Title: Learning consistent subcellular landmarks to quantify changes in multiplexed protein maps Speaker: Dr Scott Berry (UNSW) Abstract: Highly multiplexed imaging holds enormous promise for understanding how spatial context shapes the activity of the genome and its products at multiple length scales. We have recently developed a deep-learning framework called CAMPA (Conditional Autoencoder for Multiplexed Pixel Analysis) to learn representations of molecular pixel-profiles that are consistent across heterogeneous cell populations and experimental perturbations. CAMPA identifies consistent subcellular landmarks, which can be quantitatively compared in terms of their sizes, shapes, molecular compositions, and relative spatial organisation. Using high-resolution multiplexed immunofluorescence, this reveals how subcellular organisation changes upon perturbation of RNA production, RNA processing, or cell size, and uncovers links between the molecular composition of membraneless organelles and cell-to-cell variability in bulk RNA synthesis rates. By capturing interpretable cellular phenotypes, we anticipate that CAMPA will accelerate the systematic mapping of multiscale atlases of biological organisation to identify the rules by which context shapes physiology and disease. About the speaker: Scott has a background in Theoretical Physics and Molecular Biology. He studied a PhD at the John Innes Centre in Norwich, UK, on mechanisms of epigenetic memory in plants, before moving to the University of Zurich in Switzerland as an HFSP and EMBO postdoctoral fellow. In Zurich, Scott worked on mechanisms of mRNA concentration homeostasis in mammalian cells and experimental and computational approaches for acquiring and analysing highly multiplexed image data. In 2021, Scott started his group at Single Molecule Science, the EMBL Australia node at the University of New South Wales in Sydney. His group works on quantitative regulation of gene expression at the single-cell level, primarily employing microscopy and systems biology approaches â including mathematical modelling.