Dynorphin acts as a neuromodulator to inhibit itch in the dorsal horn of the spinal cord

Abstract

Menthol and other counterstimuli relieve itch, resulting in an antipruritic state that persists for minutes to hours. However, the neural basis for this effect is unclear, and the underlying neuromodulatory mechanisms are unknown. Previous studies revealed that Bhlhb5(-/-) mice, which lack a specific population of spinal inhibitory interneurons (B5-I neurons), develop pathological itch. Here we characterize B5-I neurons and show that they belong to a neurochemically distinct subset. We provide cause-and-effect evidence that B5-I neurons inhibit itch and show that dynorphin, which is released from B5-I neurons, is a key neuromodulator of pruritus. Finally, we show that B5-I neurons are innervated by menthol-, capsaicin-, and mustard oil-responsive sensory neurons and are required for the inhibition of itch by menthol. These findings provide a cellular basis for the inhibition of itch by chemical counterstimuli and suggest that kappa opioids may be a broadly effective therapy for pathological itch.

Figure 1

Acute Inhibition of B5-I Cells Results in Elevated Itch (A) The inhibitory subset of Bhlhb5-expressing neurons in the superficial dorsal horn (B5-I neurons) coexpress sst_2A. Spinal cord sections from P4 mice were immunostained to reveal Bhlhb5 (green), sst_2A (red), and the inhibitory marker Pax2 (blue). The vast majority (∼90%) of cells expressing Bhlhb5 and Pax2 in laminae I and II colabel with sst_2A (arrows). A single confocal optical section through laminae I-IIo is shown. Scale bar, 20 μm. (B) Outward current was observed upon application of somatostatin (SST, 1 μM) to 50% of cells with the Bhlhb5-cre allele. (Note that the Bhlhb5-cre allele also labels other populations including excitatory neurons, which do not respond to SST.) (C) The number of sst_2A-expressing neurons in dorsal horn is significantly diminished in Bhlhb5^−/− mice. Spinal cord sections from 4- to 5-week-old wild-type (top) or Bhlhb5^−/− (bottom) mice were immunostained to reveal sst_2A (green) and Pax2 (magenta). Approximately half of the inhibitory (Pax2-expressing) neurons in laminae I and II express sst_2A in wild-type mice (arrows), and these cells are dramatically reduced in Bhlhb5 mutant mice. A single optical section is shown. Scale bar, 50 μm. (D) Quantification of (C). There is a significant reduction (^∗p < 0.05) in the number of sst_2A-expressing neurons (sst_2A +ve) in laminae I-II of the dorsal horn in Bhlhb5^−/− relative to wild-type (WT), with no significant change (NS) in the number of Pax2-positive inhibitory interneurons that do not express sst_2A (sst_2A –ve). Data are represented as mean + SD number of cells in laminae I-II per dorsal horn through 100 μm cord taken from L4 (n = 6 mice per genotype, 2 dorsal horns per mouse), analyzed by two-way ANOVA followed by pairwise comparison using the Holm-Sidak method. (E) Schematic depicting inhibition of sst_2A-expressing interneurons with the somatostatin analog octreotide, resulting in elevated itch. (F) Intrathecal administration of octreotide (3, 10, 30, or 100 ng in 5 μl vehicle) dose dependently evoked spontaneous scratching behavior in wild-type mice (n = 6–8 mice/treatment). Bhlhb5^−/− mice receiving 100 ng of octreotide intrathecally showed very little scratching response. Intrathecal injections were confirmed by coinjection of 10% methylene blue (n = 8 mice). Total scratching bouts (mean ± SEM) were measured over a 30 min observation period. One-way ANOVA was used to compare mean scratch bouts between treatment groups followed by Tukey’s post hoc test (^∗ indicates significantly different than PBS, p < 0.05). (G) Pruritogen-induced itch behavior was significantly enhanced following intrathecal octreotide (3 ng). Chloroquine (100 μg) was injected intradermally in the calf 30 min after treatment with either octreotide (i.t.) or vehicle (PBS; i.t.). Itch behavior was defined as the cumulative amount of time spent biting/licking the injection site over 30 min. Data are represented as mean ± SEM (^∗p < 0.05, Student’s t test). Also see Figure S1 for the specificity of octreotide-mediated behavioral effects.

Figure 2

B5-I Neurons Belong to a Population that Expresses Galanin and/or nNOS (A) The vast majority (95.4%, range 95.3%–95.7%, n = 3) of galanin-immunoreactive cells in laminae I-II (magenta) were Bhlhb5 immunoreactive (green; double arrow), and galanin-expressing cells accounted for 78.1% (range: 72.8%–86.4%) of B5-I neurons (image from lamina I-IIo). Numerous nNOS-immunoreactive cells (magenta) coexpress Bhlhb5 (green) as shown by the arrow (n = 3, image from lamina I). NPY seldom colocalized with Bhlhb5 (2.3% of NPY cells, range 1.1%–4.7%, n = 3; arrowheads illustrate cells that do not colocalize, lamina II). Images are single confocal optical sections from mice of indicated ages. (B) Populations of inhibitory interneurons in laminae I-II of adult dorsal horn. Approximately 54% of these cells express sst_2A (sst_2A positive), and these can be further subdivided into classes based on expression of galanin (red), nNOS (blue), galanin and nNOS (magenta), or sst_2A only (neither galanin nor nNOS; green). B5-I neurons belong to the classes that express galanin and/or nNOS. (C) Single optical sections of laminae I-II from wild-type or Bhlhb5^−/− mice reveal a dramatic loss of the sst_2A-expressing cells that contain galanin (red, double-headed arrow) and nNOS (blue, arrows), while the sst_2A-expressing cells that contain neither galanin nor nNOS (sst_2A only) are still present (arrowheads). Scale bar, 20 μm. (D) Quantification of (C) showing a significant reduction in cells expressing galanin (red), nNOS (blue), and galanin/nNOS (magenta). There was no significant change (NS) in the number of cells expressing sst_2A alone (green). Data are represented as mean + SD number of cells in laminae I-II per dorsal horn through 100 μm cord taken from L4 (n = 6 mice, genotype, 2 dorsal horns/mouse), analyzed by two-way ANOVA followed by pairwise comparison using the Holm-Sidak method (^∗ indicates p < 0.05). See Figure S2 for large field views.

Figure 3

B5-I Neurons Express Dynorphin (A) Spinal cord sections from P4 mice (n = 3) were immunostained to reveal Bhlhb5 (green), PPD (red), and Pax2 (blue). Virtually all (99%, range 98%–100%) cells expressing PPD and Pax2 were Bhlhb5 immunoreactive (arrows), and these accounted for the majority (85%, range 82.3%–87.95%) of B5-I cells at P4. Asterisk indicates a B5-I cell that does not express PPD. Pax2-negative Bhlhb5-expressing cells (presumed excitatory cells) are indicated with arrowheads. Scale bar, 20 μm. Similar results were observed using antibodies directed against Dynorphin B (Figure S3). (B) Spinal cord sections from 4- to 5-week-old wild-type (left) or Bhlhb5^−/− (right) mice immunostained for sst_2A (green) and PPD (magenta). In wild-type mice, dynorphin is expressed in a subset of sst_2A-expressing neurons (arrows), whereas in Bhlhb5^−/− mice, the sst_2A-expressing neurons that remain lack dynorphin (arrowheads). Images are single confocal optical sections. (C) Quantification of (B) showing reduction in the mean number of dynorphin-expressing cells in laminae I and II in Bhlhb5^−/− mice compared to wild-type controls. Data are represented as mean + SD number of cells per dorsal horn through 100 μm cord taken from L4 (n = 3 mice/genotype) and were analyzed by Student’s t test (^∗ indicates p < 0.05). Also see Figure S3.

Figure 4

Systemic Administration of U-50,488 or Nalfurafine Inhibits Scratching Behavior (A) Molecular structure of two KOR agonists, U-50,488 and nalfurafine (also called TRK-820). (B–F) Pretreatment with U-50,488 (3 mg/kg) or nalfurafine (20 μg/kg) significantly attenuates scratching following intradermal injection of chloroquine (200 μg) (B and C), SLIGRL (100 nM) (D), Histamine (100 μg) (E), or 5-HT (30 μg) (F) relative to control (PBS). Data are represented as mean + SEM number of scratch bouts during the first 40 min after pruritogen injection (n = 8 mice/treatment). For (B), (D), (E), and (F), data were analyzed by one-way ANOVA and Tukey’s post hoc test; ^∗p < 0.05. For (C), data were analyzed by two-way ANOVA and Tukey’s post hoc test; significant effects (p < 0.05) of U-50,488 (^∗) and nalfurafine (#) are indicated. (G) Spontaneous scratching induced by AEW treatment was significantly reduced in mice pretreated with either U-50,488 or nalfurafine compared to controls receiving vehicle (PBS). Data are represented as mean + SEM number of scratch bouts recorded over a 1 hr observation period (n = 8 mice/treatment). Data were analyzed by one-way ANOVA and Tukey’s post hoc test; ^∗p < 0.05. (H) Pretreatment with nalfurafine (20 μg/kg) significantly attenuated chloroquine-induced scratching behavior in both wild-type (WT; #p < 0.05) and Bhlhb5^−/− (†p < 0.05) mice. ^∗ indicates significant difference (p < 0.05) in chloroquine-induced scratching between WT and Bhlhb5^−/− mice. Experiments were performed using 4-week-old littermate pairs, prior to development of skin lesions (n = 8 mice/treatment). Data were analyzed by two-way ANOVA and Tukey’s post hoc test. (I) Itch sensitivity in constitutive preprodynorphin^−/− (PPD^−/−) mice (Loacker et al., 2007) was analyzed by measuring the response to an intradermal injection of chloroquine into the nape of the neck. Scratching behavior did not significantly differ between treatment groups (n = 7 mice/genotype), suggesting that PPD^−/− mice respond normally to acute pruritic stimuli. Data are represented as mean + SEM, and significance was assessed using a Student’s t test.

Figure 5

Kappa Agonists Selectively Inhibit Itch- but Not Pain-Associated Behaviors (A and B) The cheek model was used to discriminate between pain- (B) and itch-related (A) behaviors. Wiping the cheek with the forepaw following an intradermal injection of a chemical stimulus is indicative of pain, while scratching the injection site with the hindlimb indicates itch. (C) Intradermal chloroquine (100 μg) injected into the cheek elicited robust hindlimb-mediated scratching, and this was significantly attenuated in mice pretreated with nalfurafine (20 μg/kg) compared to control. (D) Nalfurafine (20 μg/kg) had no significant effect on chloroquine-evoked wiping behavior. (E) Intradermal injection of capsaicin (30 μg) into the cheek caused a small amount of hindlimb scratching, which was significantly reduced by nalfurafine (20 μg/kg). (F) Nalfurafine (20 μg/kg) had no significant effect on capsaicin-induced wiping. For (C)–(F), data are shown as mean + SEM (n = 8 mice/treatment); ^∗p < 0.05, Student’s t test; NS indicates no significant effect.

Figure 6

Modulation of Kappa Opioid Tone in the Spinal Cord Bidirectionally Modulates Itch Behavior (A) The calf model was used to evaluate itch-related behaviors. In this model, a pruritogen is injected into the skin of the calf and biting is indicative of itch. (B) Intrathecal administration of 10 μg U-50,488 or 40 ng nalfurafine (doses 60-fold lower than those used above for systemic administration) significantly reduced chloroquine-induced biting. Data are presented as mean + SEM (n = 6–8 mice/treatment). ^∗ indicates significant difference (p < 0.05) between treatment and control using one-way ANOVA and Tukey’s post hoc test. (C) Nalfurafine significantly reduces GRP-induced itch behavior. Intrathecal GRP-evoked scratching behavior was significantly attenuated when GRP (0.1 nmol) was coinjected with nalfurafine (40 ng) compared to PBS. Data are represented as mean + SEM number of scratch bouts recorded over a 30 min observation period (n = 7 mice/treatment). Data were analyzed by a Student’s t test; ^∗ indicates p < 0.05. (D) Molecular structure of two kappa opioid receptor antagonists, norbinaltorphimine (norBNI) and 5′-guanidinonaltrindole (5′GNTI). (E) Chloroquine-induced biting was significantly elevated after intrathecal administration of the kappa opioid antagonists 5′GNTI (1 μg) or nor-BNI (1 μg). Data are presented as mean + SEM (n = 6–8 mice/treatment). ^∗ indicates significant difference (p < 0.05) between treatment and control using a one-way ANOVA and Tukey’s post hoc test.

Figure 7

B5-I Neurons Are Innervated by Sensory Neurons that Respond to Capsaicin, Mustard Oil, and Menthol (A) Bhlhb5-cre neurons were recorded in patch-clamp experiments; fluorescence (left) and IR-DIC (right) image. B5-I neurons had input resistances of 641.7 ± 71.7 MΩ and a resting membrane potential of −63.3 ± 1.4 mV. Every neuron exhibited EPSCs at an average amplitude of 7.9 ± 0.6 pA at a holding potential of −70 mV. No IPSCs were observed because the reversal potential for IPSCs was near −70 mV. (B) Representative firing pattern of B5-I neuron in response to depolarizing current pulse of 25 (red) and 100 (black) pA. (C) Morphology of B5-I neurons. Neurolucida reconstructions revealed that most B5-I neurons are central (illustrated) or unclassified. Blue, dendrites; red, axons. (D) Schematic illustrating experimental setup to test whether B5-I neurons receive input from TrpV1-, TrpA1-, or TrpM8-expressing neurons. (E–J) Presynaptic effect of 2 μM capsaicin (E), 100 μM allyl isothiocyanate (mustard oil) (G), and 500 μM menthol (I). The majority of B5-I neurons showed a significant increase in sEPSC frequency after bath application of capsaicin (80%; F), mustard oil (86%; H), and menthol (90%; J). See Figure S5 for further electrophysiological analysis of B5-I neurons.

Figure 8

B5-I Neurons Mediate Inhibition of Itch by Chemical Counterstimuli (A) Mice were treated topically on the cheek with 10 μl of either 8% menthol or PBS (control). Menthol treatment resulted in modest wiping behavior that ceased within 5 min. Ten minutes after initial treatment, chloroquine (100 μg) was injected intradermally into the cheek and hindlimb-mediated scratching was quantified. Menthol significantly reduced subsequent chloroquine-induced scratching behavior in wild-type mice, but not in Bhlhb5^−/− mice. Data are presented as mean + SEM (n = 8 mice/treatment). ^∗ indicates significant difference (p < 0.05) between treatment and control using two-way ANOVA and Tukey’s post hoc test. Note that there was also a significant difference in chloroquine-induced scratching as a function of genotype, as seen previously (Ross et al., 2010). (B) Model: menthol-, capsaicin-, and mustard oil-sensitive sensory neurons inhibit itch via B5-I neurons in dorsal horn. B5-I neurons release GABA and/or glycine, which may cause acute inhibition of itch, as well as dynorphin, which acts as an inhibitory neuromodulator. Though the postsynaptic targets of B5-I neurons are not known, the finding that kappa agonists inhibit GRP-mediated itch implies that kappa opioids act on or downstream of GRPR neurons.