Saved in:
Bibliographic Details
Main Authors: Ros, Berta, Olives-Verger, Mireia, Fuses, Caterina, Canals, Josep M, Soriano, Jordi, Abante, Jordi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.14615
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914068733886464
author Ros, Berta
Olives-Verger, Mireia
Fuses, Caterina
Canals, Josep M
Soriano, Jordi
Abante, Jordi
author_facet Ros, Berta
Olives-Verger, Mireia
Fuses, Caterina
Canals, Josep M
Soriano, Jordi
Abante, Jordi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_14615
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Integration of Calcium Imaging Traces via Deep Generative Modeling
Ros, Berta
Olives-Verger, Mireia
Fuses, Caterina
Canals, Josep M
Soriano, Jordi
Abante, Jordi
Neurons and Cognition
Machine Learning
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.
title Integration of Calcium Imaging Traces via Deep Generative Modeling
topic Neurons and Cognition
Machine Learning
url https://arxiv.org/abs/2501.14615