Statistical Machine Learning for Learning Representations of Embryonic Development

Watch a Big Data Conference 2024 talk exploring how statistical machine learning frameworks help understand the complex relationship between mechanical forces, cell morphology, and gene expression during embryonic development. Discover innovative approaches to analyzing single cell techniques and in toto imaging that reveal the dynamic processes of organogenesis in early embryos. Learn about specific applications in studying boundary formation in mouse embryo development and aligning data from light sheet recordings of pre-gastrulation development. Gain insights into how individual cells interpret environmental information to drive movement, division, and specialization, ultimately contributing to the ever-changing embryonic environment. The presentation by Bianca Dumitrascu from Columbia Data Science Institute bridges the gap between genomics and biophysics in developmental biology through advanced statistical analysis methods.