Research

Dr. Chenglin Miao published a paper in Advanced Science.

Hippocampal place codes change substantially across days, yet the mechanisms governing their temporal evolution remain incompletely understood. To quantitatively characterize this process, longitudinal one-photon calcium imaging of dorsal CA1 neurons in mice is performed for up to 56 days across multiple goal-oriented navigation tasks. Parallel to mice's improvements in maze learning and navigational performance, thousands of place fields exhibit complex evolutionary trajectories characterized by formation, disappearance, and retention. Leveraging statistical analyses and sequential learning models (e.g., recurrent neural networks and hidden Markov models), a position-, decision-making-, and novelty-irrelevant Single-Field Evolution Rule (SFER) is identified: active states of a place field increase its probability of remaining active in the subsequent session, whereas inactive states reduce it. Simulations of a stochastic discrete dynamical system defined by SFER reveal that the novelty-related stabilization of dCA1 place codes at the population level emerges as a collective outcome of the novelty-irrelevant SFER. Among the ten tested models, SFER-based models provide the best predictions of field evolutions, and an extended version incorporating inter-field interactions and day-to-day fluctuations effectively captured coordinated multi-field evolution. This framework offers a novel, efficient, and parsimonious approach that demonstrates the derivational relationship between activity-dependent single-field evolution and population-level drift dynamics in the hippocampus.

Original link: https://advanced.onlinelibrary.wiley.com/doi/epdf/10.1002/advs.202509532