SynapsNet: Enhancing Neuronal Population Dynamics Modeling via Learning Functional Connectivity

TL;DR

SynapsNet is a biologically inspired deep learning framework that models neuronal population dynamics and functional connectivity, outperforming existing methods and providing interpretable insights into neuron interactions.

Contribution

We introduce SynapsNet, a novel deep learning approach that explicitly models functional connectivity and neuron interactions, improving prediction accuracy and interpretability.

Findings

SynapsNet outperforms existing models in predicting neuronal population activity.

It accurately learns functional connectivity that reveals neuron interactions.

Validated on mouse cortical datasets across multiple recording modalities.

Abstract

The availability of large-scale neuronal population datasets necessitates new methods to model population dynamics and extract interpretable, scientifically translatable insights. Existing deep learning methods often overlook the biological mechanisms underlying population activity and thus exhibit suboptimal performance with neuronal data and provide little to no interpretable information about neurons and their interactions. In response, we introduce SynapsNet, a novel deep-learning framework that effectively models population dynamics and functional interactions between neurons. Within this biologically realistic framework, each neuron, characterized by a latent embedding, sends and receives currents through directed connections. A shared decoder uses the input current, previous neuronal activity, neuron embedding, and behavioral data to predict the population activity in the next time step. Unlike common sequential models that treat population activity as a multichannel time series, SynapsNet applies its decoder to each neuron (channel) individually, with the learnable functional connectivity serving as the sole pathway for information flow between neurons. Our experiments, conducted on mouse cortical activity from publicly available datasets and recorded using the two most common population recording modalities (Ca imaging and Neuropixels) across three distinct tasks, demonstrate that SynapsNet consistently outperforms existing models in forecasting population activity. Additionally, our experiments on both real and synthetic data showed that SynapsNet accurately learns functional connectivity that reveals predictive interactions between neurons.