PUBLICATION
A deep learning framework for quantitative analysis of actin microridges
- Authors
- Bhavna, R., Sonawane, M.
- ID
- ZDB-PUB-230604-36
- Date
- 2023
- Source
- NPJ systems biology and applications 9: 2121 (Journal)
- Registered Authors
- Sonawane, Mahendra
- Keywords
- none
- MeSH Terms
-
- Actin Cytoskeleton/genetics
- Actins*/genetics
- Actomyosin
- Animals
- Deep Learning*
- Zebrafish/genetics
- PubMed
- 37268613 Full text @ NPJ Syst Biol Appl
Citation
Bhavna, R., Sonawane, M. (2023) A deep learning framework for quantitative analysis of actin microridges. NPJ systems biology and applications. 9:2121.
Abstract
Microridges are evolutionarily conserved actin-rich protrusions present on the apical surface of squamous epithelial cells. In zebrafish epidermal cells, microridges form self-evolving patterns due to the underlying actomyosin network dynamics. However, their morphological and dynamic characteristics have remained poorly understood owing to a lack of computational methods. We achieved ~95% pixel-level accuracy with a deep learning microridge segmentation strategy enabling quantitative insights into their bio-physical-mechanical characteristics. From the segmented images, we estimated an effective microridge persistence length of ~6.1 μm. We discovered the presence of mechanical fluctuations and found relatively greater stresses stored within patterns of yolk than flank, indicating distinct regulation of their actomyosin networks. Furthermore, spontaneous formations and positional fluctuations of actin clusters within microridges were associated with pattern rearrangements over short length/time-scales. Our framework allows large-scale spatiotemporal analysis of microridges during epithelial development and probing of their responses to chemical and genetic perturbations to unravel the underlying patterning mechanisms.
Genes / Markers
Expression
Phenotype
Mutations / Transgenics
Human Disease / Model
Sequence Targeting Reagents
Fish
Orthology
Engineered Foreign Genes
Mapping