Abstract

Motivated behaviors, such as social interactions, are governed by the interplay between mesocorticolimbic structures, such as the ventral tegmental area (VTA), basolateral amygdala (BLA), and medial prefrontal cortex (mPFC). Adverse childhood experiences and early life stress (ELS) can impact these networks and behaviors, which is associated with increased risk for psychiatric illnesses. While it is known that the VTA projects to both the BLA and mPFC, the influence of these inputs on local network activity which govern behavioral states—and whether ELS impacts VTA-mediated network communication—remains unknown. Our study demonstrates that VTA inputs influence BLA oscillations and entrainment of mPFC activity in mice and that ELS weakens the ability of the VTA to coordinate BLA network states, while also impairing dopaminergic signaling between VTA and BLA. Optogenetic stimulation of VTABLA terminals decreased social interaction in ELS mice, which can be recapitulated in control mice by inhibiting VTA→BLA communication. These data suggest that ELS impacts social reward via the VTA→BLA dopamine network.

Significance Statement

It is well established that oscillatory states in the basolateral amygdala (BLA) govern behavioral states. However, a gap in our knowledge exists regarding the mechanisms mediating transitions between BLA network states. Here we demonstrate a novel mechanism modulating BLA network states involving dopamine inputs from the VTA. Further, we demonstrate that early life stress, a major risk factor for psychiatric illnesses, impairs the ability of dopaminergic inputs from the VTA to coordinate BLA and mPFC network states. Thus, this study provides a novel mechanism mediating transitions between oscillatory states in the BLA which are well documented to govern behavioral states and demonstrates pathological perturbations in the ability of the VTA to coordinate BLA network states following early life stress.

Introduction

Adverse childhood experiences (ACEs) are major risk factors for psychiatric illnesses. For example, maternal neglect is known to impair cognition, weaken resiliency toward future stressors, and increase the propensity to develop mood and substance use disorders in affected offspring (Bolton et al., 2018; Reshetnikov et al., 2020; for review see Delavari et al., 2016). Recent reports show that roughly 20% of children in the United States are exposed to ACEs and research has found a striking comorbidity between frequency and severity of ACEs with psychiatric illnesses (Humphreys et al., 2020; Sheridan and McLaughlin, 2020; Berman et al., 2022). In conjunction with these findings, decades of work have implicated the mesocorticolimbic system (MCL) as being a psychophysiological focal point due to its susceptibility to the effects of stressors (Sullivan and Dufresne, 2006; Butts et al., 2011), including early life stress (ELS; Rodrigues et al., 2011; Ventriglio et al., 2015), and its involvement in proper establishment and maintenance of reward processing and subsequent motived behaviors (Fibiger and Phillips, 1988). These epidemiological and deductive research studies support a role for the MCL in contributing to behavioral deficits associated with early life adversity; however, the mechanisms through which ELS influences the MCL to induce altered behavioral outcomes remains unclear. Revealing these mechanisms has the potential to provide both useful information regarding the pathophysiology of disease and potential novel avenues for therapeutic intervention.

Many aspects of motivation involve dopaminergic (DA) neurons within and across the MCL. Further, studies have shown that the MCL DA system is not fully developed until adulthood in both humans (Rothmond et al., 2012) and rodents (Voorn et al., 1988), making adolescents particularly vulnerable to ACEs and ELS, respectively (Bayer et al., 1993). Specifically, in rodents, the MCL DA system hits maturity on postnatal day 21 (P21; Voorn et al., 1988) with hindbrain features (e.g., neurons and neuropeptides) known to be structurally and functionally altered following ELS by this timepoint (Dubé et al., 2015; Bolton et al., 2018). While a growing body of research has narrowed the impact of ELS to a subset of nodes within the MCL, the mechanisms mediating the developmental impact of altered DA signaling on emotional processing and motivation are not fully understood.

Accumulating evidence from our lab and others demonstrates that network states (distinct oscillatory activity, quantified as local field potentials; LFPs) in the basolateral amygdala (BLA) govern behavioral states (Cao et al., 2016; Antonoudiou et al., 2022; Fu et al., 2022), particularly those involved in valence processing (Nukitram et al., 2021; DiLeo et al., 2022). Moreover, the BLA is well established as the primary emotional hub within the mammalian brain (Wolf et al., 2004; Namburi et al., 2016; Ju and Beyeler, 2021). Previous research has also shown that the VTA (Martínez-Hernández et al., 2006; Valencia-Torres et al., 2017) and connections between the VTA and regions across the MCL (Lowes et al., 2021; Smith and Torregrossa, 2021; Sun et al., 2021) are necessary for proper regulation of incentive attributions of salience to stimuli, which influence behaviors. The VTA has direct projections to the BLA (Floresco and Maric, 2007; Lüthi and Lüscher, 2014; Correia and Goosens, 2016), which monosynaptically projects to the medial prefrontal cortex (Floresco and Maric, 2007; Cheriyan et al., 2016; Sun et al., 2019; mPFC; anterior region of the MCL)—a region also known to be susceptible to stress (Shansky and Morrison, 2009; Belleau et al., 2019) and is involved in motivation processing (Somerville et al., 2013; Ko, 2017; Yang et al., 2022). Therefore, it is reasonable to hypothesize that VTA inputs into the BLA likely influence motivated behaviors.

Despite the acknowledgment of the VTA's projections to both the BLA and mPFC, the specific influence of these DA pathways on local network dynamics and motivated behaviors remains elusive. Moreover, the impact of ELS on VTA→BLA communication and the mechanisms mediating the subsequent behavioral consequences have yet to be fully elucidated. This study addresses these gaps in knowledge by examining the intricate modulatory role of the VTA in regulating oscillatory states in the BLA and, in turn, influencing mPFC activity and social motivation. In foundational experiments within control DAT-Cre animals, where Cre-dependent opsins were expressed in the VTA, we demonstrate that DA released from the VTA is sufficient to drive BLA activity across a range of stimulation frequencies. We go on to show that while the VTA robustly controls BLA and entrains mPFC network states, driving BLA→mPFC coherence, ELS diminishes these effects. Further, we show that activation of VTA projections to the BLA results in social avoidance in ELS mice but not in control mice with VTA→BLA DA signaling intact. Inhibition of these VTA efferents increases social avoidance in control mice, further supporting this network's involvement in stress vulnerability, and its control over stimulus incentive assignment. These findings have implications for our understanding of the etiology and potential therapeutic interventions for psychiatric disorders marked by disrupted motivation and reward processing.

Materials and MethodsAnimals

C57BL/6J mice were housed at Tufts University School of Medicine in a temperature- and humidity-controlled environment, maintained on a 12 h light/dark cycle (lights on at 7 A.M.) with ad libitum access to food and water. All animal procedures were handled according to the protocols approved by the Tufts University Institutional Animal Care and Use Committee (IACUC).

Early life stress paradigm

Pregnant C57BL/6J dams were purchased directly from Jackson Laboratory and were delivered and singly housed on day 16 of gestation (E16) at Tufts University School of Medicine. These cages were checked daily for litter births, at which time litters were randomly assigned to standard-rearing (control; CNT) or maternal separation (ELS) groups. ELS began on P1 and consisted of the removal and placement of the dam into a clean cage, out of the sight of her litter, for 3 h (beginning at 9 A.M.) for 5 d per week from P1 toP21. Offspring were weaned on P21. For all experimental conditions, ELS and CNT animals were age and litter matched.

Stereotaxic surgery

Adult (>P60) male CNT and ELS mice were anesthetized by intraperitoneal injection (i.p.) of a ketamine/xylazine cocktail (90–120 mg/kg and 5–10 mg/kg, respectively). Before the onset of the procedure, sustained release buprenorphine (0.5–1 mg/kg) was administered subcutaneously as postoperative analgesia. The head of the mouse was shaved, antiseptic solution was applied, and an incision on the scalp was made to expose the skull. For viral injections, mice were unilaterally injected with a virus targeted at either the BLA or ventral tegmental area (VTA; see Table 1 for details) using a pulled glass pipette at a flow rate of 100 nl per minute using positive pressure from a 10 ml syringe. All viruses were purchased from Addgene. Post hoc imaging was performed to validate targeted viral expression.

Table 1.

Stereotaxic viral injection methods

LFP recordings

LFP recordings were performed in awake, adult C57BL/6J CNT and ELS mice, using custom-designed headmounts (Pinnacle 8201-C). These headmounts consisted of two depth electrodes (PFA-coated stainless steel wire, A-M Systems) targeted at the medial prefrontal cortex (mPFC; from bregma: AP: +1.75; ML: −0.30; DV: −2.0 mm) and BLA (from bregma: AP: −1.35; ML: −3.20; DV: −5.10 mm). The headmounts were affixed to the skull using stainless steel screws as ground and reference following 2.5 weeks from viral injection. The LFP data were bandpass filtered (1–250 Hz, Chebyshev Type II filter), and spectral analysis was performed in Python using custom-made scripts utilizing the fast Fourier transform. Specifically, spectral analysis of the LFP/EEG signal was performed using the short-time Fourier transform (STFT) with a 5 s Hann window and 50% overlap as done previously (Antonoudiou et al., 2022). The power line noise (59–61 Hz) was removed and values were filled using nearest interpolation. Outliers in each spectrogram were identified using a two-stage process. Firstly, a time-series was obtained from the mean power across frequencies of each spectrogram. Large deviations, defined as those greater than the mean plus 4 times the standard deviation, were replaced with the median of the nonoutlying data. Then, a sliding window method was applied to detect more subtle outliers based on local context, using 5× the median absolute deviation (MAD) of each 5 min window. Resulting outliers were removed and replaced with forward fill interpolation of the nearest values. All resulting time-series, obtained from the mean power across frequencies, were manually verified.

For optogenetic experiments, CNT and ELS mice expressing either ChrR or Jaws (Table 1) were implanted with an in-house modified version of the described headmounts, optrode, which consisted of the addition of an optic fiber (200 µm, 0.22 NA; Thorlabs) attached to the depth electrode aimed at BLA. Photostimulation was performed with a red light delivered through the optic fiber coupled to a red laser (640 nm, max power = 500 mW, Laserglow Technologies). The light intensity setting used for all optogenetic experiments in awake mice was measured at 30–40 mW from the end of the opto-cannula (Thorlabs; 200 µm, 0.39 NA). Sine waveforms for photostimulation were generated through LabChart (ADInstruments). The LFP data were bandpass filtered between 3 and 300 Hz.

For pulsed photostimulation experiments (5, 10, 20, and 40 Hz), stimulations were pseudorandomized, where each stimulation frequency was repeated three times, and post hoc analyses revealed no presentation order effect on power elevation. The average response was used for further quantification. The power spectral densities for optogenetic experiments were obtained in 1 s bins (50% overlap) using custom-made Python scripts. For LFP power ratio, quantification of the power of the oscillations was obtained at approximately ±1 Hz of each stimulation frequency during (0−120 s) and before stimulation (0−30 s). Only stimuli that produced phase-locked LFP responses ±2 standard deviations from group average were included. The continuous Morse wavelet transform (Lilly and Olhede, 2012) was used to visualize opto-spectrograms. For LFP coherence analyses, BLA→mPFC LFP synchronization was quantified using the phase locking value (PLV; Lachaux et al., 1999), obtained around bandpass-filtered ±1 Hz of each stimulation frequency, using custom-made Python scripts. These values were normalized across frequencies as a ratio between stimulation period and baseline period, as done for power-ratio analyses.

Recording in vivo dopamine responses in BLA

Biosensing of dopamine binding was performed in awake, adult CNT and ELS animals, using the GRAB-DA sensor and the nVoke miniaturized microscope (an integrated imaging and optogenetics system, 455 nm blue GCaMP excitation LED, 590 nm amber optogenetic LED, Inscopix). Following injection of ChrR in VTA and GRABDA2m in BLA (Table 1), an Inscopix lens affixed to a baseplate (Inscopix, 1050-004413) was placed in the BLA. Mice were allowed to recover for 7 weeks prior to experimentation to allow for optimal viral expression and in vivo imaging. On the recording day, each animal was removed from their home cage, placed in a testing cage (a cage identical to home cage, containing fresh bedding/nesting), and had the miniature integrated microscope system (nVoke HD 2.0; Inscopix) attached to their baseplate. Each animal was given 10 min to habituate to the testing cage, at which time images were acquired using data acquisition software (ver. 2.0.0; Inscopix) at 20 frames per second, 20% of LED power, and a gain kept between (2 and 5, varying based on clarity of field of view; FOV). Images were acquired across a 10 min session consisting of 15 trials of 40 hz, 5 s pulse trains (5 ms width) of 620 nm LED (20 mW) light initiated every 30 s.

Acquired imaging data were downsampled (1/2 spatial binning), preprocessed, motion corrected, DA transients of ROIs (three concentric circles as detailed in Inscopix Processing Guidelines: https://iqlearning.inscopix.com/best-practices/applications/nt-imaging/single-color/processing) were extracted, and a change in fluorescence (ΔF/F) was computed using Inscopix Data Processing Software (ver. 1.9.2; Inscopix). All extracted traces were then subjected to a series of custom-built Python scripts which quadratically detrended the DA signals (to account for photobleaching across a session; application of a second-degree polynomial fit as seen in Zarahn et al., 1997; Taylor et al., 2021), normalized each ROI to the mean baseline (prestimulation) periods, and then parsed these signals into individual trials for analyses. Given that the DA response is intrinsically linked to the available DA in the region of recording, all statistical tests were computed using the trials as observations, thus accounting for the dependent nature of DA depletion across a session.

Three-chamber social interaction task

We recorded behavior from adult CNT and ELS mice during a three-chamber social interaction task (3CST) following 3 weeks postviral infusion in a Plexiglas rectangular box (71 cm × 30 cm × 35 cm), made up of three identically shaped compartments, without a top. The compartments were separated by a transparent piece of Plexiglas, with cut-outs to allow for free movement between each compartment. The left and right compartments each had an inverted wire cup (diameter 8 cm) placed in the center of them, which had a designated depressed (1/4 inch lower) cylindrical section to ensure wire cups remained in place throughout testing. The apparatus and wire cups were thoroughly cleaned with 70% ethanol between each trial.

The 3CST consisted of two sessions (Toy-Toy and Toy-Female), each made up of a habituation and testing trial. The testing protocols were identical in structure made up of four trials, each with the inverted cups holding either a toy or a novel, female conspecific: mice explored the arena and toys (Toy-Toy session; habituation) for 10 min, they repeated this with the exception that one of the sides (testing; pseudorandomly chosen) triggered photostimulation upon physical entrance into the interaction zone (3 cm space directly extending beyond the wire cup), they begin a new habituation trial where they can explore and interact with a toy or a female mouse (Toy-Female; habituation), and finally they explore the arena with the same female mouse, triggering photostimulation upon entrance into the interaction zone around her wire cup (testing). During interaction zone triggered stimulation, mice received VTABLA 30–40 mW photostimulation through the optic fiber coupled to a red laser (640 nm) at 40 Hz (Table 2).

Table 2.

3CST sample protocol

The overall activity of the test mouse in the 3CST was automatically recorded with the EthoVision XT video tracking system (Noldus). The amount of time that test mice spent in each chamber and the immediate vicinity (3 cm) of the cages (termed as “interaction zone”) was measured. A custom-built Arduino script was used to receive inputs from EthoVision XT, which detailed when an animal was in the interaction zone, causing the 640 nm laser to send the 40 hz pulse trains (described above) indefinitely, until the animal left the interaction zone. Social preference scores (PS) were calculated as the percentage of time spent in the stimulation side (TS) out of the total time spent in either left or right side of the area (TS + TNS; Eq. 1). Normalized preference scores (NS) were calculated as the ratio between the preference score observed during the testing trial (PST) and the preference score observed during the habituation trial (PSH; see Eq. 2). Here, time (T) is the cumulative seconds that the nose of the test mouse was detected in the interaction zone (which ensures actual interaction between test mouse and caged object; toy or female mouse). In this manner, we were able to unbiasedly quantify interaction preference, whereby a PS value >1 indicates more time spent interacting on the stimulation side. An NS value >1 indicates the 640 nm stimulation (testing trials) increased this interaction time, in comparison with nonstimulated (habituation) trials.PreferenceScore(PS)=100×TS(TNS+TS)(1) NormalizedPreferenceScore(NS)=100×PSTPSH.(2) Female conspecifics in estrous (most receptive to mating) verified using vaginal lavage and microscopy according to Cora et al. (2015) were used as the social stimulus. Groups were counterbalanced for order of light stimulation as well as side assigned as the social zone (see Table 2 for details). A three-way mixed ANOVA (lifegroup × stimulation side × session) was performed and revealed no significant difference (p > 0.05), revealing that the session presentation order, nor side the stimulation occurred on, affected CNT and ELS animals differently.

Quantification and statistical analysis

All statistical analyses were performed using Python (Python Software Foundation). Multigroup tests were tested with ANOVAs followed by post hoc multiple comparisons. A Greenhouse–Geisser correction was applied where appropriate and when assumption of sphericity was violated. For electrophysiological parameters between two groups, Mann–Whitney U tests were run with Benjamini/Hochberg procedure to control for false discovery rate (statsmodels). For comparison of ELS and CNT, appropriate one-way tests were applied, chosen based on distribution of data and test assumptions. The statistical package Pingouin was used for all tests, except for correlation analyses and patch-clamp electrophysiological comparisons. All tests and results are reported for each comparison, named in accordance with the figure the results detail. A p value <0.05 was considered statistically significant.

Results

To determine whether dopaminergic inputs from the VTA had a mediating effect on BLA activity, we infused AAV-DIO-ChrR-tdT into VTA in standard-reared (CNT) DAT-Cre mice. Following a transfection period to allow for expression of ChrR-tdT in projection neurons from VTA, pulsed red light (640 nm) photoexcitation (5–40 Hz) in the BLA produced robust phase-locked LFP responses in the BLA (Fig. 1, Table 3) and coordinating BLA activity. It is important to note that repeated photostimulation did have any effect on power elevation (Fig. 2E,F; Table 4). These findings underscore the significant role that VTA DA has in regulating the BLA, supporting the validity of investigating how these dynamics might be altered under conditions of developmental stress.

Figure 1.

VTABLA photostimulation DAT-Cre mice drives network activity. inhibits ability for VTABLA to drive network activity. A, Schematic of sagittal view shows at P70, in DAT-Cre mice (N = 7), AAV-Syn-ChrimsonR-tDT was injected into VTA, with an optrode placed into BLA while a grounding screw was placed over frontal cortex (FC). B, Summary of LFP power ratio from BLA between pulsed stimulation and baseline periods (baseline = 0) where power was measured at each stimulation frequency for three, 2 min trials. Asterisks within bars indicate significant change from baseline. *p < 0.05, **p < 0.01, ***p < 0.001. Error bars represent SEM.

Figure 2.

VTABLA robustly drives BLA and mPFC network activity. Representative traces and STFT transformations for a CNT animal during a (A) 5 Hz, (B) 10 Hz, (C) 20 Hz, and (D) 40 Hz trial. Top, Stimulated frequency LFP trace atop filtered (2–100 Hz) LFP traces (gray) from BLA (left) and mPFC (right). Middle, zoomed in portions from above traces show five periods before, during, and after 10 mW 640 nm photoexcitation. Bottom, STFT transformation from respective traces; horizontal white lines indicate onset/offset of 640 nm laser. E, Grouped bar plot, organized by stimulation order, shows LFP power ratio between pulsed stimulation and baseline periods where power was measured at each stimulation frequency for CNT (blue, n = 7) animals. F, Same as E with the exception that analyses performed on ELS (red, n = 8) animals. Spectrograms were not bandpass filtered but the power around stimulation frequencies were retrieved for the relative power plot in subpanels E and F.

Table 3.

Statistical analyses for Figure 1

Table 4.

Statistical analyses for Figure 2

To probe whether VTA→BLA (VTABLA) activation influences BLA network activity, and if developmental stress alters these responses, we implemented an ELS protocol in male C57BL/6J mice, such that mice were either CNT or subjected to maternal separation stress for 3 h daily, 5 d per week from P1 to P21 (Fig. 3A). Following weaning and maturation, infusion of AAV-ChrR-tdT viral vector into VTA resulted in expression of ChrR-tdT in projection neurons from VTA, with strong terminal expression centered in BLA (Fig. 3B). The aforementioned photoexcitation experiment was repeated for these CNT and ELS animals, resulting in significant phase-locked LFP responses in both the BLA and mPFC, indicating that excitation of VTA inputs into the BLA is sufficient to control BLA network synchronization across a range of frequencies and entrain the mPFC network, with ELS attenuating this effect (Fig. 3D, Table 5). These results suggest that the ability for VTA inputs into the BLA to coordinate BLA→mPFC network states is impaired following ELS, which may give rise to aberrant processing of salient cues (Lauzon et al., 2009; Yizhar and Klavir, 2018) and, thus, maladaptive behaviors (Felix-Ortiz et al., 2016; for review see Likhtik and Paz, 2015).

Figure 3.

ELS inhibits ability for VTABLA to drive network activity. A, Experimental timeline for ELS cohort. Timeline is identical for CNT cohort excluding maternal separation (D1–21). B, Left, Schematic of sagittal view shows at P70, AAV-Syn-ChrRimsonR-tDT was injected into VTA, with an optrode and electrode placed into BLA and mPFC, respectively. Right, Representative fluorescence images of -tdT expression in the BLA. C, Top, Representative 20 Hz LFP trace (colored) overlaid on raw LFP trace (2–100 Hz; gray) from BLA (left) and mPFC (right). Middle, Zoomed in portions from above traces show five periods before, during, and after 10 mW 640 nm photoexcitation. Bottom, STFT transformation from respective traces; vertical dashed white lines indicate onset/offset of 640 nm laser. Spectrogram was not bandpass filtered but the power around stimulation frequencies were retrieved for the relative power plot for D. D, Summary of LFP power ratio from BLA (left) and mPFC (right) between pulsed stimulation and baseline periods (baseline = 0) where power was measured at each stimulation frequency for CNT (blue, n = 7) and ELS (red, n = 8) conditions. Asterisks within bars indicate significant change from baseline. Asterisks atop horizontal bars indicate difference between CNT and ELS. *p < 0.05, **p < 0.01, ***p < 0.001. Error bars represent SEM.

Table 5.

Statistical analyses for Figure 3

To examine the impact of ELS on VTABLA-driven BLA→mPFC coordinated activity, we computed the PLV across a series of photoexcitation frequencies (Fig. 4A–D). As expected, photoactivation of VTABLA terminals promotes BLA activity to lead the activity in the mPFC (Fig. 4B,D; Table 5). Further, our results reveal an attenuation in the VTA-mediated coherence between BLA and mPFC following ELS (Fig. 4E). Specifically, VTABLA activation significantly enhances BLA→mPFC coherence in all frequencies >5 Hz, regardless of developmental stress. However, 40 Hz stimulation-induced phase coherence in the ELS group is significantly reduced relative to controls (Fig. 4E, Table 6)—a frequency previously shown to modulate sociability (i.e., interaction and avoidance behaviors) in rodents (Huang et al., 2020; Ferrara et al., 2023). The PLV calculation incorporates zero-phase differences that could arise from spurious synchrony such as volume conduction (Bruña et al., 2018). We therefore also computed the imaginary phase locking value (iPLV) that isolates noninstantaneous phase differences (Bruña et al., 2018). We find that VTABLA-driven BLA→mPFC was significantly coordinated in CNT and ELS mice at 20 and 40 Hz (Fig. 4F, Table 6). Additionally, 40 Hz stimulation-induced phase coherence in ELS group was lower than CNT with a p = 0.051 (Fig. 4F, Table 6) in agreement with the PLV findings indicating that ELS reduces that VTABLA-driven BLA→mPFC coordination.

Figure 4.

ELS minimizes VTABLA→mPFC functional network connectivity. A, Representative LFP traces from BLA and mPFC before (top) and during (bottom) 40 Hz VTABLA photoexcitation for a CNT mouse. B, Top, Representative summary bar plots for animal in A detailing VTA-evoked BLA→mPFC coherence at each stimulation frequency. Bottom, Phase histogram for baseline (gray) and 40 Hz stimulation (red) in A. C, D, Same analyses seen in A and B for a representative ELS mouse. Summary of LFP coherence (PLV, E; and iPLV, F) ratio between pulsed stimulation and baseline periods where BLA→mPFC coherence is measured at each stimulation frequency for CNT (blue, n = 7) and ELS (red, n = 8) conditions. Dashed horizontal line indicates baseline response. Asterisks within bars indicate significant change from baseline. Asterisks atop horizontal bars indicate difference between CNT and ELS. #p ∼ 0.05, *p < 0.05, **p < 0.01, ***p < 0.001. Error bars represent SEM.

Table 6.

Statistical analyses for Figure 4

Building on the observed reduction in VTABLA-mediated coherence between the BLA and mPFC following ELS, we hypothesized that ELS disrupts DA release from VTABLA projections, impairing DA-dependent modulation of network activity. To directly test this, we measured BLA DA responses by virally expressing a DA fluorescent sensor, GRABDA2M (Beier et al., 2015), in the BLA of animals outfitted for microendoscopic imaging (Inscopix; Fig. 5A). Our initial inquiry evaluated the impact of ELS on the magnitude of DA response in the BLA following 40 Hz VTABLA activation, via photoexciting VTA ChrR expressing terminals in the BLA. We revealed that the VTABLA-evoked DA response in CNT + ChrR animals were reliably greater than baseline fluorescence, reaching significance within 1 s of VTABLA terminal activation (Fig. 5B,C; Table 7). However, ELS robustly decreased this response, quantitatively resembling CNT + eGFP animals (Fig. 5B–D, Table 7). Collectively, these data demonstrate that ELS reduces VTABLA DA signaling.

Figure 5.

ELS reduces ELS reduces VTABLA DA response. A, Schematic of sagittal and coronal views show AAV9-Syn-ChrRimsonR-tDT or AAV9-hSyn-eGFP was injected into VTA, AAV9-hSyn-GRABDA2m injected into BLA, with GRIN lens implanted above BLA. B, Representative traces show dopamine (DA) response across a recording window consisting of 15–5 s trials of 20 mW red (620 ± 30 nm) 40 Hz photoexcitation indicated by horizontal black bars; eGFP, gray; CNT, blue; ELS, red. C, Grouped bar plot shows trial-averaged normalized DA response for each second of 5 sec stimulation for eGFP (n = 4), CNT (n = 4), and ELS (n = 5) animals. Dashed horizontal line indicates baseline response. D, Summary plot shows session-averaged normalized DA response for YFP, CNT, and ELS animals. *p < 0.05. Error bars represent SEM.

Table 7.

Statistical analyses for Figure 5

Noting the impact of ELS on VTABLA DA signaling, we focused our attention on interrogating the impact of ELS on innate motivated behaviors, such as social interaction. We assessed the impact of ELS on social preference using a 3CST which evaluated an animal's proclivity to investigate either an inanimate object (fake mouse toy) or novel, female conspecific (female) with or without rhythmic VTABLA activation (Fig. 6A–D). Then, 40 Hz stimulation was chosen for terminal activation because BLA gamma (30–80 Hz) is known to be crucial for emotional/social processing (Stujenske et al., 2014; Felix-Ortiz et al., 2016), and it is the frequency band where rearing conditions caused a significant difference in BLA→mPFC functional connectivity (Fig. 4E,F). CNT and ELS animals showed comparable interaction levels when presented with toys, with no effect of VTABLA photoexcitation (On) on interaction preference in comparison with trials in the absence of photoexcitation (Off; Figs. 6E, left; Table 8). Further scrutiny regarding whether ELS impacted the capability of mice to interact, specifically looking at locomotor activity in terms of time spent within each 3CST chamber, revealed that ELS animals had similar locomotor behavior as CNT animals (Fig. 6F, Table 8). Conversely, when presented with the decision to interact with a toy or a female in the absence of VTABLA activation, animals robustly preferred to socialize (Fig. 6E, right; Table 8). However, in trials where VTABLA activation occurred, ELS animals changed their preference, erring on the side of social avoidance, a behavior that was not exhibited in CNT animals with intact VTABLA DA signaling (Fig. 6G, Table 8). These data suggest that the changes in VTABLA DA signaling impair social interaction.