Dual Effects of TARP γ-2 on Glutamate Efficacy Can Account for AMPA Receptor Autoinactivation

Abstract

Fast excitatory transmission in the CNS is mediated mainly by AMPA-type glutamate receptors (AMPARs) associated with transmembrane AMPAR regulatory proteins (TARPs). At the high glutamate concentrations typically seen during synaptic transmission, TARPs slow receptor desensitization and enhance mean channel conductance. However, their influence on channels gated by low glutamate concentrations, as encountered during delayed transmitter clearance or synaptic spillover, is poorly understood. We report here that TARP γ-2 reduces the ability of low glutamate concentrations to cause AMPAR desensitization and enhances channel gating at low glutamate occupancy. Simulations show that, by shifting the balance between AMPAR activation and desensitization, TARPs can markedly facilitate the transduction of spillover-mediated synaptic signaling. Furthermore, the dual effects of TARPs can account for biphasic steady-state glutamate concentration-response curves-a phenomenon termed "autoinactivation," previously thought to reflect desensitization-mediated AMPAR/TARP dissociation.

Keywords: EPSC; GluA1; cerebellar granule cell; diffusion model; kinetic model; short-term plasticity; single-channel; spillover; subconductance; synaptic.

Graphical abstract

Figure 1

γ-2 Has Opposite Effects on Glutamate Potency for Activation and Desensitization (A) Representative currents (–60 mV) elicited by fast applications of glutamate to outside-out patches from HEK293 cells transfected with GluA1 (left) or GluA1/γ-2 (right). (B) Currents elicited by 10 mM glutamate following pre-desensitization by a range of lower glutamate concentrations. (C) Pooled data fit with the Hill equation showing opposite γ-2-induced shifts in GluA1 potency for activation (filled circles) and desensitization (open circles). Symbols indicate mean and error bars indicate SEM. (D) Pooled data showing glutamate EC₅₀ for peak currents and glutamate IC₅₀ for pre-exposure. Bars show mean and error bars show SEM. (E) Representative GluA1/γ-2 currents. Inset: peak and steady-state concentration-response curves from the illustrated records. Note the inflection in the steady-state curve. (F) Pooled data (n = 6 patches). Peak currents were well described by a single Hill function, and steady-state currents were best described by a double Hill function. Error bars denote SEM. ^∗∗p < 0.01, ^∗∗∗p < 0.001 (Welch t test). See also Figure S1.

Figure 2

Measures of Conductance, Polyamine Block, and Kainate Efficacy Suggest Maintained AMPAR/TARP Association following Desensitization (A) Representative GluA1/γ-2 I-V data. Peak and steady-state currents are scaled between 0 and –60mV. (B) Conductance-voltage (G-V) plots of peak (GluA1 with- and without γ-2) and steady-state responses (GluA1/γ-2 only). Symbols indicate mean and error bars indicate SEM. Dashed lines are fits of the Boltzmann equation (Supplemental Experimental Procedures), from which values of voltage of half-maximal block (V_1/2) were determined. The steady-state current of GluA1 alone was too small to analyze. (C) Pooled data showing V_1/2 of spermine block (one-way ANOVA, F_{2, 8.7} = 311.53, p < 0.0001). Bars indicate mean and error bars indicate SEM. (D) Representative averaged glutamate-activated GluA1/γ-2 current (82 applications). Non-stationary fluctuation analysis (NSFA) was applied to the first 95% of the decay (inset, gray shading) and compared with stationary fluctuation analysis (SFA) of steady-state currents (red shading). (E) Representative current variance plots for the decaying component (NSFA, filled symbols) and steady-state component (SFA, open symbol), yielding the indicated channel conductance estimates. (F) Pooled data showing weighted mean channel conductance (one-way ANOVA, F_{2, 18.9} = 14.51, p = 0.00015). Bars indicate mean and error bars indicate SEM. (G and H) Representative traces (G) and scaled responses (H) showing 10 mM glutamate- and 1 mM kainate-evoked currents as GluA1/γ-2 recovers from desensitization induced by 10 mM glutamate. (I) Pooled data from four to five patches showing that the time course of recovery is the same for both agonists. ^∗∗p < 0.01, ^∗∗∗p < 0.001 (Welch t test).

Figure 3

A Basic Kinetic Scheme Can Predict Biphasic Steady-State Concentration-Response Relationships (A) A simple model, scheme 1, with two agonist binding steps (R0 → R1→ R2), two desensitized states (D1 and D2), and two open states (O1 and O2) with an equal conductance. (B) Using rates based on previously published values for GluA1 (Robert and Howe, 2003; k_on = 2 × 10⁷ M⁻¹s⁻¹, k_off = 9,000 s⁻¹, α₁ = α₂ = 3,100 s⁻¹, β₁ = β₂ = 8,000 s⁻¹, δ₁ = δ₂ = 1,800 s⁻¹, γ₁ = γ₂ = 35 s⁻¹), scheme 1 generates sigmoidal concentration response curves for both peak and steady-state activation. (C) Decreasing occupancy of D1 relative to D2 (for example, increasing γ₁ or δ₂) or increasing the occupancy of O1 relative to O2 (for example, increasing α₂ or β₁) leads to biphasic steady-state concentration-response curves with minimal effects on peak concentration-response curves.

Figure 4

Concentration Dependence of GluA1/γ-2 Entry into and Exit from Desensitized States (A) Representative normalized GluA1/γ-2 currents (–60 mV) showing markedly slowed desensitization at low glutamate concentrations (time constant of desensitization [τ_des] is 2.8 ms with 10 mM glutamate and 8.9 ms with 30 μM). (B) Representative records showing the time course of entry into desensitization (jumping between control, 10 μM glutamate, and 10 mM glutamate). Three selected pulse protocols are illustrated. The dashed line is an exponential fit, giving a time constant of 26.6 ms. (C) GluA1 (blue) and GluA1/γ-2 (black) desensitization kinetics measured using protocols of the type shown in (A) or (B) (n = 5–8; filled or open symbols, respectively). Symbols indicate mean and error bars indicate SEM. (D) Recovery from desensitization by 10 μM glutamate measured using a two-pulse protocol. Three selected pulse protocols are illustrated. The dashed line is an exponential fit, giving a time constant of 119 ms. (E) Monoexponential Hodgkin-Huxley fits of pooled averaged time courses of GluA1 recovery from desensitization by 10 μM, 100 μM, or 10 mM glutamate (n = 7). Recovery profiles are fitted with a single time constant (120 ms) with a variable m (Experimental Procedures). (F) GluA1/γ-2 recovery from desensitization by a range of glutamate concentrations. Data were globally fitted with a double exponential function, giving fast time constant of recovery (τ_f) = 74 ms and slow time constant of recovery (τ_s) = 390 ms. Inset: the kinetics of recovery from desensitization; the weighted time constant of recovery (τ_w) is not markedly concentration-dependent.

Figure 5

γ-2 Increases the Efficacy of Glutamate at Partially Liganded AMPARs (A) Schematic of slow NBQX unbinding, which allows the time course of channel activation by glutamate to be observed. (B) Normalized representative currents recorded following 50 μM NBQX/10 mM glutamate exchange (with 50 μM cyclothiazide). γ-2 speeds the current onset (enlargement of the highlighted section), reducing the Hodgkin-Huxley exponent (m) required to fit the records (dashed red lines). (C) Pooled data from H-H fits. γ-2 accelerated the onset of NBQX/glutamate currents for each AMPAR subtype. Two-way ANOVA indicated significant main effects for AMPAR type (F_{2, 31} = 48.43, p < 0.0001) and for γ-2 (F_{1, 31} = 187.97, p < 0.0001) but no interaction between AMPAR type and TARP (F_{2, 31} = 0.41, p = 0.67). ^∗∗p < 0.01, ^∗∗∗p < 0.001 (Welch t test). Symbols indicate mean and error bars indicate SEM. (D) Representative single-channel NBQX/glutamate records displaying four discrete conductance levels. Measured conductance values are indicated. (E) Normalized probability densities for closed, O1, O2, O3, and O4 conductance states, pooled from 560 identified conductances in 134 NBQX/glutamate sweeps. The dashed red lies are Gaussian fits. (F) Normalized, pooled GluA1/γ-2 NBQX/glutamate current (n = 6). Data are fit (dashed red line) using the scheme shown in (A) (k_NBQX, 19 s^–1), with the mean estimates of the four conductance states (O1, 3.7 pS; O2, 16.1 pS; O3, 30.6 pS; O4, 38.6 pS). See also Figure S2.

Figure 6

A Revised Kinetic Scheme Can Approximate Multiple Aspects of GluA1/γ-2 Behavior (A) Scheme 2 is a modified form of scheme RH, with mechanistic changes highlighted (red) and assigned conductance levels (green). (B–D) A single set of rates within scheme 2 can simultaneously approximate (dashed red lines) the three concentration response relationships (B), desensitization kinetics (C), and recovery kinetics (D) of GluA1/γ-2. Symbols indicate mean and error bars indicate SEM. The following rate constants were used: k₁ = 1.3 × 10⁷ M^–1s^–1, k_–1 = 3,000 s^–1, α = 1,000 s^–1, β = 6,000 s^–1, δ₁ = 1,200 s^–1, γ₁ = 16 s^–1, δ₂ = 1,300 s^–1, γ₂ = 3,900 s^–1, δ₃ = 250 s^–1, δ₀ = 0.48 s^–1, γ₀ = 4.4 s^–1, k_–2 = 63 s^–1, and k_–3 = 630 s^–1. See also Figure S3.

Figure 7

Co-expression of γ-2 Reduces Inhibition of GluA1-Mediated Charge Transfer by Background Glutamate and Is Predicted to Enhance Charge Transfer by Spillover (A) Simulated responses of GluA1 (scheme RH, left) and recorded GluA1 currents (right) in response to two 1-ms pulses of 10 mM glutamate (100 Hz), with and without background application of 1 μM glutamate. Charge transfer was measured as the area under the curve. (B) As for (A) but for GluA1/γ-2, simulated using scheme 2, and for GluA1/γ-2 currents. (C) Bar chart showing that simulations and data are in agreement, with ∼4-fold less glutamate-mediated reduction in charge transfer for γ-2-containing receptors than for GluA1 alone. Bars indicate mean and error bars indicate SEM. (D and E) Responses of GluA1 (scheme RH) and GluA1/γ-2 (scheme 2) to simulated synaptic glutamate waveforms (Nielsen et al., 2004). The concentration profiles used represent (D) fusion of a single vesicle either locally or at the nearest-neighbor active zone or (E) action potential-evoked release causing prolonged spillover, either with or without local release. Spillover or nearest-neighbor charge as a percentage of direct or local charge is indicated. ^∗∗∗p > 0.001 (Welch t test). See also Figure S4.