RT Journal Article
SR Electronic
T1 Learning interpretable cellular and gene signature embeddings from single-cell transcriptomic data
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2021.01.13.426593
DO 10.1101/2021.01.13.426593
A1 Yifan Zhao
A1 Huiyu Cai
A1 Zuobai Zhang
A1 Jian Tang
A1 Yue Li
YR 2021
UL http://biorxiv.org/content/early/2021/01/15/2021.01.13.426593.abstract
AB The advent of single-cell RNA sequencing (scRNA-seq) technologies has revolutionized transcriptomic studies. However, integrative analysis of scRNA-seq data remains a challenge largely due to batch effects. We present single-cell Embedded Topic Model (scETM), an unsupervised deep generative model that recapitulates known cell types by inferring the latent cell topic mixtures via a variational autoencoder. scETM is scalable to over 106 cells and enables effective knowledge transfer across datasets. scETM also offers high inter-pretability and allows the incorporation of prior pathway knowledge into the gene embeddings. The scETM-inferred topics show enrichment in cell-type-specific and disease-related pathways.Competing Interest StatementThe authors have declared no competing interest.