Deep Generative Modeling of Transcriptional Dynamics and Data-View Agnostic Inference of Cellular State Changes With Single-Cell Omics Data
MCML Authors
Philipp Weiler
Dr.
Abstract
Philipp Weiler
Dr.
Abstract
Single-cell genomics is revolutionizing the field of biology to recover cellular trajectories and fate, for example. Although existing methods have proven powerful in many settings, they leave room for improvement: Approaches focus on specific data aspects and do not generalize to newly emerging data modalities, or include restrictive modeling paradigms. To overcome these limitations, this dissertation describes a deep generative model for inferring RNA velocity and a framework to unifying fate mapping in a data-view agnostic fashion.
BibTeXKey: Wei25