Gastrodin inhibits allodynia and hyperalgesia in painful diabetic neuropathy rats by decreasing excitability of nociceptive primary sensory neurons

Abstract

Painful diabetic neuropathy (PDN) is a common complication of diabetes mellitus and adversely affects the patients' quality of life. Evidence has accumulated that PDN is associated with hyperexcitability of peripheral nociceptive primary sensory neurons. However, the precise cellular mechanism underlying PDN remains elusive. This may result in the lacking of effective therapies for the treatment of PDN. The phenolic glucoside, gastrodin, which is a main constituent of the Chinese herbal medicine Gastrodia elata Blume, has been widely used as an anticonvulsant, sedative, and analgesic since ancient times. However, the cellular mechanisms underlying its analgesic actions are not well understood. By utilizing a combination of behavioral surveys and electrophysiological recordings, the present study investigated the role of gastrodin in an experimental rat model of STZ-induced PDN and to further explore the underlying cellular mechanisms. Intraperitoneal administration of gastrodin effectively attenuated both the mechanical allodynia and thermal hyperalgesia induced by STZ injection. Whole-cell patch clamp recordings were obtained from nociceptive, capsaicin-sensitive small diameter neurons of the intact dorsal root ganglion (DRG). Recordings from diabetic rats revealed that the abnormal hyperexcitability of neurons was greatly abolished by application of GAS. To determine which currents were involved in the antinociceptive action of gastrodin, we examined the effects of gastrodin on transient sodium currents (I(NaT)) and potassium currents in diabetic small DRG neurons. Diabetes caused a prominent enhancement of I(NaT) and a decrease of potassium currents, especially slowly inactivating potassium currents (I(AS)); these effects were completely reversed by GAS in a dose-dependent manner. Furthermore, changes in activation and inactivation kinetics of I(NaT) and total potassium current as well as I(AS) currents induced by STZ were normalized by GAS. This study provides a clear cellular basis for the peripheral analgesic action of gastrodin for the treatment of chronic pain, including PDN.

Figure 1. Structures of 4-hydroxybenzyl alcohol 4-O-beta-D-glucopyranoside (gastrodin or GAS).

Figure 2. Analgesic effect of GAS on the mechanical allodynia and thermal hyperalgesia induced by STZ injection.

(A) (left) Average random blood glucose levels in control (n = 15) and diabetic rats (n = 15) for up to 35 d after STZ injection. The rats developed hyperglycemia from the 3^rd day after STZ injection. (middle and right) Mechanical allodynia and thermal hyperalgesia developed in diabetic rats (n = 20) but not control rats (n = 20). Note that mechanical paw withdrawal threshold (PWT) and thermal paw withdrawal latency (PWL) were reduced from 3^rd day following STZ injection. (B, C) Intraperitoneal administration of GAS (5, 10 and 20 mg/kg body weight) attenuated mechanical allodynia (B) and thermal hyperalgesia (C) induced by STZ in a dose-dependent manner (n = 15). Concentration-response curves of GAS on mechanical allodynia and thermal hyperalgesia are shown in the right panels of (B) and (C), respectively. (D) The same concentrations of GAS were not effective on basal mechanical (left panel) and thermal (right panel) nociception in control rats (n = 5). (E) GAS did not exert any obvious effect on the hyperglycemia in diabetic rats. All data are represented as mean ± SEM. * represents a significant difference between diabetic and control groups (n = 12) by a one-way ANOVA. + represents a significant difference between diabetic groups and diabetic + GAS groups by a one-way ANOVA.

Figure 3. The inhibitory effect of GAS on the hyperexcitability of small DRG neurons in diabetic rats

. (A) Representative traces showing the spike firings in response to a depolarizing current step in capsaicin-sensitive small DRG neurons from control and diabetic rats. Note that the traces before and after GAS application in each group were from the same neuron. (B) Quantitative analysis showing that GAS (n = 7) at a concentration of 300 µM remarkably reduced the increased firing frequency in diabetic small DRG neurons (upper panel) (n = 10). The reduction of the latency of first spike induced by STZ (n = 10) was normalized by GAS (n = 7, lower panel). * represents a significant difference between diabetic and control groups by a Student’s t test. ^# represents a significant difference between diabetic groups and diabetic + GAS groups by a paired-samples t test. All data are represented as mean ± S.E.M.

Figure 4. GAS inhibited I _NaT in capsaicin-sensitive DRG neurons from diabetic rats.

(A) Representative traces of I _NaT recorded from a control (upper panel) and diabetic (lower panel) small DRG neuron. The protocol to record I _NaT is shown at the bottom. (B) Representative traces of I _NaT show that GAS (100, 300, 500 µM, and 1 mM) reversibly produced a prominent inhibition of I _NaT in diabetic small DRG neurons. (C) Quantitative analysis shows that inhibition of the peak current densities of I _NaT by GAS was dose-dependent (n = 10). (D) Concentration-response curve of GAS on I _NaT yielded an EC₅₀ of GAS at 0.24±0.003 mM (n = 8). (E) I-V relations of I _NaT in small DRG neurons from control (n = 25, open circles), diabetic (n = 30, filled circles) and diabetic +300 µM GAS (n = 10, open triangles) groups. Note that I-V curves shifted leftward in diabetic rats and GAS treatment eliminated this shift. (F) The voltage-dependent activation and the steady-state inactivation curves of I _NaT in small DRG neurons from control (n = 8 and 6, blue), diabetic (n = 6 and 7, black) and diabetic + GAS (n = 6 and 7, red) groups. (G) The time constants of activation (left panel) and inactivation (right panel) of I _NaT are plotted as a function of membrane potentials. Both time constants were significantly decreased in diabetic neurons (n = 8). This alteration was reversed by GAS (300 µM) (n = 6). (H) GAS has no effect on I _NaT in control DRG neurons (n = 5). (I) Double immunofluorescent staining shows that the biocytin-containing recorded neuron (arrow, red, left panel) is TRPV1-immunoreactive (green, middle panel). Scale bar: 100 µm. *represents a significant difference between diabetic and control groups by a one-way ANOVA. ^#represents a significant difference between diabetic groups and diabetic + GAS groups by a one-way ANOVA. All data are represented as mean ± S.E.M.

Figure 5. Diabetes reduced total Kv current in capsaicin-sensitive DRG neurons.

(A) Representative traces of potassium currents were evoked by 700 ms depolarizing commands from 0 mV to 50 mV. These panels show total Kv current (a), non-inactivating potassium current (b) and I _AS (a-b), respectively. The holding potential was −80 mV. The total Kv current (a) was recorded with a 1s prepulse to −120 mV. The non-inactivating potassium current was obtained by a test pulse preceded by a 1 s prepulse to −40 mV. I _AS is the difference current between (a) and (b). (B) The histogram shows that the peak amplitude of total Kv current and I _AS (n = 24 vs 22) as well as the non-inactivating potassium current (n = 11 vs 14) was greatly reduced after diabetes (P<0.05). (C) I-V relations (upper panel) and voltage-dependent activation curves (lower panel) of peak total Kv current were evaluated from diabetic (n = 18 and 5, filled circles) and control (n = 12 and 5, opened circles) neurons. (D) I-V relations (upper panel) and voltage-dependent activation curves (lower panel) of steady-state total Kv current are shown. (E) The time constants for the activation of total Kv current (upper panel) are plotted as a function of membrane potential (n = 8 vs 6). In the lower panel, the time constants of inactivation are plotted as a function of membrane potential. τ₁ is the slower time constant. τ₂ is the faster time constant. * represents a significant difference between diabetic and control groups by a one–way ANOVA. All data are represented as mean ± S.E.M.

Figure 6. Diabetes reduced the slowly inactivating A-type current (I _AS) in capsaicin-sensitive neurons.

(A, B) I-V relations were obtained for peak (A) and steady-state (B) I _AS from diabetic (n = 12, filled circles) and control (n = 14, open circles) small DRG neurons. (C) The voltage-dependent activation and inactivation curves for peak I _AS from diabetic (n = 12 and 10, filled circles) and control (n = 14 and 12, open circles) neurons are shown. (D) The voltage-dependent activation curve for steady-state I _AS from diabetic (n = 11, filled circles) and control (n = 7, open circles) neurons are displayed. (E) The activation time constant τ_m of I _AS from diabetic (n = 6, filled circles) and control (n = 5, open circles) neurons was measured. The time constants of I _AS were increased in diabetic neurons. (F) The inactivation time constants (τ₁, τ₂) of I _AS from diabetic (n = 6, filled circles) and control (n = 5, open circles) neurons are plotted. τ₁ is the slower time constant. τ₂ is the faster time constant. * represents a significant difference between diabetic and control groups by a one–way ANOVA. All data are represented as mean ± S.E.M.

Figure 7. GAS increased the total Kv current in capsaicin-sensitive diabetic neurons.

(A) The original traces of potassium currents, elicited at −40 mV, were obtained before and after a series of concentrations of GAS. With increasing GAS doses, the peak values of total Kv current were gradually elevated. (B) Percentage of elevated Kv current is plotted as a function of GAS concentration (n = 6). (C) I-V relations (left panel) and the voltage-dependent activation curves (right panel) of peak total Kv current were obtained from diabetic (n = 18 and 12, filled circles) and GAS neurons (n = 10 and 10, open triangles). The histogram (right panel) indicates that 300 µM GAS (n = 15) increased the amplitude of total Kv current when the membrane potential was held at −40 mV, but decreased this current at 40 mV. (D) The current density of steady-state total Kv current (left panel) is plotted as a function of membrane potential. The voltage-dependent activation curves of steady-state total Kv current are shown in the right panel. (E) The activation time constants for total Kv current are plotted as a function of membrane potential. Treatment with GAS (300 µM) significantly reduced the activation time constants (n = 8). (F) The histogram indicates that 300 µM GAS (n = 8) reduced the amplitude of non-inactivating current when the membrane potential was held at 40 mV, but did not alter this current at −40 mV. (G) GAS did not alter the potassium currents in capsaicin-sensitive neurons from control rats (n = 7). * represents a significant difference between diabetic and diabetic + GAS groups by a one-way ANOVA. All data are represented as mean ± S.E.M.

Figure 8. GAS increased the slowly inactivating A-type currents (I _AS) in capsaicin-sensitive diabetic DRG neurons.

(A) I-V relations (left panel) and voltage-dependent activation and inactivation curves (right panel) for peak I _AS were obtained from capsaicin-sensitive DRG neurons in diabetic (n = 12, 12 and 10, filled circles) and diabetic + GAS groups (n = 11, 10 and 6, open triangles). (B) The activation time constants τ_m of I _AS were measured in diabetic (n = 6, filled circles) and diabetic + GAS (n = 6, open triangles) groups. (C) I-V relations (left panel) and the voltage-dependent activation curves (right panel) for steady-state I _AS were obtained from diabetic (n = 11, filled circles) and diabetic + GAS (n = 6, open triangles) groups. The activation curve was significantly shifted leftward after GAS treatment. * represents a significant difference between diabetic and diabetic + GAS groups by a one-way ANOVA. All data are represented as mean ± S.E.M.