SKM 2021 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
BP: Fachverband Biologische Physik
BP 1: Statistical physics of biological systems (joint session BP/DY)
BP 1.1: Hauptvortrag
Montag, 27. September 2021, 10:00–10:30, H1
Physics-Informed Deep Learning for Characterizing Perturbed Cell Growth — •Robert Endres1, Henry Cavanagh1, Rob Lind2, Andreas Mosbach3, and Gabriel Scalliet3 — 1Imperial College London, UK — 2Syngenta International Research Centre, UK — 3Syngenta Crop Protection AG, Switzerland
The morphodynamical analysis of cells can be a powerful and cost-effective way of understanding the phenotypic effects of perturbations, but current techniques often only work for stationary cell behaviour. Here, we introduce a novel framework that extends the morphodynamic analysis to nonstationary dynamics during early-stage growth of the soybean rust P. pachyrhizi. At its core, our approach learns the 2-dimensional feature space of cell shape using variational autoencoders from deep learning, and subsequently models how populations of cells develop over this space using two simple differential equations, each capturing complementary aspects of the dynamics with parameters depending on the perturbations. First, a Fokker-Planck model to describe the diffusive development on a Waddington-type energy landscape, providing a global perspective on the dynamics, and second, a cell-mechanical model describing local growth as a persistent random walk. Informative perturbation-dependent parameters are found by fitting simulations to the shape-space embeddings, representing a powerful tool for linking machine-learning and biophysical modelling.