Correction for Inhibition Leads to an Allosteric Co-Agonist Model for Pentobarbital Modulation and Activation of α1β3γ2L GABAA Receptors

Abstract

Background: Pentobarbital, like propofol and etomidate, produces important general anesthetic effects through GABAA receptors. Photolabeling also indicates that pentobarbital binds to some of the same sites where propofol and etomidate act. Quantitative allosteric co-agonist models for propofol and etomidate account for modulatory and agonist effects in GABAA receptors and have proven valuable in establishing drug site characteristics and for functional analysis of mutants. We therefore sought to establish an allosteric co-agonist model for pentobarbital activation and modulation of α1β3γ2L receptors, using a novel approach to first correct pentobarbital activation data for inhibitory effects in the same concentration range.

Methods: Using oocyte-expressed α1β3γ2L GABAA receptors and two-microelectrode voltage-clamp, we quantified modulation of GABA responses by a low pentobarbital concentration and direct effects of high pentobarbital concentrations, the latter displaying mixed agonist and inhibitory effects. We then isolated and quantified pentobarbital inhibition in activated receptors using a novel single-sweep "notch" approach, and used these results to correct steady-state direct activation for inhibition.

Results: Combining results for GABA modulation and corrected direct activation, we estimated receptor open probability and optimized parameters for a Monod-Wyman-Changeux allosteric co-agonist model. Inhibition by pentobarbital was consistent with two sites with IC50s near 1 mM, while co-agonist model parameters suggest two allosteric pentobarbital agonist sites characterized by KPB ≈ 5 mM and high efficacy. The results also indicate that pentobarbital may be a more efficacious agonist than GABA.

Conclusions: Our novel approach to quantifying both inhibitory and co-agonist effects of pentobarbital provides a basis for future structure-function analyses of GABAA receptor mutations in putative pentobarbital binding sites.

Fig 1. Pentobarbital shifts GABA concentration-responses leftward.

A) Traces are from a single oocyte expressing α1β3γ2L GABA_A receptors. Bars over traces represent GABA application with concentration labeled in μM. The lower set of traces were activated by GABA supplemented with 236 μM PB. B) Combined normalized (to 1 mM GABA response) peak current results from all oocytes (n ≥ 5) is plotted as mean ± sem. Open symbols represent responses to GABA alone and solid symbols represent responses to GABA + PB.

Fig 2. Pentobarbital directly activates and Inhibits α1β3γ2L GABA_A receptors.

Top) Traces are from a single oocyte expressing α1β3γ2L GABA_A receptors. The first trace is the response to 1 mM GABA (solid bar above trace). Other traces were elicited with PB applications (open bars above traces) at concentrations labeled in μM. At PB concentrations above 1 mM, traces develop “tail” currents immediately after discontinuation of PB exposure. Bottom) Both early peak PB-elicited currents and the “trough” currents just prior to the “tail” were normalized to 1 mM GABA controls. Mean (± sem, n = 5) results are plotted. Squares represent peak currents and triangles represent trough currents.

Fig 3. Identifying a PB concentration that maximally enhances without inhibiting currents elicited with 1 mM GABA.

Top) Traces are from a single oocyte expressing α1β3γ2L GABA_A receptors. The left trace was elicited with 1 mM GABA, the middle trace with 1 mM GABA + 100 μM PB, and the right trace with 1 mM GABA + 500 μM PB. Note the absence of significant tail current with 100 μM PB and the large tail current with 500 μM PB. Bottom) Peak currents elicited with 1 mM GABA + 100 μM PB (n = 4) are 18 ± 4.4% (mean ± sd) larger than controls (p < 0.001, one way ANOVA). Peak currents elicited with 1 mM GABA + 500 μM PB are similar to controls. Based on these results, we chose 1 mM GABA + 100 μM PB as the control conditions for notch inhibition studies.

Fig 4. PB “notch” inhibition and correction of PB activation.

A) Traces are from a single oocyte expressing α1β3γ2L GABA_A receptors. Bars above the traces indicate exposure to 1 mM GABA + 100 μM PB (open bars) and 1 mM GABA + high PB (solid bars, concentration indicated in μM). Dashed lines indicate both baselines and interpolated curves fitted to the control phases of the traces. Black vertical arrows represent the inhibited current measured at steady-state inhibition, and the combined black + red vertical arrows represent the interpolated maximal activation current used to normalize steady-state inhibition. B) Combined normalized data from notch experiments (mean ± sd, n ≥ 5 at each concentration) is plotted against [PB]. The line through data represents a logistic fit: IC₅₀ = 1.13 mM (95% confidence interval = 1.03 to 1.24); Hill slope = 1.53 ± 0.088. C) Normalized trough values from Fig 2 (open triangles) were divided by fractional inhibition data from Fig 4B, resulting in corrected PB activation data (solid blue squares). Error bars represent propagated standard deviations. A logistic fit (Eq 1) to the corrected PB activation data (normalized to 1 mM GABA response) is plotted as a solid blue line: Maximum = 0.96 ± 0.092; EC₅₀ = 0.94 mM (95% confidence interval = 0.73 to 1.2 mM); Hill slope = 2.2 ± 0.53. Multiplying the PB-dependent activation function x the PB-dependent inhibition function (dashed red line) generates a biphasic dose response (dashed black line) that fits the original steady-state PB activation (trough) data.

Fig 5. A Monod-Wyman-Changeux co-agonist model for PB activation and GABA modulation in α1β3γ2L GABA_A receptors.

Estimated P_open values were generated from average data in Figs 1B and 4C and fitted with a function describing MWC co-agonism with two equivalent GABA sites and n equivalent PB sites (Eq 2 in Methods). Fitted values were: L₀ = 1100 ± 460; K_G = 33.6 ± 6.2 μM; c = 0.014 ± 0.0035; K_PB = 5.3 ± 8.6 mM; d = 0.0026 ± 0.0061; n = 1.7 ± 0.45. A) Estimated P_open values derived from Fig 1B are shown (open symbols are responses to GABA alone and solid symbols are GABA supplemented with 236 μM PB). Lines through data represent the fitted MWC model. B) Estimated P_open values derived from Fig 4C (corrected PB activation responses) are plotted as open triangles. The line through data points represents the fitted MWC model.