TASK-3 two-pore domain potassium channels enable sustained high-frequency firing in cerebellar granule neurons

Abstract

The ability of neurons, such as cerebellar granule neurons (CGNs), to fire action potentials (APs) at high frequencies during sustained depolarization is usually explained in relation to the functional properties of voltage-gated ion channels. Two-pore domain potassium (K(2P)) channels are considered to simply hyperpolarize the resting membrane potential (RMP) by increasing the potassium permeability of the membrane. However, we find that CGNs lacking the TASK-3 type K(2P) channel exhibit marked accommodation of action potential firing. The accommodation phenotype was not associated with any change in the functional properties of the underlying voltage-gated sodium channels, nor could it be explained by the more depolarized RMP that resulted from TASK-3 channel deletion. A functional rescue, involving the introduction of a nonlinear leak conductance with a dynamic current clamp, was able to restore wild-type firing properties to adult TASK-3 knock-out CGNs. Thus, in addition to the accepted role of TASK-3 channels in limiting neuronal excitability, by increasing the resting potassium conductance TASK-3 channels also increase excitability by supporting high-frequency firing once AP threshold is reached.

Figure 1.

TASK-3 KO mice exhibit a reduced potassium leak conductance. In situ hybridization data from adult wild-type (A, C) and TASK-3 KO (B, D) mouse brains comparing the distribution of TASK-3 (A, B) and TASK-1 mRNA (C, D). TASK-3 mRNA is absent from TASK-3 KO brains with no change in the expression of TASK-1 mRNA. Shown are neocortex (Cx), dentate gyrus (DG), caudate putamen (CPu), medial habenule (Hb), periglomerular (Pgl) and granule neurons (Obgr) of the olfactory bulb, reticular nucleus of the thalamus (RT), and CGNs. Scale bar, 2 mm. E, Comparison of mRNA levels between wild-type and TASK-3 KO cerebellum (real-time PCR) for seven K_2P subunits and the GABA_A receptor α6 subunit. The only significant difference between the genotypes was the absence of TASK-3 mRNA (asterisk). A similar pattern was observed for real-time PCR data in the forebrain (data not shown). Error bars indicate SEM. F, A typical voltage-clamp recording illustrating the standing outward potassium current recorded at −20 mV in a wild-type adult CGN. The command voltage has been maintained at −20 mV for at least 1 min before the amplitude of the non-inactivating component of this leak conductance was measured. The voltage was then ramped down to −110 mV in 800 ms to construct the current–voltage plots shown. G, These graphs compare the average current–voltage relationships for 34 wild-type CGNs (black trace) and 16 TASK-3 KO CGNs (gray trace).

Figure 2.

Alterations in CGN excitability associated with the TASK-3 KO. A, Voltage recordings from adult CGNs during current injection experiments comparing a wild type (black trace) and a TASK-3 KO (gray trace). The current injection protocol for both experiments is illustrated in the bottom trace. In the two examples illustrated, APs are elicited with a smaller current injection in the TASK-3 KO compared with the wild type. However, once AP threshold is passed, the TASK-3 KO CGN accommodates more profoundly than the wild-type CGN. At suprathreshold intensities, complete AP failure is observed by the end of a 300 ms current pulse in this TASK-3 KO CGN. In contrast, at the range of current injections examined, no such behavior was observed in the wild-type CGN. B, Subthreshold membrane voltage responses for wild-type and TASK-3 KO CGNs during current injection experiments. The left panel illustrates the voltage response during the experiments shown in A. The right panel plots the average response from 10 wild-type and 16 TASK-3 KO CGNs. C, AP frequency during current injections for the cells shown in A (left panel) and average responses across 10 wild-type and 16 TASK-3 KO CGNs (right panel). For the average responses, the current injection has been expressed relative to the threshold current value, and the AP frequency is normalized to the maximum response. Error bars indicate SEM.

Figure 3.

AP accommodation at threshold and suprathreshold levels of current injection are altered in the TASK-3 KO. A, At threshold current injections, the degree of AP accommodation is greater in TASK-3 KO CGNs compared with wild type. The peak amplitude of the first three APs is marked for the recordings from the two strains. Note that, in the chosen example, the TASK-3 KO has an RMP more hyperpolarized than the wild-type recording, but the threshold voltages were similar. B, Quantification of the reduction in AP height for the two strains at threshold depolarizations. The AP height has been normalized to first AP and averaged across 44 wild-type and 27 TASK-3 KO CGNs. Error bars indicate SEM. C, In this example, the wild-type CGN is capable of high-frequency AP firing during suprathreshold depolarization, but profound AP accommodation is apparent in the TASK-3 KO CGN. D, The accommodation index calculated at suprathreshold depolarizations is plotted against RMP for all wild-type (filled black circles), TASK-3 KO (filled red circles), and TASK-1 KO (open circles) recordings. Note the overlap in RMPs between genotypes and the large degree of accommodation that is only apparent in the TASK-3 KO recordings.

Figure 4.

AP accommodation in TASK-3 KO CGNs is not attributable to the depolarized RMP of TASK-3 KO CGNs. A, Example of voltage responses from an adult CGN recorded from a TASK-3 KO mouse that exhibits considerable AP accommodation at different imposed RMPs. B, Example of a wild-type CGN that only exhibits AP accommodation at depolarized potentials more positive than −50 mV. C, Quantification of the relationship between RMP and the normalized AP frequency in TASK-3 KO adult CGNs. At all imposed RMPs the output of the neurons declines at high stimulus intensities because of the accommodation phenotype. D, Quantification of the relationship between RMP and the normalized AP frequency in wild-type adult CGNs. AP accommodation only reduces the AP frequency at imposed RMPs more depolarized than −50 mV. Error bars indicate SEM.

Figure 5.

AP properties are altered in CGNs recorded from the TASK-3 KO. A, Average AP waveforms constructed from recordings in a wild-type (black trace) and TASK-3 KO (gray trace) adult CGN. These two traces illustrate the reduction in AP overshoot, but unaltered AHP in recordings form TASK-3 KO adult CGNs. The first derivative for these two APs is shown in gray. B, Phase plane plots of the APs shown in A, illustrating the similar AP threshold in the two waveforms, but reduced rate of AP rise and fall corresponding to a slower AP upstroke and repolarization in the TASK-3 KO CGN (red trace). C, Plots of the calculated AP overshoot and AHP in the wild-type (black circles; n = 49) and TASK-3 KO (gray circles; n = 29) populations. D, A scatter plot of the AP threshold against AP width has been constructed for all wild type (black circles) and TASK-3 KO (gray circles) data. All-point histograms were then constructed from the AP width data, and the distributions for wild type and TASK-3 KO data were well described by a single Gaussian distribution (solid and gray lines, respectively). From these data, it is clear that the AP width in TASK-3 KO CGNs was broader than that found in the wild-type population. E, Plot of the maximum rate of rise against the maximum rate of fall calculated from the phase plane plots for wild-type (black circles) and TASK-3 KO (gray circles) APs. Linear regressions for these two populations are shown as solid black and red lines. The dashed line indicates the predicted linear regression if both rates exhibit similar distributions. F, Continuous voltage records from a wild-type (top trace) and TASK-3 KO CGN (bottom trace) illustrating the pattern of APs elicited at threshold depolarization. G, Scatter plot illustrating the change in AP width at the observed instantaneous frequencies calculated in wild-type (black) and TASK-3 KO (gray) CGNs. The solid lines are the result of linear regression in each population.

Figure 6.

Functional properties of voltage-gated channels in adult CGNs. A, Current traces showing the rising phase of a voltage-gated sodium conductance in response to a maximal activation elicited after a voltage step from −100 to 0 mV (gray lines) recorded from a wild-type (black trace) and a TASK-3 KO (gray trace) adult CGN. B, Plot of 10–90% rise times calculated from current traces of the type shown in A from wild-type (black circles; n = 6) and TASK-3 KO (gray circles; n = 6) adult CGNs. C, A series of voltage-step protocols (gray traces) were applied to examine the voltage dependence of sodium channel activation (Na_T). A Boltzmann function was fitted to the peak conductance data for all cells examined to estimate both the V_0.5 and rate of activation. D, Another series of voltage-step protocols (gray traces) examined the voltage dependence of activation for the sustained outward potassium currents (K_V) recorded in the presence of 500 nm TTX, and once again a Boltzmann function was fitted to the conductance data to estimate the V_0.5 and rate of inactivation. E, Another series of voltage-step protocols (gray traces) examined the voltage dependence of activation for the transient potassium currents (K_A) recorded in the presence of 500 nm TTX and 1 mm TEA, and once again a Boltzmann function was fitted to the conductance data to estimate the V_0.5 and rate of inactivation. F, Bar graph illustrating the relative contribution of the Na_T, K_V, K_A, and K_2P conductance in wild-type CGNs. The conductance of the voltage-gated currents was estimated at 0 mV using the Boltzmann functions in A–C. The K_V component represented the TEA-sensitive component of the steady-state outward current, whereas the K_2P component was estimated from the TEA-insensitive outward potassium currents shown in Figure 7. G, Same conventions as D but for TASK-3 KO CGNs. Note that the only component that has significantly changed is the K_2P-like TEA-insensitive conductance reflecting the loss of TASK-3 channels.

Figure 7.

Response of a TASK-3-mediated conductance to sustained AP firing. A, Whole-cell voltage-clamp recordings were made from wild-type (black trace) and TASK-3 KO CGNs during which AP waveforms, recorded from a wild-type CGN, were used to control the command voltage of the patch-clamp amplifier. These recordings were also made in the presence of TTX, TEA, and 4-AP, and particular attention was paid to eliminating the resistive and capacitive errors associated with these recordings (see Materials and Methods). Current–voltage plots are shown for a wild-type (black) and TASK-3 KO (gray) CGN. Superimposed on this plot is the predicted GHK relationship for a 1 and 5 nS potassium conductance (dashed lines). B, Voltage-clamp recording from tsA-201 cells after recombinant expression of TASK-3. The command voltage of the patch-clamp amplifier was once again controlled by AP waveforms previously recorded from an adult wild-type CGN. It is apparent that a TASK-3-mediated conductance is elicited by these AP waveforms. Moreover, when the current–voltage relationship of this response is plotted, a clear hysteresis loop can be observed similar to that previously seen in wild-type CGNs (compare with A). However, this hysteresis loop was completely absent from untransfected cells (gray trace). The arrows indicate the rising and falling phase of the AP.

Figure 8.

Rescue of AP accommodation by insertion of a nonlinear leak conductance in TASK-3 KO adult CGNs. A, Results from a dynamic current-clamp experiment performed on a TASK-3 KO adult CGN at threshold levels of depolarization in the presence and absence of a 5 nS GHK-type leak. Note that the RMP has hyperpolarized in the presence of a 5 nS nonlinear leak, and therefore, more current is required to reach threshold. B, Quantification of the AP height before and during injection of a 5 nS nonlinear leak in TASK-3 KO adult CGNs. The AP height has been normalized to the first AP in the burst. Error bars indicate SEM. C, Plot of the AP height and AP width in each experiment in which a 5 nS nonlinear leak has been inserted. The arrows link the estimated values in each experiment before and during insertion of the leak conductance. D, Results from a dynamic current-clamp experiment performed on a TASK-3 KO CGN that exhibited complete AP accommodation during a suprathreshold depolarization. In the presence of a 5 nS nonlinear leak conductance waveform, we restored the ability of this CGN to fire during sustained depolarization. The middle trace was performed with the dynamic current-clamp waveform implemented, whereas the two traces on either side were obtained immediately before and after the waveform was present. Note how the RMP hyperpolarizes in response to the nonlinear leak conductance. E, Illustration of how the recorded voltage (black trace; V_m) influences the injected current (gray trace; I_com) when the dynamic current-clamp waveform is implemented with a 5 nS GHK-type leak.