dependent fashion without the need for proteins. The ability to create synthetic riboswitches that control gene expression in response to any desired small-molecule ligand will enable the development of sensitive genetic screens that can detect the presence of small molecules, as well as designer genetic control elements to conditionally modulate cellular behavior. Herein, we present an automated high-throughput screening method that identifies synthetic riboswitches that display extremely low background levels of gene expression in the absence of the desired ligand and robust increases in expression in its presence. Mechanistic studies reveal how these riboswitches function and suggest design principles for creating new synthetic riboswitches. We anticipate that the screening method and design principles will be generally useful for creating functional synthetic riboswitches.

Figure 1. Diagram of the 5′-region of a synthetic riboswitch, the performance of the synthetic riboswitch, and the randomization strategy

A.) Sequence of a portion of the 5′-region of the parent synthetic riboswitch with 8-bases separating the aptamer (green) and the ribosome binding site (pink); the AUG start codon (peach) is highlighted. The aptamer is shown in the secondary structure predicted for the theophylline aptamer by mFold and confirmed experimentally. B.) Measures of the activity of the synthetic riboswitch shown in A. when cloned upstream of the IS10-lacZ gene fusion and expressed in E. coli. Right axis: β-galactosidase activity in the absence (open circle) or presence of theophylline (1-mM, closed circle). Activities are expressed in Miller units, and the standard errors of the mean are less than the diameters of the circles. Left axis: The activation ratio of the synthetic riboswitch (green bar), which is determined by taking the ratio of the activities in the presence and absence of theophylline. C.) Sequence diagram of the randomized synthetic riboswitches. The aptamer is shown in green, the randomized regions in light blue, the ribosome binding site in pink, and the AUG start codon in peach. Theoretical library sizes are shown in the circle.

Figure 2. Diagram of the high throughput assay

Candidate riboswitches are identified by plating cells onto selective media containing X-gal, but no theophylline. A robotic colony picker identifies the whitest colonies (lowest levels of β-galactosidase activity) and transfers the cells to a 96-well microtiterplate. The culture is grown overnight in selective media, split, and the clones are tested for β-galactosidase activity using the automated assay described in the text.

Figure 3. Analysis of libraries and results from screens

A.) Statistics for libraries assayed. B.-E.) Measures of the activities of the synthetic riboswitches identified in the high throughput screens. Each measurement is done in triplicate. For all panels: Right axis: β-galactosidase activity in the absence (open circle) or presence of theophylline (1-mM, closed circle). Activities are expressed in Miller units, and the standard errors of the mean are less than the diameters of the circles. Left axis: The activation ratio of the synthetic riboswitch (green bar), which is determined by taking the ratio of the activities in the presence and absence of theophylline.

Figure 4. Predicted mechanisms of action of synthetic riboswitches

A.) Predicted mechanism of action of clone 8.1. In the absence of theophylline (left), the 5′-region can adopt a highly folded structure that extensively pairs the region that includes ribosome binding site to part of the aptamer sequence (shown in dark blue). In the presence of theophylline (right), the secondary structure shifts, such that the ribosome binding site is exposed. The secondary structure shown for the theophylline aptamer predicted by mFold and is identical to the structure determined by NMR. B.) Predicted mechanism of action of clone 8.2. In this case, the region containing the ribosome binding site pairs to a different region of the aptamer in the “off” state (shown in red). This demonstrates that several motifs may function as synthetic riboswitches.

Figure 5. Results from covariance experiments

β-galactosidase activities in the absence of theophylline (open circles) for the parent synthetic riboswitch (clone 8.1) (left), a triple mutant that unpairs the region near the ribosome binding site (center), and a mutant that restores the pairing (right). Activities are expressed in Miller units (shown on the left axis); the standard errors of the mean are less than the diameters of the circles. For each construct, the predicted secondary structure is shown in the region near the ribosome binding site. The parent and covariant maintain the pairing and show low background levels of β-galactosidase activity. The mutant unpairs this region and leads to leaky expression in the absence of theophylline.

Figure 6. Model for synthetic riboswitch function

A.) Predicted structures and free energies of a portion of the 5′-region of clone 8.1 determined by mFold. To represent the free energies of the bound structures, we added the experimentally determined free energy of theophylline binding (−9.2 kcal/mol) to the free energy of the un-liganded structure determined by mFold since the secondary structure of the mTCT-8-4 aptamer does not change upon ligand binding. B.) Kinetic model for synthetic riboswitch function. In the “Off” state, the ribosome binding site is paired and translation is slow (represented by the pseudo-first order rate constant k_{1 obs}, which accounts for ribosome binding and translation). The “Off” state is proposed to be in equilibrium with the ligand-free “On” state, in which the ribosome binding site is unpaired and translation is relatively fast (represented by the pseudo-first order rate constant k_{2 obs}, which is much greater than k_{1 obs}). Since this state is not highly populated, background translation is minimal. Addition of ligand (L) shifts the equilibrium to the ligand-bound “On” state, in which the ribosome binding site is unpaired and translation is relatively fast (represented by the pseudo-first order rate constant k_{3 obs}, which is also much greater than k_{1 obs}).

Figure 7. Experiments to determine switching mechanism

A.) top: A thermodynamic model for riboswitch function. Newly synthesized RNA adopts a folded conformation that prevents translation (“Off”). Addition of theophylline can drive the conformation to the “On-L” conformation. bottom: A kinetic model in which a newly synthesized RNA adopts either an “Off” or an “On-L” conformation depending on whether ligand is present during transcription, however the “Off” and “On-L” conformations do not equilibrate. B.) Time course for appearance of β-galactosidase activity (measured by ONPG hydrolysis) for clone 8.1. Theophylline was added at t = 0 to a final concentration of 3 mM; significant activity appears at 200 s. C.) Time course for appearance of β-galactosidase activity (measured by ONPG hydrolysis) for clone 8.1. Theophylline was added at t = 0 to a final concentration of 3 mM; rifampicin was added at the times shown in the legend. Rifampicin does not eliminate β-galactosidase activity when added up to 40 s prior to the addition of theophylline, supporting the thermodynamic model shown in A.) and D.) in which theophylline can induce expression even in the absence of active transcription.