CCB Seminar: Learning cellular state and dynamics in single cell genomics

Dr. Fabian Theis, Head of Computational Health Center, Helmholtz Institute Munich
Modeling cellular state as well as dynamics e.g. during differentiation or in response to perturbations is a central goal of computational biology. Single-cell technologies now give us easy and large-scale access to state observations on the transcriptomic and more recently also epigenomic level. This makes this an ideal application area for machine learning method development to understand cellular variation, contribution of particular transcripts as well as impact of perturbations.
In this talk I will shortly review a recent model for dynamic RNA velocity (scVelo) as well as its extension CellRank, which we developed to learn cellular differentiation trajectories from expression profiles. It allows users to gain insights into the timing of endocrine lineage commitment and recapitulates gene expression trends towards developmental endpoints.
While this approach focusses on individual gene expression models, recently latent space modeling and manifold learning have become a popular tool to learn overall variation in single cell gene expression. I will follow up with representation learning approaches to identify the gene expression manifold, and the introduce models for interpretable modeling of perturbations such as drug or genetic modification on this manifold.