Integration of Calcium Imaging Traces via Deep Generative Modeling

TL;DR

This paper introduces a supervised variational autoencoder framework for analyzing calcium imaging data, effectively capturing single-neuron activity, reducing batch effects, and outperforming existing models in visualization and clustering tasks.

Contribution

The study presents a novel deep generative modeling approach that learns single-neuron representations directly from calcium traces without spike inference, improving robustness and interpretability.

Findings

Outperforms state-of-the-art models in preserving biological variability.

Effectively mitigates batch effects in calcium imaging data.

Enables robust visualization and clustering of neuronal activity.

Abstract

Calcium imaging allows for the parallel measurement of large neuronal populations in a spatially resolved and minimally invasive manner, and has become a gold-standard for neuronal functionality. While deep generative models have been successfully applied to study the activity of neuronal ensembles, their potential for learning single-neuron representations from calcium imaging fluorescence traces remains largely unexplored, and batch effects remain an important hurdle. To address this, we explore supervised variational autoencoder architectures that learn compact representations of individual neurons from fluorescent traces without relying on spike inference algorithms. We find that this approach outperforms state-of-the-art models, preserving biological variability while mitigating batch effects. Across simulated and experimental datasets, this framework enables robust visualization, clustering, and interpretation of single-neuron dynamics.