Opponent regulation of action performance and timing by striatonigral and striatopallidal pathways

Abstract

The basal ganglia have been implicated in action selection and timing, but the relative contributions of the striatonigral (direct) and striatopallidal (indirect) pathways to these functions remain unclear. We investigated the effects of optogenetic stimulation of D1+ (direct) and A2A+ (indirect) neurons in the ventrolateral striatum in head-fixed mice on a fixed time reinforcement schedule. Direct pathway stimulation initiates licking, whereas indirect pathway stimulation suppresses licking and results in rebound licking after stimulation. Moreover, direct and indirect pathways also play distinct roles in timing. Direct pathway stimulation produced a resetting of the internal timing process, whereas indirect pathway stimulation transiently paused timing, and proportionally delayed the next bout of licking. Our results provide evidence for the continuous and opposing contributions of the direct and indirect pathways in the production and timing of reward-guided behavior.

Keywords: basal ganglia; licking; mouse; neuroscience; reward; striatonigral pathway; striatopallidal pathway; timing.

Figure 1.. Stimulation of the direct and indirect pathways of the orofacial striatum during a licking-based interval timing task.

(A) Left: Strategy of injection of AAV-ChR2 virus to orofacial area of the striatum in D1-Cre or A2A-Cre mice and implantation of chronic optical fibers over the injection site. (B) Serial section diagrams showing target zone for orofacial striatum. (C) Representative image of eYFP-expression in ventrolateral striatum in a D1-Cre+ mouse injected with AAV-DIO-ChR2-eYFP. Scale bar = 500 µm. (D) Representative image of eYFP-expression in an A2A-Cre+ mouse injected with AAV-DIO-ChR2-eYFP virus. Scale bars = 500 µm. (Abbreviations: ic, internal capsule; CP, caudoputamen; GPe, globus pallidus, external segment.) (E) Diagram illustrating the fixed-time interval task for head-fixed mice. Mice receive a 10% sucrose reward (5 µL) every 10 s. (F) Example lick raster of a well-trained mouse during normal trials aligned to reward delivery. Tick marks represent individual licks. (G) Mean licking rate calculated from the raster in E. Error bars show SEM.

Figure 2.. Stimulation of direct pathway in VLS generates licking.

(A) Depiction of stimulation strategy 5 s prior to reward in D1-cre mice. (B) Top: Peri-event lick raster diagrams of representative trials demonstrating normal anticipatory licking patterns in trials without laser. Bottom: 10 Hz stimulation at 5 s prior to reward results in large increases in licking activity. Both rasters reflect licking from the same mouse in the same session. (C) Mean lick rate calculated from the example session shown in B for trials with and without laser stimulation. (D) Mean increases in licking rate during laser delivery resulting from stimulation of D1 MSNs relative to control at 5 s increased as a function of stimulation frequency (n = 8 D1-ChR2 mice, n = 5 control mice; two-way ANOVA; main effect of experimental group, F_1,44 = 93.6, p<0.0001; main effect of frequency, F_3,44 = 4.64, p<0.01; interaction between frequency and group, F_3,44 = 4.84, p<0.01). (E) Depiction of stimulation strategy 1 s prior to reward. (F) Top: Peri-event lick raster diagrams of representative non-laser trials. Bottom: Raster diagram of trials containing 10 Hz stimulation during anticipatory licking. Both rasters reflect licking from the same mouse in the same session. (G) Mean lick rate calculated from the example session shown in F for trials with and without laser stimulation. (H) Stimulation of D1 MSNs at 1 s prior to reward increased the rate of anticipatory licking (two-way ANOVA, main effect of group, F_1,37 = 48.82, p<0.0001). (I) Depiction of stimulation strategy coinciding with reward delivery. (J) Top: Representative lick raster diagrams of licking behavior during trials without laser stimulation. Bottom: Raster diagram of trials from the same animal containing 10 Hz stimulation during consumption licking. Both rasters reflect behavior recorded in the same session. (K) Mean licking rate calculated from the example session shown in J for trials with and without stimulation. (L) Stimulation of D1 MSNs was capable of increasing consumption licking rate (two-way ANOVA, main effect of group, F_1,36 = 8.65, p<0.01). (M) The time of stimulation during the interval influenced the change in licking rate (two-way ANOVA, main effect of time of stimulation, F_3,67 = 9.16, p<0.0001; main effect of frequency, F_2,67 = 24.31, p<0.0001). Error bars show SEM. X symbol reflects a significant interaction between factors.

Figure 3.. Direct pathway boosts licking frequency and modulates licking duty cycle.

(A) Left: Example lick rasters from two mice showing licking frequency potentiation by direct pathway stimulation 1 second before reward. Note increase of licking to upwards of 10 Hz. Blue tick-marks denote laser pulse times. Right: Example lick raster from the same sessions showing normal licking activity around reward. (B) Spectral density analyses of licking during laser stimulation and during anticipation (1 second intervals beginning prior to reward) without stimulation. Analysis of data from the sessions represented in A is shown. (C) Power spectral density (PSD) distributions of licking during stimulation at increasing laser frequencies. Note consistent increase in power. (D) Effect of stimulation frequency on occupancy of licking at 3 distinct frequency bands (4-6, 6-8, 8-10 Hz) when stimulation occurred 1 second prior to reward. Peak licking power was related to stimulation frequency (n = 8 mice; two-way mixed ANOVA; interaction band vs stimulation frequency, F_8,58 = 2.54, p < 0.05; main effects of frequency band, F_2,58 = 15.46, p < 0.0001 and stimulation frequency, F_4,58 = 3.89, p < 0.05). Frequency bands contain non-overlapping ranges, e.g., 4-5.99, 6-7.99, and 8-10. (E) Effect of stimulation frequency on occupancy of licking in 3 frequency bands when stimulation occurred 5 seconds before reward. Licking increasingly occupied the 8-10 Hz band with increasing stimulation (two-way mixed ANOVA; interaction band vs frequency, F8_,60 = 6.43, p < 0.0001; main effects of frequency band, F_2,60 = 37.76, p < 0.0001 and stimulation frequency, F_4,60 = 2.84, p < 0.05). (F) Effect of stimulation frequency on occupancy of licking in 3 frequency bands when stimulation coincided with reward. Licking increasingly occupied the 8-10 Hz band with increasing stimulation (two-way mixed ANOVA; interaction band vs frequency, F_8,56 = 2.59, p < 0.05; main effects of frequency band, F_2,56 = 54.02, p < 0.0001 and stimulation frequency, F_4,56 = 3.3, p < 0.05). Stimulation frequency of 0 indicates no stimulation. Error bars show SEM. X symbol indicates a significant interaction between factors.

Figure 4.. Direct pathway modulates onset latency and duration of evoked licking bout.

(A) Top: The effect of stimulation frequency on evoked licking was measured for sessions with stimulation occurring at 5 s prior to reward. Bottom: Example raster plot showing longer latency to lick and shorter bout duration during 5 Hz direct pathway stimulation. B) Stimulation of the direct pathway at 25 Hz resulted in rapid licking onset and sustained licking following offset of laser stimulation. (C) Latency to lick bout onset as a function of the frequency of direct pathway stimulation (n = 8; one-way ANOVA; F_3,22 = 4.92, p<0.01). (D) Number of licks that were counted during the 1 s following direct pathway stimulation offset. Blue points reflect counts during trials with laser stimulation at 5 s before reward. Black points reflect the baseline count number observed during trials without stimulation for the same time period of the interval (two-way mixed ANOVA; main effect of stimulation: F_1,23 = 18.1, p<0.001; interaction stimulation vs. frequency, F_3,23 = 1.91, p=0.15). Error bars show SEM.

Figure 5.. Stimulation of the indirect pathway in the orofacial striatum suppresses licking.

(A) Depiction of stimulation strategy 5 s prior to reward in A2A-cre mice. (B) Top: Peri-event lick raster diagrams of representative trials demonstrating normal anticipatory licking patterns in trials without laser. Bottom:10 Hz stimulation at 5 s prior to reward results in a pause in licking. Both rasters reflect licking from the same mouse in the same session. (C) Mean lick rate calculated from the example session shown in B for trials with and without laser stimulation. (D) Mean reduction of licking rate during stimulation of the indirect pathway at 5 s (n = 8 A2A-ChR2 mice, n = 5 control mice; two-way ANOVA; main effect of experimental group, F_1,40 = 12.35, p<0.01). (E) Depiction of stimulation strategy 1 s prior to reward. (F) Top: Peri-event lick raster diagrams of representative non-laser trials. Bottom: Raster diagram of trials containing 10 Hz stimulation of the indirection pathway during anticipatory licking. Both rasters show licking from the same mouse in the same session. (G) Mean lick rate calculated from the example session shown in F for trials with and without laser stimulation. (H) Increasing stimulation frequency of the indirect pathway at 1 s prior to reward reduced the rate of anticipatory licking in A2A-Cre mice (two-way ANOVA; main effect of group, F_1,42 = 35.48, p<0.0001; main effect of frequency, F_3,42 = 8.88, p<0.0001; interaction group vs frequency, F_3,42 = 6.31, p<0.01). (I) Depiction of stimulation strategy coinciding with reward delivery. (J) Top: Representative lick raster diagrams of licking behavior during trials without laser stimulation. Bottom: Raster diagram of trials from the same mouse containing 10 Hz stimulation during consumption licking. Both rasters reflect behavior recorded in the same session. (K) Mean licking rate calculated from the example session shown in J for trials with and without stimulation. (L) Indirect pathway stimulation at the time of reward reduced licking rate (two-way ANOVA; main effect of group, F_1,42 = 6.48, p<0.05; main effect of frequency, F_3,42 = 4.01, p<0.05; interaction group vs frequency, F_3,42 = 3.38, p<0.05). (M) The time of stimulation during the interval influenced reductions in licking rate by stimulation (two-way ANOVA, main effect of time of stimulation, F_3,76 = 21.38, p<0.0001; main effect of Frequency, F_2,76 = 3.19, p<0.05). Error bars show SEM. X symbol reflects a significant interaction between factors.

Figure 6.. Rebound licking following stimulation of the indirect pathway.

(A) Top: Schematic showing stimulation of A2A-Cre mice 5 s prior to reward. Middle: Example raster plot showing the resulting rebound licking following the termination of stimulation of the indirect pathway. Orange markers indicate the onset time of discrete lick bouts. Bottom: Raster plot of licking during no-stimulation trials from the same mouse, aligned to the same time point in the interval as above. Note the predominant alignment of lick onset times following laser stimulation. (B) Top: Example of another mouse showing rebound licking after indirect pathway stimulation. Bottom: Raster plot of licking during non-stimulation trials from the same mouse in the same session. C) Comparison of licking rate during stimulation and non-stimulation trials. Indirect pathway stimulation resulted in an increase in licking rate following laser termination when compared to the same time period in non-stimulation trials (n = 8 mice; two-way mixed ANOVA, effect of stimulation F_1,24 = 11.08, p<0.01). (D) Reduction of lick onset latency following stimulation termination compared to mean latency for the same time period in non-stimulation trials (two-way mixed ANOVA, main effect of stimulation: F_1,24 = 16.41, p<0.001; interaction stimulation vs trial type, F_3,24 = 5.73, p<0.01). (E) Reduction of lick onset latency variance following stimulation offset compared to the variance of licking initiation for the same time period in non-stimulation trials (two-way mixed ANOVA, main effect of frequency, F_3,24 = 6.12, p<0.01; interaction frequency vs. trial type, F_3,24 = 8.63, p<0.001). Error bars show SEM. X symbol reflects a significant interaction between factors.

Figure 7.. The effect of motivation on licking affected by direct and indirect pathway stimulation.

(A) The effect of motivation on licking related to direct and indirect pathway manipulation was measured for sessions with stimulation occurring at 5 s prior to reward. (B) Example raster plot showing progressive reduction of licking evoked by 10 Hz direct pathway stimulation at 5 s before reward. Trial numbers reflect the number of laser presentations delivered with the number of rewards the animal received in parentheses. (C) Example raster plot showing a reduced influence of motivation on evoked licking with higher frequency stimulation of the direct pathway. Data are from the same mouse but a different session as shown in B. Trial numbers reflect the number of laser presentations delivered with the number of rewards the animal received in parentheses. (D) Grouped bar plot showing the reduced impact of laser stimulation at 5 s before reward on evoked licking as a function of trial quartile (n = 8; two-way mixed ANOVA; effect of quartile, F_3,72 = 3.64, p<0.05; effect of frequency, F_3,72 = 9.5, p<0.001; interaction quartile vs frequency, F_9,72 = 2.62, p<0.05). (E) Grouped bar plot showing an increase of lick onset latency as a result of direct pathway stimulation as a function of trial quartile (two-way mixed ANOVA, effect of quartile, F_3,60 = 3.25, p<0.05; effect of frequency, F_3,60 = 5.67, p<0.01; interaction quartile vs frequency, F_9,60 = 0.38, p=0.93). (F) Example raster plot showing the increase in rebound latency following 50 Hz stimulation of the indirect pathway over the course of the experimental session. Trial numbers reflect the number of laser presentations delivered with the number of rewards the animal received in parentheses. (G) Grouped bar plot showing the increase of lick onset latency following laser stimulation offset as a function of trial quartile (n = 8, two-way mixed ANOVA, effect of quartile, F_3,72 = 4.04, p<0.05; effect of frequency, F_3,72 = 3.88, p<0.05; interaction quartile vs frequency, F_9,72 = 2.16, p<0.05). Error bars show SEM. X symbol reflects a significant interaction between factors.

Figure 8.. Peak probe trials reveal the operation of an internal timing mechanism.

(A) Top: Example raster plot of licking during consecutive 10 s fixed-time trials. Licking is aligned to the first of two consecutive reward delivery times. Bottom: Mean licking rate for the session shown in the above raster. (B) Top: Example raster plot showing licking during peak probe trials. During peak trials, reward is delivered then withheld 10 s later, resulting in a discrete bout of licking in the absence of any stimuli. Bottom: The average licking rate for the session shown in the above raster. Averaging across probe trials results in a characteristic peak in licking. Data shown for both trial types were recorded from the same mouse and session. Error bars show SEM.

Figure 9.. Direct pathway stimulation resets the internal clock.

(A) Left: Mean licking rate across subjects during peak probe trials with and without laser stimulation concurrent with reward delivery. Scale bars reflect the population mean peak times for probe trails with (blue) and without (green) laser stimulation. Middle: Mean licking rate across subjects during probe trials delivered in the presence and absence of laser stimulation at 3 s post reward. Scale bars reflect the population mean peak times for probe trails with (blue) and without (green) laser stimulation. Right: Mean licking rate across subjects during normal probe trials and peak probe trials containing laser stimulation at 5 s following reward. Scale bars reflect the population mean peak times for probe trails with (blue) and without (green) laser stimulation. (B) Magnitudes of peak shifts in seconds as a function of time of direct pathway stimulation. The y-axis reflects the difference between the mean peak time occurring during laser trials subtracted by the mean peak time during trials without stimulation (n = 4 female mice; One-way RM ANOVA; F_3,9 = 21.68, p<0.001). Peak analyses were performed on the entire behavioral session to maximize statistical power. Points reflect individual data points. (C) Quantification of the peak duration during normal peak probe trials and those with laser stimulation. Stimulation resulted in a reduction of the peak width (n = 4; two-way mixed ANOVA; effect of stimulation, F_1,12 = 35.49, p<0.0001). D) There were no changes in the skewness of the peak distributions. Error bars show SEM.

Figure 10.. Indirect pathway stimulation pauses the internal clock.

(A) Top: Peri-event lick raster of representative peak probe trials without laser delivery. Middle: 25 Hz stimulation at 5 s following reward during trials in which rebound licking causes a delay and a recovery in peak licking. Both rasters reflect licking from the same mouse in the same session. Bottom: Mean lick rate calculated from the example session shown above for peak probe trials without laser stimulation and stimulation trials showing a ‘recovery’ pattern. (B) Top: Peri-event lick raster diagrams of representative peak probe trials without laser delivery. Middle: 25 Hz stimulation at 5 s following reward during trials in which rebound licking initiates peak licking. Both rasters show licking from the same mouse in the same session. Bottom: Mean lick rate calculated from the example session shown above for peak probe trials without laser stimulation and stimulation trials showing an ‘initiation’ pattern. (C) Top: Peri-event lick raster of a third subject’s representative peak probe trials produced in the absence of laser delivery. Middle: 25 Hz stimulation at 5 s following reward during trials in which no rebound licking was detected. Bottom: Mean lick rate calculated from the example session shown above for peak probe trials without laser stimulation and stimulation trials showing a ‘no rebound’ pattern. (D) The three types of patterns occurred with equal probability throughout the behavioral session (n = 5 (3 female and two male); one-way RM ANOVA, F_2,8 = 0.64, p=0.5). (E) Peak shifts were measured by subtracting the mean peak time of each pattern by the mean peak time without stimulation. Recovery and no rebound trials showed significant positive peak shifts (two-tailed t-tests, p<0.05), whereas initiation trials trended toward negative peak shifts (two-tailed t-test, t₄ = 2, p=0.1). (F) Initiation trials showed significant increases in the duration of the peak (two-tailed t-test, t₄ = 4.18, p<0.05). (G) There were no changes in skewness of licking distributions for any trial type. (H) Fraction of peak trials showing each pattern during the first and second halves of the behavioral session. On the whole, the recovery pattern was gradually replaced with no rebound pattern (two-way, mixed ANOVA, interaction trial type x session half, F_1,12 = 7.38, p<0.01). Error bars show SEM. X symbol reflects a significant interaction between factors. Points in bar graphs reflect individual data points.

Figure 11.. Direct pathway modulates licking CPG activity via integration.

(A) Left: Laser-evoked licking frequency corresponding to the peak of the power spectral density distribution as a function of direct pathway laser stimulation frequency. Data for stimulation frequencies 5–25 Hz are shown. Right: Hypothetical expected linear laser-evoked licking frequencies if direct pathway stimulation directly drove each lick. Note that in this scenario, 5 Hz stimulation would result in licking at 5 Hz and 25 Hz stimulation would result in licking at 25 Hz. (B) Proposed mechanism translating direct pathway stimulation to SNr output activity via integration. Higher frequency direct pathway stimulation results in faster filling of the integrator that leads to a faster rate of change as well as longer-lasting output. (C) Increasing SNr output brings lower-level licking centers above several different activity thresholds, corresponding to varying discrete licking frequencies. 5 Hz stimulation does not result in 5 Hz licking. CPG output is capped at 10 Hz. (D) Greater filling of the integrator results in a more sustained licking output at a given frequency level. This is reflected in the increasing power in a given frequency band with increasing frequency of stimulation, suggesting a role for the modulation of licking duty cycle by the BG.

Author response image 1.

Author response image 2.