Segmentation of spatial experience by hippocampal θ sequences

Abstract

The encoding and storage of experience by the hippocampus is essential for the formation of episodic memories and the transformation of individual experiences into semantic structures such as maps and schemas. The rodent hippocampus compresses ongoing experience into repeating theta sequences, but the factors determining the content of theta sequences are not understood. Here we first show that the spatial paths represented by theta sequences in rats extend farther in front of the rat during acceleration and higher running speeds and begin farther behind the rat during deceleration. Second, the length of the path is directly related to the length of the theta cycle and the number of gamma cycles in it. Finally, theta sequences represent the environment in segments or 'chunks'. These results imply that information encoded in theta sequences is subject to powerful modulation by behavior and task variables. Furthermore, these findings suggest a potential mechanism for the cognitive 'chunking' of experience.

Figure 1

Distinct populations of theta sequences on the two-choice T maze. (a) The two-choice T maze. The maze had two possible physical configurations, the second indicated by dashed lines. Noteworthy landmarks on the maze include the maze start (MS), turn 1 (T1), turn 2 (T2), top corner (TC), feeder 1 (F1), feeder 2 (F2) and bottom corner (BC). Arrows indicate the direction of maze traversal. (b) Overall and selected sequence count over the linearized maze. Overall sequence count over the maze (n = 618,408 sequences) is a reflection of the amount of time rats spent at each location on the maze. Selected sequence count (n = 33,397 sequences) indicates the number of sequences at each location on the maze that passed the inclusion criteria described in the main text. (c) Theta sequence histogram of rat velocity versus path length, defined as the distance (in centimeters) from the decoded start of the sequence of firing within the theta cycle to the decoded end of the sequence (see Online Methods). The color of each pixel indicates the number of theta sequences with a specified path length (x axis) recorded while a rat was running at a particular velocity (y axis). The horizontal dashed line separates low- from high-velocity theta sequences. (d) High-velocity sequence count (n = 29,351 sequences) over the linearized maze. The number of high-velocity sequences (sequences above horizontal line in c) at each location on the maze. (e) Low-velocity sequence count (n = 4,046 sequences) over the linearized maze. Occupancy is defined as time spent at each location on the maze.

Figure 2

Examples of ahead sequences while rats were located at the choice point. Top, the rat’s average velocity over the theta cycle. Each place field center represented by a spike in the sequence (colored point in corresponding bottom panel) is plotted on the two-dimensional maze at the location of its two-dimensional place field center. The arrow shows the rat’s location. Bottom left, spikes plotted by place field center location (space) relative to the rat’s position (along either a left or right loop of the maze) over a single theta cycle (see Online Methods). LFPs filtered between 6 Hz and 12 Hz (red), 40 Hz and 100 Hz (green) and unfiltered (gray) are plotted below. Colored points indicate spikes that contribute positively to the sequence score according to the sequence detection algorithm (for visualization purposes only). The color of the spike indicates its relative time within the sequence (light blue, early; light purple, late). For cells with multiple place fields, gray points are plotted at every place field center belonging to the cell (colored points occupy the place field center that contributes maximally to the score). Spikes that do not contribute positively to the sequence score are also plotted in gray. Bottom right, the Bayesian decoded spatial probability distributions computed over the theta cycle (see Online Methods). Red indicates high probability, blue low probability. These examples likely correspond to the previously reported ‘sweeps’.

Figure 3

Examples of ahead and behind sequences. Top, sequences representing paths more ahead of the rat while rats were at various locations on the maze. Middle, sequences representing paths that are behind and ahead of the rat. Bottom, paths more behind the rat. See Figure 2 caption for details.

Figure 4

Characteristics of theta sequence ahead and behind length. (a) Mean ahead length as a function of path length. (b) Mean behind length as a function of path length. (c) Mean behind length as a function of ahead length. Note the inverse relationship between ahead length and behind length. (d) Ahead and behind length changes as a function of theta cycle separation. The absolute value of the average change in both ahead and behind length increased from successive theta cycles (beginning with 1 on the x axis) to a separation of about seven theta cycles and then leveled off. This indicates that the spaces mapped by neural activity in adjacent theta cycles are more similar than the spaces mapped in nonadjacent cycles. (e) Adjacent sequences tend to have related ahead and behind lengths but also occasionally include lengths that are substantially different. Sequences that are more separated (twenty theta cycles shown) tend to have larger changes in ahead and behind length. The subtraction between these two distributions is shown in an inset. Also shown is the distribution of all differences, ignoring the theta cycle distance between the two cycles. Sequences separated by 20 cycles approach random chance, whereas sequences separated by only a single theta cycle are more likely to be similar to each other. These analyses included 29,351 theta cycles. Line width in a–d indicate s.e.m. Note that some y axes have non-zero origins.

Figure 5

Theta period and gamma cycles vary as functions of path length. (a–c) The thick black curves show mean theta period (a) or mean number of gamma cycles (b) (y axis) with increasing path length (x axis). The gray curves were generated by multiplying the average velocity versus path length relationship (Fig. 8b) by the theta period versus velocity relationship or gamma cycle versus velocity relationship (c). Thus, the gray curve is the expected relationship if the theta period (a) or the number of gamma cycles (b) were merely a function of the relationship between theta period and velocity and path length and velocity. (d) Mean spike count, cell count, rat distance traveled and gamma cycles as functions of theta period. This analysis included 29,351 theta sequences. Line width indicates s.e.m. for a–d. Note that some y axes have non-zero origins.

Figure 6

Ahead length, behind length and path distribution vary according to landmarks on the maze. (a) Ahead length as a function of location on maze. Peaks indicate locations at which the represented path extended farther ahead of the rat, on average. Troughs indicate locations where the represented path ended closer to the rat’s location. (b) Density of represented paths as a function of location on maze. Peaks indicate regions of the maze that were overrepresented by theta sequences. The y axis is the average z score (z score computed over each session). (c) Behind length as a function of location on maze. Peaks indicate locations at which the represented path began farther behind the rat, on average. Troughs indicate locations where the represented path began closer to the rat’s location. (d) Average ahead length minus average behind length. This plot demonstrates the alternating pattern of representations that are more ahead and more behind the rat, as a function of location on the maze. This analysis included 29,351 theta sequences. Line width indicates s.e.m. Controls in a–c include a curve produced by randomly reassigning theta sequences with different rat locations. This shuffling procedure was done one hundred times, and the average shuffled distribution is plotted alongside the real data. Note that some y axes have non-zero origins.

Figure 7

Segmented representation of space by theta sequences. (a) Average decoded spatial path during a theta sequence as a function of the rat’s location on the maze. Each column corresponds to the average decoded path when the rat was at a particular location on the maze. Thus, each column corresponds to the mean p(x|s), where x is the position along the maze and s is the spike sequence. The solid white line shows the weighted circular mean of each column. Dotted white line indicates the x = y line. (b) The chunking process can be seen in the pinches in spatial correlation between chunks (at landmark locations marked by intersections of white lines) found when we calculated the full joint probability by squaring the decoding matrix or by calculating the cross-spatial correlations of the decoding matrix (c). This analysis included 29,351 theta sequences.

Figure 8

Relationships between rat behavior and the represented path. (a) Relationship between acceleration and path, ahead and behind lengths. (b) Relationship between velocity and path, ahead and behind lengths. Dashed lines in a and b indicate the peak of the velocity versus length relationships. As seen in a, acceleration is relatively constant with increasing path length. However, acceleration and ahead length are positively correlated, and acceleration and behind length are negatively correlated for shorter sequences (left of dashed line). This relationship changes for longer sequences (right of dashed line). Similarly, in b, velocity is positively correlated with path, ahead and behind length for shorter sequences, but the relationship changes for longer sequences. This analysis included 29,351 theta sequences. Line width indicates s.e.m. Note that some y axes have non-zero origins.