TARGETING ORGANELLE-ORGANELLE ORGANIZATION VIA MICROSCOPY-BASED HIGH-CONTENT PHENOTYPIC SCREENING AND GENERATIVE NEURAL NETWORKS
2Department of Industrial Engineering & Management, Ben-Gurion University of the Negev, Beer-Sheva, Israel
3Department of Computer Science, Jerusalem College of Technology, Jerusalem, Israel
Disruption in cell organization determined by the cell’s organelles composition in space and improper organelle-organelle organization leads to impaired cell function in many diseases. Thus, discovery of drugs that revert the cell structure and organization to its “healthy” state is an initial step in some drug discovery pipelines. High-content image-based screening is emerging as a powerful technology to identify phenotypic differences in cell populations with several applications including drug screening. While current computational approaches pool image-based features from different modalities, each of a distinct organelle, we develop new methodology to measure alterations in the spatial dependencies between different organelles and apply it to identify new treatments that interfere with specific spatial dependencies between organelles. The methodology is based on measuring the reconstruction error of generative neural networks that map the different modalities to one another. Our preliminary results indicate that this approach is feasible, and that spatial organelle dependencies are much more sensitive, specific, interpretable, and reproducible readouts for phenotypic cell screening. Specifically, we show that (1) phenotypes are dramatically amplified making it easier to identify subtle phenotypes, (2) new phenotypes that are missed by traditional analyses can be discovered, (3) spatial dependencies are differentially determined based on organelles composition and perturbation, implying a more specific and interpretable readout, and (4) reproducibility is improved with these new measurements. Overall, our methodology is the first to target defects in inter-organelle spatial dependencies and will enable discovery and mechanistic interpretability of the effects each treatment has on specific aspects of cell organization in terms of “breaking” existing relations between multiple cell structures, which are currently inaccessible. This approach holds the promise for broad translational applicability in drug discovery, repurposing existing drugs, and combinatorial drug therapy.