Lhx6-positive GABA-releasing neurons of the zona incerta promote sleep

Abstract

Multiple populations of wake-promoting neurons have been characterized in mammals, but few sleep-promoting neurons have been identified. Wake-promoting cell types include hypocretin and GABA (γ-aminobutyric-acid)-releasing neurons of the lateral hypothalamus, which promote the transition to wakefulness from non-rapid eye movement (NREM) and rapid eye movement (REM) sleep. Here we show that a subset of GABAergic neurons in the mouse ventral zona incerta, which express the LIM homeodomain factor Lhx6 and are activated by sleep pressure, both directly inhibit wake-active hypocretin and GABAergic cells in the lateral hypothalamus and receive inputs from multiple sleep-wake-regulating neurons. Conditional deletion of Lhx6 from the developing diencephalon leads to decreases in both NREM and REM sleep. Furthermore, selective activation and inhibition of Lhx6-positive neurons in the ventral zona incerta bidirectionally regulate sleep time in adult mice, in part through hypocretin-dependent mechanisms. These studies identify a GABAergic subpopulation of neurons in the ventral zona incerta that promote sleep.

Extended Data Figure 1. Distribution of diencephalic Lhx6⁺ neurons and immunohistochemical analysis of Lhx6-expressing neurons

Continued from Fig. 1. a, Schematics showing the distribution of Lhx6⁺ neurons in diencephalon. Blue boxes indicate Lhx6⁺ neurons (green) in the zona incerta, dorsomedial hypothalamus and the posterior hypothalamus, with representative images shown in b–d. b–d, Co-expression of eGFP (green) and Lhx6 in Lhx6–eGFP line (red) in zona incerta (b), dorsomedial hypothalamic nucleus (c), and posterior hypothalamus (d). eGFP signal fills the cell cytoplasm, whereas Lhx6 immunostaining is nuclear. Insets show magnified images of b–d. Image in b is identical to main Fig. 1b and is included for comparison. Scale bar, 100 µm. e, The percentage Lhx6⁺ and eGFP-expressing neurons in the Lhx6–eGFP line over the number of Lhx6–eGFP⁺ neurons in the zona incerta. n = 5 mice, eight sections per group. Data are mean ± s.e.m. f–i, Representative images showing Vgat-Cre;Ai9 (f, red) and Lhx6⁺ neurons (g, green) in the zona incerta. Merged image is shown in h and magnification is shown in i. j–m, Representative images showing Pvalb⁺ neurons (j, red) and Lhx6–eGFP⁺ neurons (k, green) in the zona incerta. Merged image is shown in l and magnification is shown in m. n–q, Representative images showing somatostatin neurons from FISH (n, red) and Lhx6–eGFP neurons (o, green) in the zona incerta. Merged image is shown in p and magnification is shown in q. Scale bars, 100 µm (d, f–h, j–l, n–p) and 25 µm (i, m, q).

Extended Data Figure 2. Lhx6-Cre activity recapitulates endogenous Lhx6 expression pattern and immunohistochemical analysis of Lhx6-expressing neurons

Continued from Extended Data Fig. 1. a–d, Representative images showing Lhx6⁺ neurons in the zona incerta (a, green), tdTomato expression in the Lhx6-cre;Ai9 line (b, red). tdTomato staining is also observed in endothelial cells, where Lhx6 expression is not detected in adult mouse brains. Merged image is shown in c and magnification is shown in d. Arrows indicate examples of colocalization of Lhx6 and tdTomato expression. e, The percentage Lhx6⁺tdTomato⁺ neurons relative to tdTomato⁺ neurons in the zona incerta in the Lhx6-cre;Ai9 line. n = 3 mice. Data are mean ± s.e.m. f–h, Representative images showing MCH⁺ neurons (f, red) in the lateral hypothalamus and Lhx6–eGFP neurons (g, green) in the zona incerta. Merged image is shown in h. i–k, Representative images showing Hcrt⁺ neurons (i, red) in the lateral hypothalamus and Lhx6–eGFP neurons (j, green) in the zona incerta. Merged image is shown in k. Scale bars, 100 µm (a–c, f–k) and 25 µm (d).

Extended Data Figure 3. Additional data showing mapping of neural projection sites of Lhx6-expressing neurons in the VZI, and projection sites of Slc32a1 and Pvalb-expressing cells in the zona incerta

Continued from Fig. 1. a, Schematics showing neural projection sites of Lhx6⁺ neurons in the zona incerta across multiple brain regions after ChR2–eYFP virus injection into the zona incerta of the Lhx6-cre line. b, e, h, k, n, Representative images of eYFP⁺ axonal processes of Lhx6⁺ neurons of the VZI (green) in amygdala (b), substantia nigra (e), periaqueductal grey (h), ventral tegmental area (k) and dorsal raphe nucleus (n). TH (red) immunostaining was used to demarcate the amygdala, substantia nigra, periaqueductal grey and ventral tegmental area in b, e, h and k. TPH2 (red) immunostaining was used to demarcate the dorsal raphe nucleus in n. Scale bars, 100 µm. c, f, i, l, o, High-power images of the brain of a Slc32a1-cre mouse injected with DIO-rAAV–eGFP in the zona incerta, demonstrating infection in zona incerta (c), central thalamus (f, o), amygdala (i) and periaqueductal grey (l). White arrows indicate eGFP⁺ processes in i. Scale bars, 200 µm. d, g, j, m, p, High-power images of the brain of a Pvalb-cre mouse injected with DIO-rAAV–eGFP in zona incerta. eGFP⁺ processes are detected in the zona incerta (d) and central thalamus (g, m). No signal is detected in the amygdala (j) and very little signal is seen in the periaqueductal grey (m). Scale bars, 200 µm. c, d, f, g, i, j, l, m, o, p, Images were obtained from the Allen Brain Atlas Mouse Connectome Project. Experiment numbers 17106613 for Scl32a1-IRES-Cre (section 73 (c, f, i), section 58 (l) and section 44 (o)) and 301539438 for Pvalb-IRES-Cre (section 68 (d, g, j), section 60 (m) and section 45 (p)). Amyg, amygdala; CPu, caudate putamen; DR, dorsal raphe nucleus; ECIC, external cortex of the inferior colliculus; Hip, hippocampus; LH, lateral hypothalamus; MGP, medial globus pallidus; MM, mammillary nucleus; PAG, periaqueductal grey; PH, posterior hypothalamus; Pn, paranigral nucleus; SNpc, substantia nigra pars compact; VTA, ventral tegmental area.

Extended Data Figure 4. Presynaptic inputs to Lhx6⁺ zona incerta neurons

Continued from Fig. 1. a, Schematic showing the distribution of presynaptic neurons (red dots) to Lhx6 zona incerta neurons and location of presynaptic neurons across the rostro-caudal gradient of the mouse brain. For mice injected with rabies + TVA (tumour virus A, the receptor for modified rabies virus), n = 4. For rabies only controls, n = 2. b–d, Distribution of presynaptic neurons to Lhx6⁺ zona incerta neurons located in the lateral hypothalamus (RABV, b, red). GABA immunostaining (c, grey) was used to label neurons in the lateral hypothalamus. Merged image is shown in d. e–g, Distribution of presynaptic neurons to Lhx6 zona incerta neurons located in the periaqueductal grey (RABV, e, red). GABA immunostaining (f, grey) was used to label neurons in the periaqueductal grey. Merged is shown in g. Arrows indicate neurons with RABV and GABA co-localization (b– g). Scale bar, 100 µm. AC, anterior commissural nucleus; AR, arcuate nucleus; Acb, nucleus accumbens; aPAG, anterior periaqueductal grey; APT, anterior pretectal nucleus; ATC, anteromedial thalamic nucleus; BNST, bed nucleus of the stria terminalis; CA1, hippocampus CA1; CA3, hippocampus CA3; CeA, central nucleus of the amygdala; Cg1/Cg2, cingulate cortex; Cl, Claustrum; CM, central medial nucleus of thalamus; CPu, striatum; DG, dentate gyrus; DMH, dorsomedial hypothalamus; DpG, motor-related nuclei of superior colliculus; DR, dorsal raphe nucleus; ECIC, external cortex of the inferior colliculus; Ent, entorhinal cortex; Gi, midline gigantocellular nucleus of the medulla; HDB/VDB, nucleus of the diagonal band; Ing, intermediate grey layer of superior colliculus; Lat, lateral/dentate cerebellar nucleus; LDTG, laterodorsal tegmental nucleus; LH, lateral hypothalamus; LHb, lateral habenula; LO, lateral orbital cortex; LPBE, lateral parabrachial nucleus of the pons; LPOA, lateral preoptic area; LS, lateral septum; LVE, lateral vestibular nucleus; M1/M2, frontal/secondary motor cortex; Med, fastigial nucleus; MePD, posterodorsal medial amygdaloid nucleus; MHb, medial habenula; MM, medial mammillary nucleus; MnPO, median preoptic nucleus; MnR, median raphe nucleus; MPB, medial parabrachial nucleus; MPOA, medial preoptic area; MS, medial septal nucleus; PH, posterior hypothalamus; Pir, piriform cortex; PnO, pontine reticular nucleus, oral part; PPTG, pedunculopontine tegmental nucleus; PVH, paraventricular nucleus of the hypothalamus; PVT, paraventricular nucleus of thalamus; RMG, nucleus raphe magnus; Rn, red nucleus; RS, retrosplenial area; RT, reticular nucleus; RtTg, midbrain reticular formation; S, subiculum; S1/S2, somatosensory cortex; S1BF, barrel cortex; SFO, subfornical organ; SNPC, substantia nigra pars compact; SNR, substantia nigra, reticular part; SPF, parafascicular thalamic nucleus; SuM, supramammillary nucleus; TeA, temporal association cortex; TMN, tuberomammillary nucleus; VLGN, ventrolateral geniculate nucleus; vlPAG, ventrolateral Periaqueductal grey; VMH, ventromedial hypothalamus; VO, ventral orbital cortex; VP, ventral pallidum; VTA, ventral tegmental area; ZI, zona incerta.

Extended Data Figure 5. Synaptic outputs of Lhx6 neurons in the zona incerta

Continued from Fig. 2. a, Schematic showing injection of AAV9-DIO-ChR2–mCherry into the zona incerta of Lhx6-cre;Hcrt–eGFP mice. The red box shows the location of Hcrt-expressing neurons (green) in the lateral hypothalamus and the ventromedial portion of the zona incerta with ChR2-expressing Lhx6⁺ neurons (red) shown in the image on the right. Scale bar, 300 µm. b, Responses of two Hcrt neurons to brief (3 ms) photostimulation of ChR2-expressing Lhx6 axons. The average responses (left) and two representative responses (right) are shown for each neuron. The responses are depolarizing owing to the high chloride internal solution used. The amplitude of the average responses was smaller than for individual responses because of the failure rate to any individual photostimulation (24.0 ± 5.9%, range 65.8–0%; n = 15 cells). c, Average responses recorded from a Hcrt neuron to photostimulation of ChR2-expressing Lhx6 axons under control conditions (left), following bath application of the sodium channel blocker tetrodotoxin (TTX, middle) and following the addition of the potassium channel blocker 4-AP (right). Note that the cell shows a depolarizing response owing to the high chloride internal recording solution. d, Summary data showing the amplitude of the average response to the first photostimulation under control conditions, following bath application of TTX and TTX together with 4-AP. The responses recorded using a high chloride internal solution in TTX and 4-AP treatment indicate that ChR2-expressing Lhx6⁺ VZI neurons form monosynaptic connections onto the recorded Hcrt⁺ neurons (control, 4.85 ± 1.37 mV; TTX, 0.07 ± 0.04 mV; TTX + 4-AP, 6.65 ± 1.50 mV; two-way ANOVA with Bonferroni correction, control versus TTX, *P = 0.01498; TTX versus TTX + 4-AP, **P = 0.00178, control versus TTX + 4-AP, P = 0.61814; n = 6 cells from four mice). e–g, Expression of eGFP (e, green) in recorded Hcrt–eGFP neurons was confirmed by filling the recorded cells in the lateral hypothalamus with biocytin (f, blue). Arrows indicate colocalization of the two markers in the recorded neurons as seen in the merged image (g). Scale bar, 50 µm. h, Schematic showing injection of AAV9-DIO-ChR2–eYFP into the zona incerta of Lhx6-Cre;Gad2-NLS–mCherry mice (left). The red box shows the location of the image (right) showing Gad2-expressing neurons (red) in the lateral hypothalamus and Lhx6⁺ neurons (green) in the ventromedial portion of the zona incerta. Scale bar, 500 µm. i–k, Colocalization of mCherry (i, red) in Gad2-NLS–mCherry mice with biocytin (j, blue) in Gad2⁺ neurons recorded in the lateral hypothalamus. The arrow indicates colocalization of the two markers as seen in the merged image (k). Scale bar, 20 µm. l, Average responses recorded from a Gad2-expressing neuron to brief (3 ms) photostimulation of ChR2-expressing Lhx6 axons under control conditions (left), following bath application of the ionotropic glutamate receptor antagonists, CPP and NBQX (middle) and following the addition of the GABA_A receptor antagonist, gabazine (right). Note that the response is depolarizing owing to the high concentration of chloride in the internal recording solution. Responses were eliminated in the presence of gabazine (control, 3.96 ± 1.55 mV; CPP + NBQX, 3.48 ± 2.16 mV; CPP + NBQX + gabazine: 0.01 ± 0.01 mV; n = 3 cells from two mice). m, Schematic showing injection of AAV9-DIO-ChR2–mCherry virus into the zona incerta of Lhx6-creER^T2;Lhx6–eGFP mice (left). The red box indicates the location of a representative image from one mouse (right) showing mCherry-expressing (red) and eGFP-expressing (green) Lhx6⁺ neurons in the zona incerta. The red box indicates the location of higher magnification images in n–p. Scale bar, 100 µm. n–p, Expression of mCherry (n, red) and eGFP (o, green) in Lhx6-creER^T2;Lhx6–eGFP mice injected with AAV9-DIO-ChR2–mCherry in the zona incerta. The merged image is shown in p. Arrows in p indicate a subset of Lhx6⁺ neurons that express both ChR2–mCherry and eGFP. Scale bar, 100 µm. q, Average response elicited by 500 ms photostimulation in a ChR2-expressing Lhx6⁺ VZI neuron recorded in whole-cell voltage-clamp mode (left) and a representative trace of action potentials elicited by brief 3-ms flashes of blue light (10 Hz) recorded in current-clamp in the same neuron (right). Note that the train of light pulses reliably elicits action potentials. Responses to 500-ms long light pulses recorded in voltage-clamp were used to distinguish ChR2-expressing from non-ChR2-expressing Lhx6⁺ VZI neurons. r, Representative average responses of two non-ChR2-expressing Lhx6⁺ neurons to photostimulation of axons of ChR2-expressing Lhx6⁺ neurons. The responses are depolarizing because of the high concentration of chloride in the internal recording solution. s, Representative responses from two Lhx6⁺ neurons in response to steps of depolarizing (+50 pA) current. Average responses to hyperpolarizing current steps (−25 pA) are also shown. t, The spike half-width (left; n = 17 cells) and sag amplitude (right; n = 14 cells) of recorded Lhx6⁺ neurons. The mean ± s.e.m. of the responses are shown in black. u, Plot of the inter-spike intervals for trains of action potentials elicited in Lhx6⁺ neurons by 1-s steps of depolarizing current. The mean ± s.e.m. of the responses are shown in black (n = 15 cells).

Extended Data Figure 6. Lhx6 expression is selectively deleted in the diencephalon, but preserved in the telencephalon of Lhx6-conditional knockout Foxd1-cre;Lhx6^lox/lox (cKO) line, and Lhx6 cKO mice do not display obvious behavioural abnormalities other than changes in sleep patterns

Continued from Fig. 3. a–l, Representative images of Lhx6 immunostaining (green) in the cortex (a–d), amygdala (e–h) and zona incerta (i–l) of control (a, b, e, f, i, j) and cKO (c, d, g, h, k, l) mice. Magnified images of a, c, e, g, i, k are shown in b, d, f, h, j, l, respectively. Note an absence of Lhx6 expression in the zona incerta of the cKO group. Scale bars, 100 µm. m, n, Sample EEG recordings for control (m) and cKO (n) mice with wake (yellow), REM sleep (red) and NREM sleep (purple) indicated, along with hypnogram (sleep stage), FFT-derived delta power (femtovolts²), EEG spectrum (frequency), EEG raw activity (amplitude) and EMG raw activity (amplitude) between ZT7 and ZT10. o, p, Bout length quantification (o) showing the duration of wake, NREM and REM episodes and bout count quantification (p) showing sleep–wake transitions in control (Foxd1-cre;Lhx6^lox/+) and cKO (Foxd1-cre;Lhx6^lox/lox) groups. Two-way ANOVA followed by Sidak’s post hoc test. n = 8 control and 8 cKO mice. q–v, Light–dark preference test (q), EPM (r, s), grip strength (t), open field test (u) and rotarod (v) were conducted in control (red) and Lhx6 cKO (blue) groups. *P < 0.05 for changes in sleep patterns (m–p); no significant difference (P > 0.1) was detected for all other behaviours (q–v) analysed; two-way ANOVA followed by Sidak’s post hoc test. Data are mean ± s.e.m. n = 8 control and 8 cKO mice.

Extended Data Figure 7. Distribution of AAV-DREADD infection sites in the zona incerta of Lhx6-cre mice and CNO activates Fos expression in AAV-DIO-hM3Dq-injected Lhx6-Cre mice, whereas CNO does not affect sleep in AAV-DIO–mCherry-injected Lhx6-Cre mice

Continued from Fig. 4. a, Schematics showing distribution of DREADD-infected (hM3Dq or hM4Di mice) neurons (red) across the rostrocaudal extent of the zona incerta after AAV-DREADD was injected into the zona incerta of Lhx6-cre mice. Infection is specific to the zona incerta in 12 Lhx6-cre mice (red colour indicates infection site from all 12 mice). Yellow colour indicates additional infected areas seen in 4 out of 12 mice. b–d, Representative images showing co-expression of hM3Dq DREADD in the zona incerta of Lhx6-cre mice (b, red) with Lhx6 immunostaining (c, green). The merged image is shown in d, inset shows a magnified image of d. e–g, Representative images showing co-expression of AAV-hM4Di infection in the zona incerta of Lhx6-cre mice (e, red) with Lhx6 immunostaining (f, green). A merged image is shown in g; inset shows a magnified image of g. Scale bar, 100 µm. h–j, Representative images showing hM3Dq–mCherry expression (red) and Fos immunostaining in the zona incerta of Lhx6-cre mice after saline (h) or CNO (i) injection. A magnified image of i is shown in j. k, The percentage Fos⁺ neurons in hM3Dq–mCherry⁺ Lhx6-expressing neurons in the zona incerta in mice injected with saline or CNO. ***P < 0.001, two-tailed paired t-test; n = 4 mice, 8 sections for saline; n = 5 mice, 8 sections for CNO. l–n, Representative images showing hM4Di–mCherry expression (red) and Fos immunostaining (green) in the zona incerta of Lhx6-Cre mice after saline (l) or CNO (m) injection. A magnified image of l is shown in n. Scale bars, 100 µm. o, The percentage Fos⁺ neurons in hM4Di–mCherry⁺ Lhx6-expressing neurons in the zona incerta in mice injected with saline or CNO. *P < 0.05, two-tailed paired t-test; n = 3 mice, 8 sections for saline; n = 3 mice, 8 sections for CNO. Data are mean ± s.e.m. o–q, Saline- or CNO-injection at ZT5 in the AAV8-DIO–mCherry group shows that CNO injection does not affect sleep. EEG analysis showing amount of time spent across ZT in wake (o), REM sleep (p) and NREM sleep (q). P > 0.1 for all behavioural readouts, two-way ANOVA followed by Sidak’s post hoc test, n = 4 mice for saline, n = 4 mice for CNO.

Extended Data Figure 8. Additional data from G_q DREADD-injected Lhx6-cre mice

Continued from Fig. 4. a, Schematics showing the construct of the AAV-DIO-hM3Dq–mCherry virus and the injection site of virus into the zona incerta of Lhx6-cre mice. b, EEG analysis showing the percentage of time in 2-h bins spent in wake (top), NREM sleep (middle) and REM sleep (bottom) after injection of saline or CNO at ZT17 in hM3Dq groups. c, Bout length quantification (top) showing durations for wake, NREM and REM episodes and bout count (bottom) showing sleep–wake transitions with saline or CNO injection in hM3Dq groups. d, FFT analysis of EEG power spectrum frequency of NREM stage of CNO-injected AAV-DIO-hM3Dq-infected mice (blue) compared to control (saline-injection, red). e, Grouped EEG frequency data obtained from spectrum band analysis of saline- (red) and CNO-injected (blue) hM3Dq mice. f, FFT analysis of EEG power spectrum frequency of the wake stage of CNO-injected AAV-DIO-hM3Dq-infected mice (blue) compared to control (saline-injection, red). g, Grouped EEG frequency data obtained from spectrum band analysis of saline- (red) and CNO-injected (blue) hM3Dq mice. Data are mean ± s.e.m. *P < 0.05, **P < 0.01; two-way ANOVA followed by Sidak’s post hoc test (b, c, e, g). n = 8 mice (b–g).

Extended Data Figure 9. The dual orexin receptor antagonist suvorexant can increase both NREM and REM sleep

Continued from Fig. 4. a, Schematic showing sleep recording paradigm (EEG and EMG recording) for experiments with suvorexant. b, EEG analysis showing the percentage of time in 2-h bins spent in wake (left), NREM sleep (middle) and REM sleep (right) after injection of saline or suvorexant at ZT5. c, EEG analysis showing the percentage of time in 2-h bins. The data show that suvorexant does not show a clear additive effect in combination with CNO in regulating time spent in wake (left), NREM sleep (middle) and REM sleep (right) when co-administered to mice expressing G_q DREADDs in Lhx6⁺ neurons in the zona incerta in the first 2 h after administration. Data are mean ± s.e.m. *P < 0.05; two-way ANOVA followed by Sidak’s post hoc test, n = 10 mice.

Extended Data Figure 10. Additional data from AAV-DIO-hM4Di-injected Lhx6-cre mice

Continued from Fig. 4. a, Schematics showing the construct of AAV-DIO-hM4Di–mCherry virus and the injection sites of virus into the zona incerta of Lhx6-cre mice. b, EEG analysis showing the percentage of time in 2-h bins spent in wake (top), NREM sleep (middle) and REM sleep (bottom) after injection of saline or CNO at ZT17 in hM4Di groups. c, Bout length quantification (top) showing duration of wake, NREM and REM episodes and bout count (bottom) showing sleep–wake transitions with saline or CNO injection in hM4Di groups. d, FFT analysis of EEG power spectrum frequency of NREM stage of CNO-injected AAV-DIO-hM4Di (blue) compared to control (saline-injection, red). e, Grouped EEG frequency data of spectrum band analysis between saline- (red) and CNO-injected (blue) hM4Di groups. f, FFT analysis of EEG power spectrum frequency of NREM stage of CNO-injected AAV-DIO-hM4Di (blue) compared to control (saline-injection, red). g, Grouped EEG frequency data of spectrum band analysis between saline- (red) and CNO-injected (blue) hM4Di groups. Data are mean ± s.e.m. *P < 0.05, **P < 0.01, ***P < 0.001; two-way ANOVA followed by Sidak’s post hoc test. n = 8 mice.

Figure 1. Lhx6⁺ neurons in the VZI are GABAergic, receive synaptic inputs from sleep-regulating regions, and project to Hcrt⁺ neurons in the lateral hypothalamus

a, Distribution of Lhx6⁺ neurons in the hypothalamus. Box indicates the location of Lhx6⁺ neurons (green) in the VZI in b. b, Co-expression of eGFP (green) in the Lhx6–eGFP line with Lhx6 (red) in the VZI. Inset, magnification of the boxed area. c, The percentage of Lhx6⁺tdTomato⁺ cells (blue) in the VZI relative to all tdTomato⁺ cells in the VZI in Slc32a1-cre;Ai9 mice. The percentage of Lhx6⁺tdTomato⁺ neurons (red) relative to all Lhx6⁺ neurons in the VZI in Slc32a1-cre;Ai9 mice. n = 3 mice, eight sections per group. d, The percentage of Lhx6⁺Gad1⁺ cells (blue) relative to all Gad1⁺ neurons in the VZI. The percentage of Lhx6⁺Gad1⁺ cells (red) relative to all Lhx6⁺ cells in the VZI. n = 3 mice, six sections per group. Data are mean ± s.e.m. (c, d). e–g, Co-localization of Lhx6–eGFP (e, green) with Gad1 mRNA (f, red) in the VZI. Merged image is shown in g. h, ChR2–eYFP virus injection site in the zona incerta of the Lhx6-cre line. i, j, Distribution of ChR2–eYFP-infected Lhx6⁺ neurons (green) in the zona incerta (i) and projections of Lhx6⁺ neurons in the lateral hypothalamus (j). Tyrosine hydroxylase (TH) (i, red), and Hcrt (j, red) are shown. k, Rabies virus (RABV) injection site in the zona incerta of Lhx6-cre, and the distribution of neurons presynaptic to Lhx6⁺ VZI cells. l–n, RABV⁺ cells in the nucleus of the diagonal band (l, red) stained with anti-Chat (m, grey). Merged image is shown in n. o–q, RABV⁺ cells in the ventral tegmental area (o, red) stained with anti-tyrosine hydroxylase (p, grey). Merged image is shown in q. r–t, RABV⁺ cells in the dorsal raphe nucleus (r, red) stained with anti-TPH2 (s, grey). Merged image is shown in t. Scale bars, 100 µm. Arrows show cells co-expressing relevant markers. Amy, amygdala; CeA, central nucleus of the amygdala; Cg1/Cg2, cingulate cortex; DB, diagonal band; DpG, motor-related nuclei of superior colliculus; Gi, midline gigantocellular nucleus of the medulla; LH, lateral hypothalamus; LO/VO, lateral/ventral orbital cortex; LS, lateral septum; M1/M2, frontal/secondary motor cortex; POA, preoptic area; PPTG, pedunculopontine tegmental nucleus; RtTg, midbrain reticular formation; SFO, subfornical organ; SNR/VTA, substantia nigra reticular part/ventral tegmental area; vlPAG/DR, ventrolateral periaqueductal grey/dorsal raphe nucleus; VTA/SNPC, ventral tegmental area/substantia nigra pars compact; ZI, zona incerta.

Figure 2. Lhx6⁺ VZI neurons are activated by sleep pressure and are presynaptic to Hcrt⁺ and GABAergic neurons in the lateral hypothalamus

a, b, d–g, Representative images of Fos immunostaining (red) and Lhx6–eGFP expression (green) in VZI for ZT0 (a), ZT6 (b), ZT14 (d), ZT18 (e), following sleep deprivation (SD) (f) and sleep deprivation paired with recovery sleep (RS) (g). Scale bar, 100 µm. c, h, The percentage of Fos⁺Lhx6⁺ neurons in the zona incerta across ZT (c) and under sleep pressure (h). **P < 0.01; linear mixed-effect model fit by REML (h), two-tailed one-way ANOVA (c). n = 4 mice per group, four brain sections analysed bilaterally per mouse. i, Average response to photostimulation (500 ms) of a ChR2-expressing Lhx6⁺ VZI neuron (left; voltage-clamp) and action potentials elicited by photostimulation (3 ms, 10 Hz) from the same neuron (right; current-clamp). j, Responses of two Hcrt⁺ neurons to depolarizing current steps. k, Postsynaptic responses from a Hcrt⁺ neuron following photostimulation of ChR2⁺Lhx6⁺ neurons under control conditions (left), with glutamate receptor blockers NBQX (2,3-dioxo-6-nitro-1,2,3,4-tetrahydrobenzo[f]quinoxaline-7-sulfonamide disodium salt) and CPP ((RS)-3-(2-carboxypiperazin-4-yl)-propyl-1-phosphonic acid) (CPP + NBQX; middle), CPP, NBQX and the GABA_A receptor antagonist gabazine (6-imino-3-(4-methoxyphenyl)-1(6H)-pyridazinebutanoic acid hydrobromide) (CPP + NBQX + gabazine; right) and after gabazine washout (far-right). Inset shows the onset of the postsynaptic response shown at an expanded timescale for the control. l, Amplitudes of the first postsynaptic response to photostimulation in control conditions, with NBQX and CPP, with NBQX, CPP and gabazine, and after gabazine washout. Two-way ANOVA with Bonferroni correction; control versus CPP + NBQX, P = 1; CPP + NBQX versus CPP + NBQX + gabazine, ***P = 0.00024; control versus CPP + NBQX + gabazine, ***P = 0.00077; CPP + NBQX versus CPP + NBQX + gabazine washout, *P = 0.0478; n = 8 Hcrt neurons from four mice. m–p, Responses to depolarizing current steps (left) and average short-latency postsynaptic potentials (right) in Gad2⁺ neurons following photostimulation of ChR2⁺Lhx6⁺ neurons. Data are mean ± s.e.m. (c, h, l).

Figure 3. Selective loss of Lhx6 expression in the diencephalon reduces both NREM and REM sleep

a, Generation of diencephalic-specific Lhx6 conditional knockout (cKO) line by crossing Foxd1-cre and Lhx6^lox/lox lines. A, anterior, D, dorsal, P, posterior, V, ventral. b, EEG/EMG analysis showing the percentage of the day–night cycle spent awake and in NREM and REM sleep in control (Foxd1-cre;Lhx6^lox/+) and cKO groups. c, Fast Fourier transform (FFT) analysis of EEG power spectrum during NREM sleep of cKO (blue) compared to control (red) mice. d, The collapsed EEG frequency data are shown for control (red) and cKO (blue) mice. e, FFT analysis of EEG power spectrum frequency in cKO mice (blue) compared to controls (red). f, The collapsed EEG frequency data are shown for control (red) and cKO (blue) mice. n = 8 control and 8 cKO mice for all experiments. Data are mean ± s.e.m. *P < 0.05, **P < 0.01; two-way ANOVA followed by Sidak’s post hoc test.

Figure 4. DREADD-dependent activation or inhibition of Lhx6⁺ neurons in the zona incerta regulates NREM and REM sleep

a, Schematic showing sleep recording conditions with saline- or CNO-injection in hM3Dq-infected (left, b–d) or hM4Di-infected (right, e–g) mice. b, hM3Dq–mCherry viral construct and injection site in Lhx6-cre mice. c, Percentage of time spent during the 12 h after injection in wake (top), NREM sleep (middle) and REM sleep (bottom) in saline- or CNO-injection in hM3Dq groups. d, Percentage of time spent in wake (top), NREM sleep (middle) and REM sleep (bottom) in 2-h bins following injection of saline or CNO at ZT5 in hM3Dq mice. e, hM4Di–mCherry viral construct and injection site in Lhx6-cre mice. f, Percentage of time spent during the 12 h after injection in wake (top), NREM sleep (middle) and REM sleep (bottom) in saline- or CNO-injection in hM4Di mice. g, Percentage of time in wake (top), NREM sleep (middle) and REM sleep (bottom) in 2-h bins following injection of saline or CNO at ZT5 in hM4Di mice. *P < 0.05, **P < 0.01, ***P < 0.001; two-way ANOVA followed by Sidak’s post hoc test. n = 8 mice for all experiments. Data are mean ± s.e.m.