Differences in temporal processing speeds between the right and left auditory cortex reflect the strength of recurrent synaptic connectivity

Abstract

Brain asymmetry in the sensitivity to spectrotemporal modulation is an established functional feature that underlies the perception of speech and music. The left auditory cortex (ACx) is believed to specialize in processing fast temporal components of speech sounds, and the right ACx slower components. However, the circuit features and neural computations behind these lateralized spectrotemporal processes are poorly understood. To answer these mechanistic questions we use mice, an animal model that captures some relevant features of human communication systems. In this study, we screened for circuit features that could subserve temporal integration differences between the left and right ACx. We mapped excitatory input to principal neurons in all cortical layers and found significantly stronger recurrent connections in the superficial layers of the right ACx compared to the left. We hypothesized that the underlying recurrent neural dynamics would exhibit differential characteristic timescales corresponding to their hemispheric specialization. To investigate, we recorded spike trains from awake mice and estimated the network time constants using a statistical method to combine evidence from multiple weak signal-to-noise ratio neurons. We found longer temporal integration windows in the superficial layers of the right ACx compared to the left as predicted by stronger recurrent excitation. Our study shows substantial evidence linking stronger recurrent synaptic connections to longer network timescales. These findings support speech processing theories that purport asymmetry in temporal integration is a crucial feature of lateralization in auditory processing.

Fig 1. Summary of excitatory pathways in the left and right ACx across all cortical layers.

(A, B) Patterns of excitatory synaptic input were recorded using LSPS as described in the text. Maps were averaged over all cells in each layer and then interpolated for clarity. Masked areas indicate direct hits in >50% of cells for that region. White triangles denote location of somata. Laminar boundaries were defined with respect to the fractional distance from the L1/L2 boundary to the white matter. L5A and L5B were defined as the upper and lower 50% of L5, respectively. N indicates number of recorded cells for each panel. (C) Pixel-wise significance maps (p < 0.05, unpaired 2-tailed t tests) for response amplitude in left vs. right ACx. Red and green denote significantly higher average response in the left and right ACx, respectively. Gray denotes no significant difference. (D) Same as C but maps from both hemispheres were pooled and assigned to 2 groups at random with the same total N shown in A, B. (E) Graphs of the significant pixel counts for measured (C) and random (D) comparisons. (F) Models depicting potential synaptic mechanisms underlying the right ACx’s higher excitatory connectivity in superficial layers compared to the left ACx. The left panel shows both cortices with a similar pool of presynaptic sources of EPSCs (traces) projecting onto postsynaptic targets (triangles), but the distribution of event amplitudes differs. The right panel shows the left and right ACx differ in their pool of presynaptic inputs but have a similar event amplitude distribution. (G) Observed frequency of event amplitudes in superficial layers of the left and right ACx. Inset shows empirical cumulative distribution of event amplitudes. The data underlying all the plots in this figure are included in S1 Data. ACx, auditory cortex; LSPS, laser scanning photostimulation.

Fig 2. Recurrent connections are significantly stronger in superficial layers of the right ACx.

(A) Schematic diagram of the generation of laminar input–output maps [14]. Left, 2D LSPS-derived input maps for each cell were summed over the anterior-posterior axis to produce 1D maps of input strength vs. cortical depth (vertical strips). Note that anteroposterior information is discarded, such that the 2 L6 input hotspots for the L3 cell (top) collapse to a single spot. Triangles denote soma location. Middle, the 1D maps were rotated 90 degrees (for graphic clarity), sorted by cortical depth of the soma, and binned (bin size = 80 μm). Right, the binned maps were combined into a single 2D map of presynaptic input location (x axis) vs. binned postsynaptic soma location (y axis). Maps were interpolated for display. (B) Input–output map for the left ACx, constructed as shown in A. Diagonal line indicates x = y with respect to cortical depth. The diagonal does not span the full x axis because recorded cell bodies (y axis) were confined between L2 and L6, whereas the stimulation grid (x axis) extended more broadly from L1 into the white matter. (C) Same as B but for the right ACx. (D) Same map as in B but showing only pathways in the 75th percentile and above in the left ACx. (E) Same as D but for the right ACx. (F) Summary of loops and pathways in the 75th percentile and above in the left ACx and right ACx (G). In F and G, the arrow thickness indicates strength of the pathway (thickest in the 99th percentile to thinnest in the 75th percentile), ascending pathways are shown in black, descending in gray, recurrent in violet, and open loop in dashed line. The data underlying all the plots in this figure are included in S1 Data. ACx, auditory cortex; LSPS, laser scanning photostimulation.

Fig 3. Stronger network events in the right ACx.

(A, left) All traces of cell-attached recording from an L3 excitatory neuron in the left ACx with 4 μm concentration of SR95531 in the bath. Black arrow on the x axis marks the onset of photostimulation. (A, middle) Map of action potentials evoked in the cell shown in the left panel and the population of cells recorded in the left ACx (n = 8, right). Triangles show position of the cells recorded. (B, left and middle) Same experimental conditions as in A, but conducted in the right ACx of the same animal. (B, right) Population map of all cells recorded in the right ACx (n = 8). (C) Duration of events was calculated from the onset of the first action potential to the return of the membrane potential back to baseline period (see Methods for details). (D) The duration of network events is shown using the survival function, which demonstrates that duration times are shorter in the left ACx compared to the right (n = 16). All cells were mapped using the same number of stimulus sites (i.e., same stimulus grid). The data underlying all the plots in this figure are included in S1 Data. ACx, auditory cortex.

Fig 4. Timescales of neural activity were longer in the right ACx.

(A) Schematic of the fitted exponential decay and its parameters. (B) Sketch of the procedure to estimate the bias and uncertainty in the time constant of single neurons. We used the DG model with neuron-specified exponential autocorrelations to generate surrogate data, re-fit exponentials, and extract surrogate time constants. Finally, we fit a lognormal distribution to the surrogate time constants to estimate the bias and variance. (C) Example left and right ACx data, autocorrelations, and sample of surrogate data generated from DG model with the extracted autocorrelation. (D) Bias corrected time constant with its uncertainty against mean firing rate for each neuron. Time constant error bars are the standard deviation of the surrogate lognormal distribution. Firing rate error bars are the standard error over trials. (E) Time constant posterior distributions obtained by integrating the single neuron observations for each hemisphere. The total number of cells in panels D and E is 45 (23 right ACx, 22 left ACx). The data underlying all the plots in this figure are included in S1 Data and S1 File. ACx, auditory cortex; DG, dichotomized Gaussian.