Motivational salience signal in the basal forebrain is coupled with faster and more precise decision speed

Abstract

The survival of animals depends critically on prioritizing responses to motivationally salient stimuli. While it is generally believed that motivational salience increases decision speed, the quantitative relationship between motivational salience and decision speed, measured by reaction time (RT), remains unclear. Here we show that the neural correlate of motivational salience in the basal forebrain (BF), defined independently of RT, is coupled with faster and also more precise decision speed. In rats performing a reward-biased simple RT task, motivational salience was encoded by BF bursting response that occurred before RT. We found that faster RTs were tightly coupled with stronger BF motivational salience signals. Furthermore, the fraction of RT variability reflecting the contribution of intrinsic noise in the decision-making process was actively suppressed in faster RT distributions with stronger BF motivational salience signals. Artificially augmenting the BF motivational salience signal via electrical stimulation led to faster and more precise RTs and supports a causal relationship. Together, these results not only describe for the first time, to our knowledge, the quantitative relationship between motivational salience and faster decision speed, they also reveal the quantitative coupling relationship between motivational salience and more precise RT. Our results further establish the existence of an early and previously unrecognized step in the decision-making process that determines both the RT speed and variability of the entire decision-making process and suggest that this novel decision step is dictated largely by the BF motivational salience signal. Finally, our study raises the hypothesis that the dysregulation of decision speed in conditions such as depression, schizophrenia, and cognitive aging may result from the functional impairment of the motivational salience signal encoded by the poorly understood noncholinergic BF neurons.

Figure 1. Reward-biased simple RT task.

(A) Schematic of the reward-biased simple RT task. Rats initiated each trial by nosepoking in a fixation port following a trial start light signal. Inside the fixation port, three trial types—S-Large, S-Small, and Catch—were presented with equal probability and respectively associated with a large, small, or no reward in the adjacent port. RT was defined as the time between sound onset and fixation port exit. (B) Scatter plot of the mean RT in S-Large versus S-Small trials. Each dot represents one session from one rat (n = 339, 16 rats). Inset shows the overall mean ± sem (paired t test). (C) RT modulation as a ratio of mean RT between S-Large versus S-Small trials in each session around the reversal learning transition. Seventeen individual transition sequences (gray lines) with at least five sessions both before and after reversal learning were plotted, with the overall mean ± sem in black. In the first three sessions after the reversal learning transition, RT was faster toward S-Small, which predicted the larger reward before reversal. The RT difference grew larger with more training, and did not reach asymptotic level after 10 sessions.

Figure 2. Phasic bursting response of BF neurons encodes motivational salience and precedes RT.

BF population PSTH to trial start light signal (A), sound onset (B), fixation port exit (C), and the first drop of water reward (D). The population PSTH (mean ± sem) for BF bursting neurons (red, n = 144) and all other BF neurons (blue, n = 165) recorded from six rats in 40 sessions. The yellow shaded area indicates the {50, 160} ms window used to calculate BF bursting amplitude. BF bursting neurons also showed bursting responses to trial start signal and reward. The bursting response to sound onset largely dissipated before RT.

Figure 3. BF bursting amplitude predicts RT modulation between S-Large and S-Small trials.

(A) Bursting responses of one representative BF neuron to S-Large and S-Small onset. Individual trials in raster plots were aligned to sound onset and sorted by RT (blue). (B) Population PSTH (mean ± sem) for BF bursting neurons (n = 144) showed stronger bursting to S-Large than to S-Small. The mean RTs for the corresponding trials were indicated in the inset (mean ± std, n = 40 sessions). (C) Scatter plot of the mean bursting amplitude for each BF bursting neuron in S-Large versus S-Small trials from one session. Each dot represents one BF bursting neuron (n = 144), with red dots representing neurons recorded during the first three sessions after reversal (n = 14). (D) Correlation between BF bursting amplitude modulation and mean RT modulation in one session, each calculated as a ratio between S-Large and S-Small trials. Results plotted separately for individual BF bursting neurons (gray), as well as for the entire bursting population per session during the first three reversal sessions (red) or afterwards (blue). Between S-Large and S-Small trials in a session, BF bursting strength was strongly correlated with the modulation of mean RT.

Figure 4. No modulation of BF bursting amplitude within a trial type.

(A and B) Population PSTHs (mean ± sem) and scatter plots of bursting amplitude for all BF bursting neurons in faster (blue) and slower (cyan) RTs within S-Large (A) and S-Small (B) trials. Convention as in Figure 3B–C. There was little modulation of BF bursting amplitude within a trial type. (C–D) Correlation between BF bursting amplitude modulation and mean RT modulation between faster and slower RTs within S-Large (C) and S-Small (D) trials. Convention as in Figure 3D.

Figure 5. RTs are organized as a family or recinormal distributions swiveling against a fix time point.

(A) A representative session shows that RTs in S-Large and S-Small trials were recinormally distributed and can be transformed into a straight line by plotting 1/RT versus its z-score. Each dot represents RT from one trial. The intersection point of the two RT distributions is indicated by the blue circle. (B) 2-D histogram of the intersection point across sessions shows that the two RT distributions typically intersected around 160 ms. (C) Schematic of the intersection point analysis. Transforming the two RT distributions into straight lines by plotting −1/RT versus its z-score predicts novel invariant relationships between the intersection point (x₀, y₀) and parameters (μ₁, σ₁) and (μ₂, σ₂). (D) The x-coordinate of the intersection point is expressed as (μ₂σ₁−μ₁σ₂)/(σ₂−σ₁). The numerator and denominator are plotted on the y- and x-axis, respectively, along with the linear fit. Each dot is derived from RT distributions in one session (n = 339, 16 rats). (E) The y-coordinate of the intersection point is expressed as (μ₂−μ₁)/( σ₂−σ₁). Convention as in (D). (F) These data support the model that RT distributions swivel against a fixed time point, and predict that this family of RT distributions can be generated by a single neural mechanism whose activation level sets the parameters of RT distributions.

Figure 6. Augmenting BF bursting strength via BF electrical stimulation leads to faster and more precise RTs.

(A) Schematic of the BF stimulation task. An identical 6 kHz tone was presented either paired with or without BF electrical stimulation delivered during the BF bursting window. Both trial types led to the same reward amount. (B) An example session shows that BF electrical stimulation led to a faster RT distribution compared to nonstimulated tone-alone trials. Convention as in Figure 5A. (C) Increasing BF stimulation current led to faster RTs (mean ± sem) in stimulated trials but no change of RT in nonstimulated trials (linear mixed model, n = 7 rats, 44 sessions). (D) Stronger stimulation current led to stronger RT modulation between stimulated and nonstimulated trials (linear mixed model). Data from individual animals plotted as gray lines, with the population mean ± sem in black. (E) BF stimulation also produced more precise RTs while largely preserving the coupling between μ and σ parameters of RT distributions as seen in Figure 5D. The blue line represents the linear regression, whereas the black dotted line represents the linear regression from Figure 5D for comparison. See Figure S9 for more details.