Task-evoked activity quenches neural correlations and variability across cortical areas

Abstract

Many large-scale functional connectivity studies have emphasized the importance of communication through increased inter-region correlations during task states. In contrast, local circuit studies have demonstrated that task states primarily reduce correlations among pairs of neurons, likely enhancing their information coding by suppressing shared spontaneous activity. Here we sought to adjudicate between these conflicting perspectives, assessing whether co-active brain regions during task states tend to increase or decrease their correlations. We found that variability and correlations primarily decrease across a variety of cortical regions in two highly distinct data sets: non-human primate spiking data and human functional magnetic resonance imaging data. Moreover, this observed variability and correlation reduction was accompanied by an overall increase in dimensionality (reflecting less information redundancy) during task states, suggesting that decreased correlations increased information coding capacity. We further found in both spiking and neural mass computational models that task-evoked activity increased the stability around a stable attractor, globally quenching neural variability and correlations. Together, our results provide an integrative mechanistic account that encompasses measures of large-scale neural activity, variability, and correlations during resting and task states.

Fig 1. Testing the hypothesis that task-evoked neural variability and correlations are quenched across cortical areas in NHP spiking and human fMRI data sets.

We used two highly distinct data sets to test the hypothesis that task-evoked activity globally quenches neural variability and correlations to suppress background spontaneous activity/noise. This contrasts with the alternate hypothesis, namely that task-evoked activity increases variability and correlation to facilitate inter-region communication. Importantly, the two data sets were analyzed in a statistically consistent manner, including the removal of the mean task-evoked response to isolate neural-to-neural interactions. a,b) Using mean-field spike rate data collected simultaneously from six different cortical areas [29], we compared the spiking variability and spike count correlations between task-state (i.e., following task cue onset) and rest-state spiking activity. We defined rest state as the inter-trial interval (ITI) directly preceding the trial. This was performed by estimating the mean-field spike rate by averaging across multi-units in each cortical area, allowing us to target the activity of large neural populations. c,d) Using human fMRI data obtained from the Human Connectome Project [30], we compared the neural variability and correlations (i.e., FC) of the BOLD signal during task block intervals to equivalent resting-state intervals. We used seven highly distinct cognitive tasks. Time series and task timings are illustrative, and do not reflect actual data.

Fig 2. Neural variability and correlations decrease during task states relative to rest in spiking data.

Results for the replication subject are reported in S1 Fig. a) We measured mean-field spike recordings from six different cortical areas during a motion-color categorization task. b) We calculated the average spike rate across all recordings during the rest period (ITI) and task period (task cue), across trials. Each data point reflects the firing rate across 25 consecutive trials. c) We calculated the cross-trial spiking variance for each region during task and rest states, and then averaged across all regions. Each data point reflects the spiking variance across 25 consecutive trials. d) We calculated the average cross-trial neural correlation for task and rest states between all pairs of recorded brain regions. (Spike rates were averaged within each cortical area.) Each data point reflects the correlation across 25 consecutive trials. e-g) For each pair of brain regions, we visualize the correlation matrices between each recording site for the averaged rest period, task period, and the differences between task versus rest state spike count correlations. h) We also observed no increases in covariance (non-normalized correlation) [–33]. For panels e-h, plots were thresholded and tested for multiple comparisons using an FDR-corrected p<0.05 threshold. Boxplots indicate the interquartile range of the distribution, dotted black line indicates the mean, grey line indicates the median, and the distribution is visualized using a swarm plot. Scatter plot visualizations of b-d can be found in S15 Fig.

Fig 3. Variability and correlations decrease during task states in human fMRI data.

Figures for the replication cohort are in S4 Fig. Figures for each task separately are shown in S8 and S9 Figs. a) We first compared the global variability during task and rest states, which is averaged across all brain regions, and then b) computed the task- versus rest-state variability for each brain region. c) Scatter plot depicting the variance of each parcel during task states (y-axis) and rest states (x-axis). Dotted grey line denotes no change between rest and task states. d) We next compared the correlation matrices for resting state blocks with (e) task state blocks, and (f) computed the task- versus rest-state correlation matrix difference. g) We found that the average FC between all pairs of brain regions is significantly reduced during task state. h) We found that the average correlation for each brain region, decreased for each brain region during task state. i) Scatter plot depicting the FC (correlation values) of each pair of parcels during task states (y-axis) and rest states (x-axis). Dotted grey line denotes no change between rest and task states. For panels b-f, and h, plots were tested for multiple comparisons using an FDR-corrected p<0.05 threshold. Boxplots indicate the interquartile range of the distribution, dotted black line indicates the mean, grey line indicates the median, and the distribution is visualized using a swarm plot.

Fig 4. Task variability/correlations decrease independently of mean task activity removal step in fMRI data.

Instead of computing variance/correlations across time points within task blocks (and removing mean task effects), variance/correlations can be calculated across task blocks (for each time point within a block). This approach isolates ongoing neural activity that is not task-locked, and has been used in both spiking and fMRI data [2,4]. a) To isolate ongoing spontaneous activity that is not time-locked to the task, we estimated the variance at each time point across task blocks. The variance at each time point was calculated for each ROI and task condition separately, but then averaged across ROIs and task conditions. Note that to obtain an equivalent variance estimate during resting state, we applied an identical block structure to rest data to accurately compare rest to task state variability. Variability across block time points was averaged across brain regions and task conditions. Error bars denote standard deviation across subjects. b) Variance across task block time points was significantly reduced during task blocks relative to identical control blocks during resting-state data. c) We performed a similar procedure for task functional connectivity estimates, correlating across blocks for all pairs of brain regions. Correlations across block time points were averaged for all pairs of brain regions and task conditions. d) Correlations during task state blocks were significantly reduced relative to identical control blocks during resting state. Boxplots indicate the interquartile range of the distribution, dotted black line indicates the mean, grey line indicates the median, and the distribution is visualized using a swarm plot.

Fig 5. Dimensionality increases during task periods relative to resting-state activity.

a) For each subject, we calculated the dimensionality using the participation ratio [37,39] during task and rest states and found that during task states, dimensionality significantly increased. b) We calculated the dimensionality of spiking activity across trials and found that during task states, dimensionality significantly increased. These findings provide a potential information-theoretic interpretation of neural correlation and variability reduction during task states. Boxplots indicate the interquartile range of the distribution, dotted black line indicates the mean, grey line indicates the median, and the distribution is visualized using a swarm plot.

Fig 6. Inferring the mean-field transfer function of a neural population with a balanced spiking model with clustered excitatory connectivity.

a) Schematic illustration of the balanced spiking model with clustered excitatory connections. Network architecture and parameters are identical to those reported in [7]. Red triangles indicate excitatory cells, blue circles indicate inhibitory cells. b) The population spike rate (excitatory cells only) subject to inhibitory regulation. We systematically stimulated a subset of the neural population and measured the corresponding mean excitatory spike rate. Spike rates were normalized between 0 and 1. Excitatory stimulation was implemented by stimulating 400 excitatory neurons, and inhibitory stimulation was implemented by stimulating 400 inhibitory neurons. Spiking statistics were calculated across 30 trials, with each point in the scatter plot indicating a different 50ms time bin. c) Population neural variability (excitatory cells only), as a function of input stimulation. d) Based on panel b, we approximated the mean field neural transfer function as a sigmoid. A sigmoid transfer function produces optimal input-output dynamics for a narrow range of inputs (gray). The same input distribution mean shifted by some excitatory/inhibitory stimulation produces a quenched dynamic range.

Fig 7. Task-evoked activity induces changes in neural variability and the underlying attractor dynamics.

Our minimal modeling approach directly links descriptive statistics (e.g., time series variability) with rigorous dynamical systems analysis (e.g., attractor dynamics). a) During different evoked states (i.e., fixed inputs), there is a reduction in the observed time series variability (measured by variance across time). This is directly related to how input-output responses change due to the changing slope in the sigmoid transfer function. b) We visualized the phase space for each of the neural populations according to state by plotting the derivative of X₁ denoted by ${\dot{X}}_1$. For each state, we estimated the fixed point attractor (plotted as a star), denoting the level of mean activity the system is drawn to given some fixed input (or absence thereof). Arrows denote the direction/vector toward each fixed point, which specify the characteristic time scale (i.e., the speed) the system approaches the fixed point. c) We ran simulations across a range of stimulation amplitudes, calculating the variance across time at each amplitude. d) We characterized the shifting attractor dynamics for each stimulus by computing the characteristic time scale at the fixed point for each stimulation amplitude. The characteristic time scale across all fixed points are nearly perfectly correlated with the neural variability of the simulated time series across all fixed inputs (rank correlation = 0.9996).

Fig 8. Task-evoked activity quenches neural correlations by altering the underlying attractor dynamics.

We used a two unit network model, the minimal model necessary to study dynamic changes in neural correlations. a) At baseline, we observed slow, high amplitude fluctuations and high neural correlations. b) To characterize the underlying attractor dynamics, we visualized the two-dimensional state space, visualizing the flow field and the nullclines (blue and red curves, where the rate of change is 0) for each unit. The intersection of the two nullclines denote the fixed point attractor. We overlaid the simulated scatter plot (cyan dots) to illustrate the correspondence between the attractor dynamics and simulation. c) We injected a fixed input stimulation, shifting the network to an ‘evoked’ state, which caused a decrease in neural variability and correlation. d) The external input transiently moved the fixed point, altering the attractor dynamics and the corresponding scatter plot. e) We systematically injected a range of fixed inputs into the network. We found that neural correlations were optimal with no external stimulation, and decreased with any external stimulation. f) Across stimulation strengths, we found that the generalized characteristic time scale (see Methods) near the fixed point explained 98% of the neural correlation variance, providing a direct association between the network’s attractor dynamics and observed neural correlations.