Variational Autoencoders for Single-Cell Genomics

Abstract

An introduction to variational autoencoders for single-cell transcriptomics. The lecture covers the probabilistic foundations of scVI, motivates deep generative modeling for noisy count data, and discusses applications to batch correction, differential expression, and dimensionality reduction in single-cell RNA-seq.

Date
Apr 15, 2021
Location
Cambridge, MA, USA
Cambridge, MA, United States
Avatar
Romain Lopez
Assistant Professor of Computer Science and Biology

My research interests lie at the intersection of statistics, computation and modeling of biological data. A significant part of my research is driven by building more statistically accurate and faster machine learning software for analyzing genomics data.