DetecDiv, a generalist deep-learning platform for automated cell division tracking and survival analysis
Abstract
Automating the extraction of meaningful temporal information from sequences of microscopy images represents a major challenge to characterize dynamical biological processes. So far, strong limitations in the ability to quantitatively analyze single-cell trajectories have prevented large-scale investigations to assess the dynamics of entry into replicative senescence in yeast. Here, we have developed DetecDiv, a microfluidic-based image acquisition platform combined with deep learning-based software for high-throughput single-cell division tracking. We show that DetecDiv can automatically reconstruct cellular replicative lifespans with high accuracy and performs similarly with various imaging platforms and geometries of microfluidic traps. In addition, this methodology provides comprehensive temporal cellular metrics using time-series classification and image semantic segmentation. Last, we show that this method can be further applied to automatically quantify the dynamics of cellular adaptation and real-time cell survival upon exposure to environmental stress. Hence, this methodology provides an all-in-one toolbox for high-throughput phenotyping for cell cycle, stress response, and replicative lifespan assays.
Data availability
Software and documentation is fully available via Github.Data used for training classifiers is available using several zenodo repositories.A demo detecdiv project that contains all information to train users on detecdiv is available on zenodo.All the links are provided in the manuscript file.
Article and author information
Author details
Funding
Agence Nationale de la Recherche (ANR-10-LABX-0030-INRT)
- Gilles Charvin
Agence Nationale de la Recherche (ANR-10-IDEX-0002-02)
- Gilles Charvin
The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.
Copyright
© 2022, Aspert et al.
This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.
Metrics
-
- 1,812
- views
-
- 337
- downloads
-
- 10
- citations
Views, downloads and citations are aggregated across all versions of this paper published by eLife.
Download links
Downloads (link to download the article as PDF)
Open citations (links to open the citations from this article in various online reference manager services)
Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)
Further reading
-
- Cell Biology
Tunneling nanotubes (TNTs) are open actin- and membrane-based channels, connecting remote cells and allowing direct transfer of cellular material (e.g. vesicles, mRNAs, protein aggregates) from the cytoplasm to the cytoplasm. Although they are important especially, in pathological conditions (e.g. cancers, neurodegenerative diseases), their precise composition and their regulation were still poorly described. Here, using a biochemical approach allowing to separate TNTs from cell bodies and from extracellular vesicles and particles (EVPs), we obtained the full composition of TNTs compared to EVPs. We then focused on two major components of our proteomic data, the CD9 and CD81 tetraspanins, and further investigated their specific roles in TNT formation and function. We show that these two tetraspanins have distinct non-redundant functions: CD9 participates in stabilizing TNTs, whereas CD81 expression is required to allow the functional transfer of vesicles in the newly formed TNTs, possibly by regulating docking to or fusion with the opposing cell.
-
- Cell Biology
Noncoding RNA plays a pivotal role as novel regulators of endothelial cell function. Type 2 diabetes, acknowledged as a primary contributor to cardiovascular diseases, plays a vital role in vascular endothelial cell dysfunction due to induced abnormalities of glucolipid metabolism and oxidative stress. In this study, aberrant expression levels of circHMGCS1 and MIR4521 were observed in diabetes-induced human umbilical vein endothelial cell dysfunction. Persistent inhibition of MIR4521 accelerated development and exacerbated vascular endothelial dysfunction in diabetic mice. Mechanistically, circHMGCS1 upregulated arginase 1 by sponging MIR4521, leading to decrease in vascular nitric oxide secretion and inhibition of endothelial nitric oxide synthase activity, and an increase in the expression of adhesion molecules and generation of cellular reactive oxygen species, reduced vasodilation and accelerated the impairment of vascular endothelial function. Collectively, these findings illuminate the physiological role and interacting mechanisms of circHMGCS1 and MIR4521 in diabetes-induced cardiovascular diseases, suggesting that modulating the expression of circHMGCS1 and MIR4521 could serve as a potential strategy to prevent diabetes-associated cardiovascular diseases. Furthermore, our findings provide a novel technical avenue for unraveling ncRNAs regulatory roles of ncRNAs in diabetes and its associated complications.