Agonism/antagonism switching in allosteric ensembles

Abstract

Ligands for several transcription factors can act as agonists under some conditions and antagonists under others. The structural and molecular bases of such effects are unknown. Previously, we demonstrated how the folding of intrinsically disordered (ID) protein sequences, in particular, and population shifts, in general, could be used to mediate allosteric coupling between different functional domains, a model that has subsequently been validated in several systems. Here it is shown that population redistribution within allosteric systems can be used as a mechanism to tune protein ensembles such that a given ligand can act as both an agonist and an antagonist. Importantly, this mechanism can be robustly encoded in the ensemble, and does not require that the interactions between the ligand and the protein differ when it is acting either as an agonist or an antagonist. Instead, the effect is due to the relative probabilities of states prior to the addition of the ligand. The ensemble view of allostery that is illuminated by these studies suggests that rather than being seen as switches with fixed responses to allosteric activation, ensembles can evolve to be "functionally pluripotent," with the capacity to up or down regulate activity in response to a stimulus. This result not only helps to explain the prevalence of intrinsic disorder in transcription factors and other cell signaling proteins, it provides important insights about the energetic ground rules governing site-to-site communication in all allosteric systems.

Fig. 1.

Three-domain allosteric protein. (A) Schematic representation of a three-domain allosteric protein comprised of domains I, II, and III that can bind ligands A, B, and C, respectively. Each domain is coupled to the other two domains through an interaction energy (Δg_int ,i-j), which is schematically represented as a shaded area between domains. (B) Free energy contributions, Boltzmann statistical weights (S_i), and probabilities of each microstate in the ensemble (Note: K_i = Exp[-ΔG_i/RT] and ϕ_i-j = Exp[-Δg_int ,i-j/RT]). Each microstate represented in the left column is either completely high-affinity (RRR), partially high-affinity (TRR, RTR, RRT, RTT, TRT, TTR), or completely low-affinity (TTT). The free energy contributions come from the transition of each domain to the low-affinity T state () plus the energy of breaking the interactions between domains (). Note: For presentation purposes only, the T states for each domain are depicted as being disordered. In reality, both T and R can be folded and competent to bind ligand. The only requirement is that one of those states (by convention, R) binds ligand with higher affinity. (C) A specific case demonstrating an agonistic allosteric response. Shown are microstates that are significantly populated (i.e., > 3%) before (Left) and after (Right) the addition of ligand A. In the absence of ligand A, the summed probability of microstates with domain III in the R state (i.e., the active microstates—domain III colored yellow) are only marginally populated (approximately 20%). Upon addition of ligand A, redistribution of the ensemble results in a positive shift in the population of these microstates (approximately 73% = 43%+30%), which corresponds to an agonistic response (i.e.,CR_III,A = +0.06). The parameters used are ΔG₁ = -1.7, ΔG₂ = 2.0, ΔG₃ = -0.9, Δg₁₂ = -2.3, Δg₂₃ = 0.1, Δg₁₃ = 1.5, and Δg_Lig,A = -5.0 all in kcal/mol. (D) A specific case demonstrating an antagonistic allosteric response. Unlike the case of agonism, the active microstates are significantly populated in the absence of ligand A (approximately 95% = 89%+6%). Upon addition of ligand A, redistribution of the ensemble results in a negative shift in the population of these microstates (35%), which corresponds to an antagonistic response (i.e.,CR_III,A = -0.06). The parameters used are ΔG₁ = -2.1, ΔG₂ = 1.0, ΔG₃ = 1.2, Δg₁₂ = -1.7, Δg₂₃ = 0.6, Δg₁₃ = -2.7, and Δg_Lig,A = -5.0, all in kcal/mol.

Fig. 2.

Specific thermodynamic architectures can produce agonism/antagonism switching. Example of a thermodynamic architecture that produces agonism-antagonism switching: ΔG₁ = -6.75, ΔG_2,B=0(1) = -4.4, ΔG_2,B>0(2) = 0.6, ΔG₃ = -2.7, Δg₁₂ = 6.8, Δg₂₃ = 4.8, Δg₁₃ = -1.9, and Δg_Lig,A = -5.0 kcal/mol. Individual free energies and populations for each microstate showing an (A) agonistic and (B) antagonistic response. Shown for both cases (Left) are the free energies of each microstate in the absence (blue bars) and presence (red bars) of ligand A (depicted as blue circles). Shown also for each case are the populations of microstates in the absence (Right, Top) and the presence (Right, Bottom) of ligand A. For the case of agonism (A), the summed population of microstates with domain III in the R state rises from 3% to 51%, while for antagonism (B) those microstates decrease from 94% to 58%. C. Coupling response (CR) dependence on stability of domains I and II (holding all other variables constant). Position 1 (yellow circle at local maximum) exhibits agonistic response to ligand A in the absence of ligand B. Position 2 (yellow circle at local minimum) exhibits antagonistic response to ligand A in the presence of ligand B (Δg_Lig,B = -5.0kcal/mol).

Fig. 3.

Energetic rules for agonism-antagonism switching. (A) Plot of interaction parameters (i.e., Δg₁₂, Δg₂₃, and Δg₁₃) that exhibit significant agonistic (> 35%) and antagonistic (< -35%) responses within a single architecture (blue nodes labeled 1–4). Each node is represented by three + or − signs that correspond to the sign of the coupling energies, Δg₁₂, Δg₂₃, and Δg₁₃, respectively. For contrast, parameter combinations that do not exhibit switching are shaded in gray (See text for details). (B) Schematic representation of the allosteric interdomain coupling for each of the switch-competent nodes in (A) with each node numbered and represented by three + or −. Red and blue arrows indicate an antagonistic and an agonistic relationship between two domains, respectively. The red and blue arrow indicates that domain III is impacted both positively and negatively through the direct and indirect effects, as described in text. Note: The color of the arrows connecting domains II and III refer to the overall impact on domain III from stabilization of domain I. For example, in Node 3 stabilization of domain I destabilizes domain II (making the arrow red). However, that destabilization of domain II (because of negative coupling to domain III) has the effect of stabilizing domain III (making the arrow to domain III blue). (C) Schematic representation of the allosteric interdomain coupling for each of the switch-incompetent nodes in (A). The coloring scheme is similar to (B) and demonstrates that switch-incompetent architectures produce either committed agonists (+++, −−+) or committed antagonists (+−−, −+−) because the direct and indirect effects are of the same sign.

Fig. 4.

Switching-competence is maximized when regulatory domains are predominantly populating low affinity or ID states. Plot of the probability of domain I being in the R state (i.e., P_I,R = P_RRR + P_RTR + P_RRT + P_RTT) vs. probability of domain II being in the R state (i.e. P_II,R = P_RRR + P_TRR + P_RRT + P_TRT) in the absence of ligand for switching-competent architectures. Colors indicate the magnitude of the change in probability for agonist and antagonist switching: yellow (± 20%), orange (± 30%), and red (± 40%); i.e., the architecture must exhibit an agonistic and an antagonistic response from ligand A exceeding the positive and negative thresholds in the absence and presence of ligand B (or vice versa). Maximum switching responses (dashed boxes) are observed in two regions, where either domain I only (i.e., Region 1) or both domains I and II (i.e. Region 2) are predominantly populating the T state (or in the case of ID proteins, the unfolded (U) state).