Parsing social context in auditory forebrain of male zebra finches

Abstract

To understand the influence of natural behavioral context on neural activity requires studying awake-behaving animals. Microdrive devices facilitate bridging behavior and physiology to examine neural dynamics across behavioral contexts. Impediments to long-term single unit recordings in awake-behaving animals include tradeoffs between weight, functional flexibility, expense, and fabrication difficulty in microdrive devices. We describe a straightforward and low-cost method to fabricate versatile and lightweight microdrives that remain functional for months in awake-behaving zebra finches (Taeniopygia guttata). The vocal and gregarious nature of zebra finches provide an opportunity to investigate neural representations of social and behavioral context. Using microdrives, we report how auditory responses in an auditory association region of the pallium are modulated by two naturalistic contexts: self- vs. externally-generated song (behavioral context), and solitary vs. social listening (social context). While auditory neurons exhibited invariance across behavioral contexts, in a social context, response strength and stimulus selectivity were greater in a social condition. We also report stimulus-specific correlates of audition in local field potentials. Using a versatile, lightweight, and accessible microdrive design for small animals, we find that the auditory forebrain represents social but not behavioral context in awake-behaving animals.

Fig 1. Experimental design of microdrive recordings in awake freely moving birds.

A) Hub and stage parts modified from du Hoffman et al. (2011). B) Example of a fully-built microdrive. C) Printed circuit board layouts for 16- and 32-channel electrode interface boards. D) Schematic of experimental chamber. A counterbalanced lever lessened torque and weight of microdrive exerted on the bird’s head during recording. E) Representative peri-stimulus time histogram of a single-unit in response to birdsong playback. F) distribution of peak-to-peak widths and decision boundary for labeling as BS or NS. Inset: exemplar unit waveforms.

Fig 2. Bird’s own song is similarly represented by NCM neurons when sung or played back a) Schematic of behavioral contexts. b-e) Effect of behavioral context on response properties of neurons in solitary audition vs directed song.

Blue =  BS neurons; red =  NS neurons. b) $F{R}_{motif}$ for both BS and NS neurons increased subtly for both neuron during directed song. c) $BLFR$ for both BS and NS neurons increased subtly during directed song. d) $Z_{motif}$ for NS neurons but not for BS neurons increased subtly during directed song. e) $Offsetratio$ in BS neurons decreased during undirected song. Left: unfiltered, right: filtered for neurons without SSA. Asterisks indicate significance of p <  0.05. Dots indicate individual neurons, horizontal lines indicate mean, and thin vertical lines indicate 95% confidence intervals.

Fig 3. Social context modulates multiple response parameters in NCM neurons. a) Schematic of solitary and social audition. b) BL FR across contexts, for NS (red) and BS (blue) neurons.

The right axis is an enlarged version of the left axis. No units have been excluded due to SSA. c) Pooled Z and Z for BOS REV across contexts, with low-SSA units excluded. d) Pooled offset Z and offset Z for BOS REV across contexts, with low-SSA units excluded. e) d’ across contexts in two representative neurons for each possible combination of stimuli. The y-axis is mirrored on the x-axis such that each box is $d_{rowstimulus-columnstimulus}$, and the diagonal compares each stimulus to itself. f) Average BOS d’ across CON, WN, and BOSR (BOS REV) for NS and BS neurons. The left axis does not exclude adapting neurons on the basis of SSA while the right axis excludes adapting units. Three asterisks indicate p <  0.01, one asterisk indicates p <  0.05.

Fig 4. Log-power differences during solitary audition in arbitrary units of LFP signal from 0-50 Hz between a) stimulation and baseline (pre) and b) between baseline (pre) and baseline (post).

Stars and dots respectively indicate significant and nonsignificant responses at a given frequency. Rejection of the null hypothesis that baseline and stimulus power spectral densities were from the same distribution at a 1% significance level. c) Difference between baseline-subtracted social and solitary audition. Positive values indicate higher baseline-subtracted LFP during solitary audition and a negative value denotes a higher baseline-normalized LFP signal during social audition.