Breast cancer is a highly heterogenous disease, both phenotypically and genetically. Here, we propose that the spatial context of organelles, specifically their subcellular location and inter-organelle relationships (topology), can be used to inform breast cancer cell classification. Thus, Organelle-Topology-Cell-Classification-Pipeline (OTCCP) was introduced to quantify the topological features of subcellular organelles, remove the bias of visual interpretation, and classify different breast cancer cell lines using a machine learning method. Our goal is to investigate the role of 3D cancer cell growth on the heterogeneity of organelle topology and morphology to increase the understanding of cancer biology on a subcellular level.
|