Variable dendritic integration in hippocampal CA3 pyramidal neurons

Abstract

The hippocampal CA3 region is essential for pattern completion and generation of sharp-wave ripples. During these operations, coordinated activation of ensembles of CA3 pyramidal neurons produces spatiotemporally structured input patterns arriving onto dendrites of recurrently connected CA3 neurons. To understand how such input patterns are translated into specific output patterns, we characterized dendritic integration in CA3 pyramidal cells using two-photon imaging and glutamate uncaging. We found that thin dendrites of CA3 pyramidal neurons integrate synchronous synaptic input in a highly supralinear fashion. The amplification was primarily mediated by NMDA receptor activation and was present over a relatively broad range of spatiotemporal input patterns. The decay of voltage responses, temporal summation, and action potential output was regulated in a compartmentalized fashion mainly by a G-protein-activated inwardly rectifying K(+) current. Our results suggest that plastic dendritic integrative mechanisms may support ensemble behavior in pyramidal neurons of the hippocampal circuitry.

Figure 1

Nonlinear Dendritic Integration of Multiple Synchronous Synaptic Inputs in Basal Dendrites of CA3 Pyramidal Neurons (A) Top: low-magnification fluorescent image of a hippocampal slice with a CA3 pyramidal neuron loaded with Alexa Fluor 488. Bottom left: two-photon stack of the basal arborization of the same neuron. Dendritic segment of interest is highlighted by yellow circle. Bottom right: high-magnification stack of the dendritic segment. (B) Arithmetic sum (left) and measured responses (middle) to a varying number of synaptic inputs evoked by two-photon glutamate uncaging. Right: dotted box in middle panel expanded (top) with corresponding first temporal derivatives of the traces (bottom). (C) Input-output function of the dendrite in (B). Dotted line represents linear function. (D) Summary (mean ± SEM) of the input-output function of 57 branches from 42 cells. Dotted line represents linear function. Gray line represents linear projection of the slope of the measured points under 4 mV expected peak. Error bars for the x axis are within the symbols. (E) Histogram of the nonlinearity, measured as the average peak_gluEPSP–peak_expected in the 5–8 mV expected amplitude range (dotted box in D). Dendrites with nonlinearity >2 mV (gray) were considered as supralinear integrators.

Figure 2

Properties of Fast Na⁺ Spikes (A) Na⁺ spike dV/dt versus distance of input site from the soma for basal primary (red dots) and terminal (blue dots) as well as apical primary (green dots) and terminal (black dots) branches. Input distance along oblique dendrites from apical trunks was 38 ± 3 μm (range: 12–69 μm; n = 34). (B and C) Left: distance-dependent distribution of dendritic Na⁺ spike strength in primary parent dendrites (B) and in terminal daughter dendrites (C) of CA1 (black, basal and apical perisomatic branches) and CA3 (red, basal branches) neurons. Right: cumulative probability of Na⁺ spike strength in the distance range indicated by the dashed box in the left panel (B, CA3: n = 41, CA1: n = 62, input 30–60 μm from soma, p < 0.05; C, CA3: n = 21, CA1: n = 30, input at 15–43 μm from the last branch point and 70–90 μm from soma, p < 0.01, Kolmogorov-Smirnov test). (D) Spike dV/dt of strong parent dendrites (P) and of connected daughter dendrites (D) in CA3 pyramidal cells. Red lines, functionally coupled P-D pairs (characterized by similar dV/dt values); blue lines, uncoupled pairs. Top schematic shows approximate stimulation positions. (E) Effect of Na⁺ spikes, evoked in perisomatic primary parent dendrites, on the AP output in CA1 and CA3 pyramidal cells. Top traces: Na⁺ spike evoked by synchronous uncaging (marked by arrow) directly evokes APs from V_rest in CA1 (left) but not in CA3 (right) pyramidal neurons. Hyperpolarization in CA1 reveals the strong Na⁺ spike triggering the precisely timed AP. Bottom: corresponding dV/dt traces. (F) Percentage of perisomatic primary parent dendrites in CA1 (n = 18/20) versus CA3 cells (at rest (V_r), n = 27/89, p < 0.001, χ² test; and at −60 mV, n = 8/14, p < 0.05, Fisher’s exact test) where the local Na⁺ spike directly evoked APs. Na⁺ spikes triggered in apical oblique dendrites were never strong enough to evoke an AP output (0/17 dendrites). Data are represented as mean ± SEM. See also Figure S1.

Figure 3

NMDARs Mediate Nonlinear Dendritic Integration in CA3 Pyramidal Cells (A) Stack two-photon image of a CA3 pyramidal cell. Yellow circle highlights stimulated dendritic segment. (B) Arithmetic sum (expected, left) and measured voltage responses evoked by uncaging at a variable number of synaptic inputs on the dendrite shown in (A) in the presence of 1 μM TTX. (C) Summarized effect of 0.5–1 μM TTX on the input-output function in CA3a pyramidal cells. Control data is also included in the data set of Figure 1D. Error bars for the x axis are within the symbols. (D) Stack two-photon image of a CA3 pyramidal cell. (E) Arithmetic sum (expected, left) and measured voltage responses evoked by synaptic inputs on the dendrite shown in (D) in the presence of 50 μM D-AP5. (F) Summarized effect of NMDAR blockers (50 μM D-AP5 or 20 μM MK801, pooled) on the input-output function. Control group is also included in the data set of Figure 1D. (G) Input-output function (left) and magnitude of nonlinearity (right) in the three CA3 subregions. Most x axis error bars are within the symbols. (H) Left: expected (gray) and measured (black) responses to synchronous synaptic stimulation in a control cell (top traces, 35 inputs) and in a different cell in the presence of 50 μM D-AP5 (bottom traces, 28 inputs). Cells were kept at V_rest (−68 to −72 mV). Right: percentage of the dendrites where APs were generated by synaptic stimulation in the 5–8 mV expected amplitude range. Data are represented as mean ± SEM. See also Figure S2.

Figure 4

Spatial and Temporal Determinants of NMDAR-Mediated Nonlinear Integration (A) Stack two-photon image of a dendritic segment in the basal arbor, with synaptic inputs clustered in the middle (left) or distributed along the dendrite (right). (B) Representative examples with expected (left) and measured (right) voltage responses to a distributed input pattern in a dendrite integrating them in a nonlinear fashion (top traces, data from dendrite in A) and in another dendrite integrating them linearly (bottom traces). Responses to clustered stimulus are not shown. (C) Summary of the input-output relationship to distributed input. Blue, dendrites with linear integration (n = 6 out of 11 dendrites); red, dendrites with nonlinear integration (n = 5/11). Black, clustered input tested in some of the dendrites (n = 7). Inset: all experiments with distributed input pooled (gray, n = 11) versus clustered data (black, n = 7). (D) Comparison of nonlinearity to distributed versus clustered input. Color code is as in (C). (E and F) Relationship between the magnitude of nonlinearity evoked by distributed input and the length of the dendritic segment where the inputs were distributed (E) and the median distance between all uncaging points (F). (G) Representative experiment using different ISIs at 25 spatially clustered inputs. (H) Summary of the sensitivity of nonlinearity to input timing. Data are represented as mean ± SEM.

Figure 5

Variability of NMDA Spike Kinetics (A) Representative traces of NMDA spikes from two dendrites in different neurons, one with fast decay (left) and one with slow decay (right). (B) Histogram of the half-width (n = 280 dendrites in 182 cells). Black, fast spikes; red, slow spikes, separated at 70 ms. (C) Half-width versus distance from soma in basal dendrites (n = 258). (D) Half-width of NMDA spikes evoked in consecutively tested dendrites within the apical or in the basal arbor of individual cells. Black lines represent only fast or only slow dendrite groups (67 cells); blue lines represent mixed dendrite groups (18 cells). (E) As in (D) but for dendrites stimulated in the apical versus basal arborization of individual cells (mixed dendrites in 5/11 cells). (F) Relationship between half-width and the magnitude of nonlinearity (n = 46, basal dendrites). (G) Input-output relationship for fast (black, n = 19) and slow (red, n = 27) NMDA spikes. Data are represented as mean ± SEM. Error bars for the x axis are within the symbols. (H) Relationship between half-width and the strength of the fast Na⁺ spike in the same dendritic segment (n = 46, basal dendrites). See also Figure S3.

Figure 6

Regulation of NMDA Spike Decay by K⁺ Currents (A–F) (i) Representative individual traces at two stimulation strengths (different laser power or synapse number) in dendrites with fast (left) or slow (right) spikes before (black) and after (gray) bath application of various K⁺ current modulators. Traces with similar amplitudes (not necessarily same laser power) are displayed for clear comparison of decay kinetics. (A) Ba²⁺ (200 μM); (B) 4-AP (2 mM, in the presence of 1 μM TTX); (C) Ba²⁺ (30 μM); (D) tertiapin-Q (0.5 μM); (E) baclofen (20 μM); (F) apamin (0.1 μM). (ii) Summary of the effect of K⁺ current modulators on NMDA spike half-width (black, half-width < 70 ms, red: half-width > 70 ms). (iii) Fractional effect of K⁺ current modulators on NMDA spike half-width (black, half-width < 70 ms, red: half-width > 70 ms). See also Figure S4.

Figure 7

NMDA Spike Decay Determines AP Output to Theta-Modulated Repetitive Synaptic Input (A) Top: theta stimulus paradigm. Middle: representative responses from dendrites with fast (left) and slow (right) NMDA spikes. Bottom: magnified traces from middle panel subthreshold to AP generation. Thick traces represent average. (B) Summary of summation by theta paradigm of fast (black) and slow (red) NMDA spikes. (C) Probability of generating the first AP among the four theta stimulation cycles in fast (black) and slow (red) NMDA spikes. (D) Firing index (see Experimental Procedures) in the two groups. (E) Relationship between half-width and firing index. The longer the half-width, the earlier the first AP-generating stimulation cycle was. (F) Representative recordings (average of at least three traces) demonstrating the effect of baclofen (top) and 30 μM Ba²⁺ (bottom) on paired-pulse summation of slow and fast NMDA spikes, respectively. (G) Summary of the effect of various K⁺ current modulators on the half-width and paired-pulse summation (20–25 inputs, 100 ms delay). Each line represents an individual experiment in which substantial change in half-width occurred. Dotted end on each line marks control condition. Data are represented as mean ± SEM. See also Figure S5.