Sparse optical microstimulation in barrel cortex drives learned behaviour in freely moving mice

Abstract

Electrical microstimulation can establish causal links between the activity of groups of neurons and perceptual and cognitive functions. However, the number and identities of neurons microstimulated, as well as the number of action potentials evoked, are difficult to ascertain. To address these issues we introduced the light-gated algal channel channelrhodopsin-2 (ChR2) specifically into a small fraction of layer 2/3 neurons of the mouse primary somatosensory cortex. ChR2 photostimulation in vivo reliably generated stimulus-locked action potentials at frequencies up to 50 Hz. Here we show that naive mice readily learned to detect brief trains of action potentials (five light pulses, 1 ms, 20 Hz). After training, mice could detect a photostimulus firing a single action potential in approximately 300 neurons. Even fewer neurons (approximately 60) were required for longer stimuli (five action potentials, 250 ms). Our results show that perceptual decisions and learning can be driven by extremely brief epochs of cortical activity in a sparse subset of supragranular cortical pyramidal neurons.

Figure 1. ChR2-assisted photostimulation of layer 2/3 barrel cortex neurons in vivo

(a) Coronal section through the electroporated mouse somatosensory cortex after immunohistochemical staining for ChR2-GFP. (b) Individual layer 2/3 neuron, side view. (c) Maximum value projection (top view) of an image stack in vivo (see Supplementary Movie 1) showing layer 2/3 neurons expressing ChR2-GFP and cytosolic RFP. (d) Schematic of the recording geometry.. (e) Action potentials recorded from one ChR2-GFP-positive neuron. Blue bars indicate photostimuli (1 ms duration, 11.6 mW/mm², 20 Hz). (f) Same as e, 50 Hz. (g) Probability of spiking as a function of light intensity (1 ms duration, 5 repetitions per condition, 15 sec between stimuli) (I_max = 11.6 mW/mm²). Each line corresponds to a different neuron, each color to a different animal. Neurons that could only be driven with photostimuli longer than 1ms were pooled at the far right (above). (h) Cumulative fraction of recorded neurons firing at various threshold intensity levels (computed from the data in g).

Figure 2. Photostimulation in freely moving mice performing a detection task

(a) Schematic of the photostimulation setup (see Methods). (b) Schematic of the behavioral apparatus and reward contingencies. The mouse initiates a trial by sticking its snout into the central port. Photostimuli are applied during a stimulation period (300 ms) accompanied by a series of bright blue light flashes delivered to the behavioral arena (30Hz, 300ms) to mask possible scattered light from the portable light source. The mouse then decides to enter either the left or the right port for a water reward. If a photostimulus was present, the choice of the left port was rewarded with a drop of water (hit, green star) whereas the choice of the right port lead to a short timeout (4 sec, miss, red star). If the stimulus was absent only the choice of the right port was rewarded with reward (correct reject, green circle) whereas the left port lead to a timeout (4 sec, false alarm, red circle). (c) Data from one session (200 trials) with a single stimulus (1 ms) with decreasing light intensities. Each horizontal line delineates 20 trials at fixed light intensity. Blue dots indicate the presence or absence of a photostimulus. Stimulated and non-stimulated trials were presented pseudo-randomly with a probability of 0.5.

Figure 3. Behavioral detection of photostimulation

(a) Comparison of the performance ((hits + correct rejections)/total trials) in mice expressing ChR2-GFP (n = 9) and control mice (n = 6) after training with 5 photostimuli (P < 0.001, t-test). (b) Performance as a function of light intensity (in % of I_max = 11.6 mW/mm²) for 5 light pulses (1ms, 20Hz, blue lines), 2 light pulses (1ms, 20Hz, green lines) and a single light pulse (1ms, red lines). Dotted lines: mean across 5 session (200–1000 trials per session). Error bars: binomial standard error. The number of ChR2-GFP-positive neurons located under the window area is indicated for each mouse. (c) Location of ChR2 expressing neurons in serial reconstruction of the sectioned brain (coronal sections). The blue cone illustrates the light source over the window. Arrows indicate rostral (r) and dorsal (d) orientation. (d) Performance as a function of the number of activated neurons. Thick lines, mean performance across all 5 animals for 1 (red), 2 (green) and 5 (blue) light pulses. Dotted lines indicate mean values of individual animals from Fig. 3b.