Genetic dissection of an amygdala microcircuit that gates conditioned fear

Abstract

The role of different amygdala nuclei (neuroanatomical subdivisions) in processing Pavlovian conditioned fear has been studied extensively, but the function of the heterogeneous neuronal subtypes within these nuclei remains poorly understood. Here we use molecular genetic approaches to map the functional connectivity of a subpopulation of GABA-containing neurons, located in the lateral subdivision of the central amygdala (CEl), which express protein kinase C-δ (PKC-δ). Channelrhodopsin-2-assisted circuit mapping in amygdala slices and cell-specific viral tracing indicate that PKC-δ(+) neurons inhibit output neurons in the medial central amygdala (CEm), and also make reciprocal inhibitory synapses with PKC-δ(-) neurons in CEl. Electrical silencing of PKC-δ(+) neurons in vivo suggests that they correspond to physiologically identified units that are inhibited by the conditioned stimulus, called CEl(off) units. This correspondence, together with behavioural data, defines an inhibitory microcircuit in CEl that gates CEm output to control the level of conditioned freezing.

Figure 1. Characterization of CEl PKCδ⁺neurons

a, In situ hybridization (ISH) for PKCδ mRNA. CA3, hippocampus; Thal, thalamus. Boxed area at higher magnification on right. b-j, Double-label fluorescence ISH (dFISH) for PKCδ mRNA and the indicated markers. Insets, boxed areas. Filled and open arrowheads indicate doubly vs. singly labeled cells, respectively. k-l, Whole-cell patch clamp recordings in acute amygdala slices. Voltage changes (red) produced by respective current injections (black) are illustrated. Resting membrane potentials were adjusted to ∼ -65 mV. m, n, Neurobiotin-filled CEl neurons recorded in (k, l) after fluorescent streptavidin labeling and immunostaining for PKCδ. o, Stimulus-response (I/O) curves for neurons based on electrophysiological profile (late-firing, n = 22; regular spiking, n = 14), or PKCδ expression (PKCδ⁺, n = 14; PKCδ^-, n = 12) in CEl. See also Tables S2-S4.

Figure 2. Transgenic targeting of PKCδ⁺neurons

a, Design of PKCδ∷GluClα−CFP-iCre BAC transgene. b-d, f-h, j-l, Expression of transgene visualized by double-label immunofluorescent labeling (dIFL) for GFP and the indicated markers. i, m, Quantification of f-h and j-l, respectively. Values are mean ± SEM, n = 3. (e) X-gal staining of PKCδ∷GluClα-iCre; Rosa∷loxP-STOP-loxP-lacZ mice reveals β-galactosidase expression (blue) in correct locations. Scale bar in b applies to c-h and j-l.

Figure 3. CEl PKCδ⁺neurons directly inhibit CEm output neurons

a-j, Anterograde axonal tracing using Cre-dependent hrGFP AAV. k-o, Retrograde tracing from CEm using red fluorescent CTB. Scale bars for b-j, l-m, respectively. p-w, Optogenetic activation of CEl PKCδ⁺ neurons inhibits PAG projecting neurons in CEm. p, Schematic illustrating double-injection/slice recording experiments. q, CTB⁺ CEm cell (CTB, arrowhead) with patch electrode (IR DIC, dashed lines) is illustrated. r-v, Whole-cell voltage-clamp (V_hold = -40 mV) (r, s) or current clamp (t-v) recordings from a back-labeled CEm neuron. r,s, IPSC triggered by a 2 ms 473 nm laser pulse, with (s) or without (r) 100 μM picrotoxin. t-v, suppression of depolarizing current injection-evoked spiking by 473 nm laser pulses (2 ms, 15 Hz), with (u) or without (t) 100 μM picrotoxin. v, w, Quantification of data in t (n = 5 cells; * P < 0.001, t-test) and v (n = 3 cells; P = 0.75, t-test), respectively.

Figure 4. PKCδ⁺and PKCδ^- make reciprocal inhibitory connections in CEl

a, Schematic and micrograph from slice preparation. Arrowhead indicates PKCδ(CFP)^minus; (YFP)^- recorded cell in CEl. b-e, Whole-cell voltage clamp (V_hold = -40 mV) (b, c) or current clamp (d, e) recordings from PKCδ^- CEl neuron showing light-triggered (d), picrotoxin-sensitive (c) IPSC, or picrotoxin-sensitive (e) suppression of depolarizing current injection-evoked spiking (d) by ChR2 activation (blue dots; 2 ms, 15 Hz). f, g, Quantification of data in d (f; n = 5 cells, *** P < 0.001, t-test) and e (g; n = 3 cells, P = 0.66, t-test), respectively. h, Schematic illustrating cell-specific Rabies virus infection. i-p, immunostaining for PKCδ(i,m), intrinsic mCherry fluorescence (j, n) and nuclear staining with TOPRO-3 (k, o) 3 days after RV^ΔG injection of transgenic (m-p) and wild-type (i-l) mice. Primary infected PKCδ⁺ neurons (m, n insets, open arrowheads) and retrogradely labeled PKCδ^- cells (m, n insets, filled arrowheads) are indicated. q-t, Triple labeling for PKCδ (q) and GABA (s) and mCherry (r). mCherry-labeled PKCδ^- cells are GABAergic (inset, arrowhead). Scale bars for f-m, n-q.

Figure 5. IVM/GluCl-mediated suppression of CEl PKCδ⁺neuronal activity

a, Strategy for selective expression of GluClαβ in CEl PKCδ⁺ neurons. Yellow, CMV-driven AAV∷GluClβ virus; blue, PKCδ∷GluClα-CFP transgene expression. b, Summary of inhibitory connections in CEA (see also Ciocchi et al). c-e, Current injection (bottom trace)-evoked spiking (top, black trace) is suppressed by 20 nM IVM (middle, red trace) in PKCδ⁺ cells expressing GluClαβ (c), but not in cells expressing either GluClβ-YFP (d) or GluClα-CFP (e). f-h, Quantification of results in c-e, respectively (f, n = 4 cells, P = 0.005); g, n = 5 cells, P = 0.73; h, n = 4 cells, P = 0.66; paired t-tests). i-n, IVM/GluCl-mediated silencing of PKCδ⁺ neurons during chronic in vivo recording. i, Behavioral data for mice used in recording experiments. Hab, habituation; FC, fear conditioning. (n = 5) j, Coronal schematic showing recording sites in CEl and CEm (-1.34 mm posterior to bregma). BLA: basolateral amygdala. k, l Representative raster plots (upper) and normalized population peristimulus time histograms (lower) of CEl_off (k; lower, n = 6 neurons from 3 mice) and CEl_on neurons (l; lower, n = 10 neurons from 4 mice) (P < 0.05). Confirmation of unit isolation is shown in Figure S11. m, Tonic activity of CEl_off neurons (One-way ANOVA (F_(2,15) = 4.845, P = 0.024) with post-hoc Bonferroni t-test (* P < 0.05), but not of CEl_on neurons (One-way ANOVA (F_(2,27) = 0.391, P = 0.680)), is significantly (Day 6) and reversibly (Day 8) reduced by IVM (10 mg/kg, i.p.), while tonic activity of CEm neurons is increased (n = 5 units from 1 mouse; one-way Kruskal-Wallis ANOVA (H = 7.487, with 2 degrees of freedom, P = 0.024) with post-hoc Tukey's HSD (* P < 0.05)). n, Specificity controls for (m). IVM injection without virus infection (n = 3; P = 0.765); vehicle (DMSO) injection with AAV2∷GluClβ virus infection (n =5; P = 0.940). CEl_on neurons (n = 10; P = 0.497); CS-non responsive neurons (n = 9; P = 0.644). *P < 0.05 (paired t-tests with vs. without IVM in virus-injected mice).