B1939
Title: Machine learning enabled pattern discovery in large-scale spatial gene expression datasets
Authors: Reza Abbasi Asl - University of California, San Francisco (United States) [presenting]
Abstract: Advances in spatially-resolved and high-throughput molecular imaging from the brain such as multiplexed immunofluorescence and spatial transcriptomics (ST) provide exciting new opportunities to augment the fundamental understanding of these processes in health and disease. The large and complex brain-wide datasets resulting from these techniques, particularly ST, have led to the rapid development of innovative machine learning (ML) tools primarily based on deep learning techniques. These ML tools are now increasingly featured in integrated experimental and computational workflows to disentangle signals from noise in complex biological systems. However, it can be difficult to understand and balance the different implicit assumptions and methodologies of a rapidly expanding toolbox of analytical tools in ST. Four major data science concepts are described and related heuristics that can help guide practitioners in their choices of the right tools for the right biological questions. These principles are then showcased in the development of an unsupervised and interpretable computational framework to identify principal patterns of 3D spatial gene expression profiles.