Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2022.01.11.475549

NNeurite: artificial neuronal networks for the unsupervised extraction of axonal and dendritic time-lapse signals

Chenouard, N.·Kouskoff, V.·Tsien, R. W.·Gambino, F.
View original source ↗Export metadata ↓

Abstract

Fluorescence microscopy of Ca2+ transients in small neurites of the behaving mouse provides an unprecedented view of the micrometer-scale mechanisms supporting neuronal communication and computation, and therefore opens the way to understanding their role in cognition. However, the exploitation of this growing and precious experimental data is impeded by the scarcity of methods dedicated to the analysis of images of neurites activity in vivo. We present NNeurite, a set of mathematical and computational techniques specialized for the analysis of time-lapse microscopy images of neurite activity in small behaving animals. Starting from noisy and unstable microscopy images containing an unknown number of small neurites, NNeurite simultaneously aligns images, denoises signals and extracts the location and the temporal activity of the sources of Ca2+ transients. At the core of NNeurite is a novel artificial neuronal network (NN) which we have specifically designed to solve the non-negative matrix factorization (NMF) problem modeling source separation in fluorescence microscopy images. For the first time, we have embedded non-rigid image alignment in the NMF optimization procedure, hence allowing to stabilize images based on the transient and weak neurite signals. NNeurite processing is free of any human intervention as NN training is unsupervised and the unknown number of Ca2+ sources is automatically obtained by the NN-based computation of a low-dimensional representation of time-lapse images. Importantly, the spatial shapes of the sources of Ca2+ fluorescence are not constrained in NNeurite, which allowed to automatically extract the micrometer-scale details of dendritic and axonal branches, such dendritic spines and synaptic boutons, in the cortex of behaving mice. We provide NNeurite as a free and open-source library to support the efforts of the community in advancing in vivo microscopy of neurite activity.

Explore related subjects

neurosciencePreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Chenouard, N., Kouskoff, V., Tsien, R. W., Gambino, F.. 2022-01-12. NNeurite: artificial neuronal networks for the unsupervised extraction of axonal and dendritic time-lapse signals. https://doi.org/10.1101/2022.01.11.475549

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

The Unreasonable Effectiveness of Cell Types in Describing Neuronal Physiological Features

Single-cell RNA sequencing (scRNA-seq) captures detailed gene expression profiles at scale, while patch-clamp recordings measure intrinsic neuronal electrophysiological properties. Modeling the relations between these two modalities remains a challenge. Here, we compare how well electrophysiological features can be predicted by traditional transcriptomic cell type classification, representations derived from a foundational model (scGPT) pretrained on large-scale scRNA-seq datasets, ion channel-coding genes, and highly variable genes. Using paired transcriptomic and electrophysiological patch-sequencing data from 495 human neurons from neurosurgical tissue, we find that cluster-level cell type representations consistently outperform highly variable gene selection, ion channel gene selection, and context-enriched scGPT embeddings. Notably, performance varies across model architectures and initializations, and the best results are obtained by combining the outputs of separate cell type and scGPT-based models. Together, these findings suggest that traditional discrete cellular classification is highly effective in predicting physiological features. For maximum performance it can be complemented by pretrained transformer models.

neuroscience↗
bioRxiv2026

A nonlinear inhibition pathway underlying cortical responses to tuned holographic optogenetic perturbations

Optogenetics enables causal manipulation of cortical activity. Perturbation responses can be counterintuitive due to network interactions, making theory essential for predicting them. Existing approaches often rely on linear approximations, which fail for many biologically relevant perturbations. Here we develop a nonlinear theory of responses to holographic perturbations in cell-type-specific recurrent networks with structured connectivity. We fit a nonlinear model to mouse V1 data, which shows cotuned-ensemble suppression: perturbing spatially clustered neurons with similar preferred orientations yields markedly stronger short-range suppression than perturbing untuned ensembles. We show that cotuned-ensemble suppression arises from a feature-tuned, nonlinear inhibition pathway implicating somatostatin-positive (SST) interneurons. The theory predicts that cotuned ensembles suppress parvalbumin-positive (PV) neurons but facilitate SST neurons, and links the degree of cotuned-ensemble suppression or facilitation to the variance of the SST response. This framework identifies mechanisms by which nonlinear inhibition sculpts cortical dynamics and establishes a predictive basis for targeted optogenetic interventions.

neuroscience↗
bioRxiv2026

Proteomic signatures of APOE ε4 across human tissues and cell types in Alzheimers disease

The apolipoprotein E {varepsilon}4 (APOE {varepsilon}4) allele is the strongest genetic risk factor for late-onset Alzheimers disease (AD). However, the underlying molecular mechanisms remain unclear. This study included 1691 participants from the Religious Orders Study and Rush Memory and Aging Project (ROSMAP), 1226 participants from the Accelerating Medicines Partnership - Alzheimers Disease (AMP-AD) Diverse Cohorts Study, and 735 participants from the Alzheimers Disease Neuroimaging Initiative (ADNI). To characterise APOE {varepsilon}4 molecular effects, we analysed proteomic data from plasma, cerebrospinal fluid (CSF), and induced pluripotent stem cell (iPSC)-derived astrocytes and neurons, as well as transcriptomic and proteomic data from multiple brain regions. The association of APOE {varepsilon}4 with AD neuropathology was also examined. APOE {varepsilon}4 carriers shared a plasma proteomic signature enriched for immune processes, irrespective of AD diagnosis. A machine learning classifier trained on this signature discriminated APOE {varepsilon}4 carriers from non-carriers in an independent cohort using CSF proteomics. APOE {varepsilon}4 carriage was associated with higher Braak stages and Consortium to Establish a Registry for Alzheimers Disease (CERAD) score. However, only limited APOE {varepsilon}4-associated transcriptomic and proteomic changes were observed in bulk brain tissue, with poor cross-layer concordance. Proteomic analyses of iPSC-derived astrocytes and neurons further revealed cell-type-specific APOE {varepsilon}4-associated changes. APOE {varepsilon}4 is associated with a consistent proteomic signature across plasma and CSF. Its molecular effects in the brain differ across cell types, brain regions and molecular layers. These findings support the need for cell-type-resolved multi-omic studies to elucidate how APOE {varepsilon}4 confers AD risk.

neuroscience↗