Broadly tuned response properties of diverse inhibitory neuron subtypes in mouse visual cortex

Abstract

Different subtypes of GABAergic neurons in sensory cortex exhibit diverse morphology, histochemical markers, and patterns of connectivity. These subtypes likely play distinct roles in cortical function, but their in vivo response properties remain unclear. We used in vivo calcium imaging, combined with immunohistochemical and genetic labels, to record visual responses in excitatory neurons and up to three distinct subtypes of GABAergic neurons (immunoreactive for parvalbumin, somatostatin, or vasoactive intestinal peptide) in layer 2/3 of mouse visual cortex. Excitatory neurons had sharp response selectivity for stimulus orientation and spatial frequency, while all GABAergic subtypes had broader selectivity. Further, bias in the responses of GABAergic neurons toward particular orientations or spatial frequencies tended to reflect net biases of the surrounding neurons. These results suggest that the sensory responses of layer 2/3 GABAergic neurons reflect the pooled activity of the surrounding population--a principle that may generalize across species and sensory modalities.

Figure 1. Three-dimensional imaging of visual response tuning in vivo

(A)Schematic of in vivo dye injection, volume imaging, and visual stimulation setup. (B) Left panel: Overlay of OGB-1 loaded cells (gray), SR101 stained astrocytes (orange), and GFP-expressing GABAergic neurons (green) in a three-dimensional volume of cortex that was continuously imaged at a rate of 1 Hz. Right panel: Maximum intensity volume projection across depth. (C) Example of visually evoked calcium responses in individual trials (gray traces) and average of 12 trials (black trace) for one excitatory neuron (GFP- / SR101-; black circle in B). Drifting gratings were presented in 12 directions (left panel). For 3 of these directions (0°, 120° and 240°), stimuli at 7 different spatial frequencies were presented (right panel). Stimuli were presented in pseudorandom order, but time courses are shown after sorting and concatenation. See also Figure S1.

Figure 2. Triple-immunostaining of GABAergic neurons

(A)Schematic in vivo cortical volume of OGB-1 labeled cells (left panel) and subsequent injection of a fixable fluorescent dextran into the extracellular space (right panel) to mark the region of imaging. (B) Schematic of ex vivo processing steps: (1) Freezing microtome sections were made parallel to the in vivo imaging plane by aligning in vivo and ex vivo brain orientation using the metal headpost used during calcium imaging (top left panel). (2) Fluorescent dextran injected in vivo (A) appeared in sections as a haze of extracellular staining ∼ 500 μm in diameter (middle left panel). Staining and vessel patterns permitted rapid localization of a pattern of cells ex vivo (bottom left panel) that matched the pattern imaged in vivo (A, left panel). (3) Up to 6 cell types were identified within a single volume by combining in vivo labeling and ex vivo immunohistochemical staining (right panels). (C) Examples of matching patterns of cells imaged in vivo and in immunohistochemical sections ex vivo. All images are maximum intensity projections across ∼20 μm in depth. In GAD67-GFP mice (left column), the pattern of GFP cells imaged in vivo was matched to the pattern of GFP cells ex vivo, while in wild-type mice (right column) the pattern of OGB-1 labeled cells in vivo was matched to the negatively stained ‘shadows’ of cells observed ex vivo that were produced by the extracellular dextran labeling. In overlay images (bottom row) individual colors were disproportionately saturated for visualization purposes. See also Figure S6E.

Figure 3. Simultaneous recordings of calcium transients and action potentials provide similar measurements of orientation selectivity

(A)Time courses of visually evoked calcium transients (black) and spike rates (gray) in response to the presentation of oriented gratings for a putative excitatory neuron (average of 6 trials; left). Polar plot of average tuning as measured by calcium transients (black) and spike rates (gray) for this excitatory cell (right, average of 0 s to 4 s post-stimulus onset). Tick marks on polar plots: 10% ΔF/F (black) and 1.5 spikes/s (gray). (B) Same as (A) for a PV neuron (red: calcium transients; gray: spike rates, average of 12 trials; left). Tick marks on polar plots: 4% ΔF/F (red) and 7 spikes/s (gray). (C) Comparison of the mean calcium transient evoked and the simultaneously measured spike rate for all recorded excitatory (left, black lines, mean ± SEM) and PV neurons (right, red lines). Only bins containing >4 trials are shown. Note the linearity of the relationship between calcium transients and spike rate and the higher spike rates recorded in the PV neurons. Firing rates above the transition from a solid to dashed line account for <15% of total spikes recorded. (D) Plot of orientation selectivity as measured simultaneously with calcium transients and spike rates. All values lie near the unity line. See also Figure S3.

Figure 4. Visual responses in excitatory neurons and subtypes of GABAergic neurons

(A)Simultaneous recordings of visually evoked calcium responses in three representative excitatory neurons of differing stimulus preference. All three were selective for stimulus orientation and/or direction (left traces), and a narrow range of spatial frequencies (right traces). (B) Representative visual responses from PV (top), SOM (middle), and VIP (bottom) subtypes of GABAergic neurons. PV neurons and SOM neurons were generally unselective or weakly selective to the orientation of the stimulus. VIP neurons exhibited very weak and variable visually driven calcium responses. (C) Normalized tuning curves (shaded gray) for direction (left, polar and Cartesian plots) and spatial frequency (right) for 16 visually responsive excitatory neurons drawn at random. Each point on the curves represents the mean response during the first 4 seconds of stimulation, normalized by the maximum response. Error bars are ± SEM. Black ticks on the right indicate 4% ΔF/F. Estimates of orientation selectivity and spatial frequency bandwidth are shown for each cell. ‘L.P.’ denotes low-pass cells whose response to a full field stimulus was greater than 50% of peak response. (D) Normalized tuning curves for 6 PV, 3 SOM, 3 VIP and 4 non-immunolabeled GABAergic neurons drawn at random from their respective populations.

Figure 5. Regardless of subtype, GABAergic neurons are less selective to visual stimuli (A-B)

Distributions of orientation selectivity (A) and spatial frequency bandwidth (B) demonstrate sharper tuning across excitatory neurons (black) compared with GABAergic neurons (red). Only responsive neurons (ΔF/F > 6%) were included. Low-pass cells (‘L.P.’) were excluded from subsequent tuning analyses. (C-D) Mean orientation selectivity (C) and spatial frequency bandwidth (D) of responsive excitatory neurons and subtypes of GABAergic neurons. N's for each class are shown in white. All error bars are ± SEM. * indicates p <.05. (E-F) The mean orientation selectivity (E) and spatial frequency bandwidth (F) were similar for GABAergic subtypes recorded in GAD67-GFP mice (GAD67) and wild-type mice (WT). VIP and SOM neurons were grouped into one category to increase statistical power. The category ‘All Neurons’, which includes all recorded SR101-negative cells, is shown merely as a control to compare wild-type and GAD67-GFP mice. Orientation selectivity was calculated as 1 - circular variance. For distributions of orientation selectivity calculated by alternate methods (Niell and Stryker, 2008), see Figure S4.

Figure 6. GABAergic tuning reflects the population average

(A)Three examples of the orientation tuning of the population average (top row, blue; average of all cellular responses within each volume) and of one representative inhibitory neuron (middle row, red) and excitatory neuron (bottom row, black) from each local population. Thick straight lines indicate estimated orientation preference. Orientation preference was not estimated for cells or population averages with tuning OSI < 0.05. Tick marks along the horizontal axis indicate 4 % ΔF/F. The number to the left of the each cellular polar plot is the difference (in degrees) between the cell and population preferred orientation. (B) Three population examples of spatial frequency tuning curves (dots) and difference-of-Gaussian fits (solid curves). As in (A), top panel indicates population average and lower panels indicate individual inhibitory and excitatory neuron tuning curves. We estimated preferred spatial frequency (vertical lines), and calculated the difference (in octaves) between the cell and population preferred spatial frequency (numbers above each panel). (C) Distribution of absolute differences between neuron and population orientation preferences for inhibitory (red) and excitatory (black) neurons, restricted to neurons with robust estimates of preference (see Experimental Procedures). (D) Distribution of absolute differences between the neuron and population preferences for spatial frequency. See also Figure S5.

Figure 7. Model of GABAergic tuning as a reflection of local population average

Within precisely organized maps (left panel, e.g., cat visual cortex), broad pooling of iso-oriented (similar color) inputs from surrounding pyramidal cells (triangles) and other sources produces highly selective GABAergic neurons (central ellipse). For regions with slight overall tuning bias or coarsely organized maps (e.g., rodent barrel cortex), broad pooling of inputs with a net bias produces moderately selective GABAergic neurons that reflect this population bias (middle panel). In cortical regions with no bias, GABAergic neurons are broadly tuned (right panel). See also Figure S6.