Machine learning topological defects in confluent tissues
arXiv:2303.08166 · doi:10.1016/j.bpr.2024.100142
Abstract
Active nematics is an emerging paradigm for characterising biological systems. One aspect of particularly intense focus is the role active nematic defects play in these systems, as they have been found to mediate a growing number of biological processes. Accurately detecting and classifying these defects in biological systems is, therefore, of vital importance to improving our understanding of such processes. While robust methods for defect detection exist for systems of elongated constituents, other systems, such as epithelial layers, are not well suited to such methods. Here, we address this problem by developing a convolutional neural network to detect and classify nematic defects in confluent cell layers. Crucially, our method is readily implementable on experimental images of cell layers and is specifically designed to be suitable for cells that are not rod-shaped. We demonstrate that our machine learning model outperforms current defect detection techniques and that this manifests itself in our method requiring less data to accurately capture defect properties. This could drastically improve the accuracy of experimental data interpretation whilst also reducing costs, advancing the study of nematic defects in biological systems.
arXiv comment15 pages, 5 figures + 2 page appendix
References in corpus (21)
- Spontaneous motion in hierarchically assembled active matter
- Topological defect launches 3D mound in the active nematic sheet of neural progenitors
- Physical Models of Collective Cell Migration
- Computational models for active matter
- Defect annihilation and proliferation in active nematics
- Orientational order of motile defects in active nematics
- Universal geometric constraints during epithelial jamming
- Defect dynamics in active nematics
- Topological defects promote layer formation in Myxococcus xanthus colonies
- Turbulent dynamics of epithelial cell cultures
- Self-organized dynamics and the transition to turbulence of confined active nematics
- Defect-mediated morphologies in growing cell colonies
- Machine learning vortices at the Kosterlitz-Thouless transition
- Dense active matter model of motion patterns in confluent cell monolayers
- Data-driven quantitative modeling of bacterial active nematics
- Bacteria solve the problem of crowding by moving slowly
- Theory of defect-mediated morphogenesis
- cellGPU: massively parallel simulations of dynamic vertex models
- Machine learning active-nematic hydrodynamics
- Distribution of Singularities in the Cosmic Microwave Background Polarization
- Detection of Islands and Droplets on Smectic Films Using Machine Learning