3.0

credits

Average Course Rating

Recent advances in sequencing technologies have enabled scientists to measure DNA, RNA and other diverse molecular modalities from individual cells at an unprecedented scale and resolution. This course will survey machine learning and statistical approaches for analyzing high-dimensional and high-throughput single-cell and spatial sequencing data. Topics include: dimensionality reduction and dynamical systems models for single-cell and spatial RNA sequencing; spatial clustering; multi-sample differential analyses; optimal transport; foundation models; and related topics. Course meetings will be a mix of lectures and student-led presentations/discussions of recent research papers. Students will complete a final project to explore one of the class topics in depth. Prior biology background is not required. Required Course Background: probability and (data science or machine learning).