PT  - JOURNAL ARTICLE
AU  - Pierre Boyeau
AU  - Romain Lopez
AU  - Jeffrey Regier
AU  - Adam Gayoso
AU  - Michael I. Jordan
AU  - Nir Yosef
TI  - Deep Generative Models for Detecting Differential Expression in Single Cells
AID  - 10.1101/794289
DP  - 2019 Jan 01
TA  - bioRxiv
PG  - 794289
4099  - http://biorxiv.org/content/early/2019/10/04/794289.short
4100  - http://biorxiv.org/content/early/2019/10/04/794289.full
AB  - Detecting differentially expressed genes is important for characterizing subpopulations of cells. However, in scRNA-seq data, nuisance variation due to technical factors like sequencing depth and RNA capture efficiency obscures the underlying biological signal. First, we show that deep generative models, which combined Bayesian statistics and deep neural networks, better estimate the log-fold-change in gene expression levels between subpopulations of cells. Second, we use Bayesian decision theory to detect differentially expressed genes while controlling the false discovery rate. Our experiments on simulated and real datasets show that our approach out-performs state-of-the-art DE frameworks. Finally, we introduce a technique for improving the posterior approximation, and show that it also improves differential expression performance.