Content area
Abstract
Single-cell RNA sequencing (scRNA-seq) data are noisy and sparse. Here, we show that transfer learning across datasets remarkably improves data quality. By coupling a deep autoencoder with a Bayesian model, SAVER-X extracts transferable gene−gene relationships across data from different labs, varying conditions and divergent species, to denoise new target datasets.
Details
Title
Data denoising with transfer learning in single-cell transcriptomics
Author
Wang, Jingshu 1 ; Agarwal, Divyansh 2
; Huang, Mo 1
; Hu, Gang 3 ; Zhou, Zilu 2 ; Ye, Chengzhong 4 ; Zhang, Nancy R 1
1 Department of Statistics, University of Pennsylvania, Philadelphia, PA, USA
2 Graduate Group in Genomics and Computational Biology, University of Pennsylvania, Philadelphia, PA, USA
3 School of Mathematical Sciences, Nankai University, Tianjin, China
4 School of Medicine, Tsinghua University, Beijing, China
; Huang, Mo 1
; Hu, Gang 3 ; Zhou, Zilu 2 ; Ye, Chengzhong 4 ; Zhang, Nancy R 1
1 Department of Statistics, University of Pennsylvania, Philadelphia, PA, USA
2 Graduate Group in Genomics and Computational Biology, University of Pennsylvania, Philadelphia, PA, USA
3 School of Mathematical Sciences, Nankai University, Tianjin, China
4 School of Medicine, Tsinghua University, Beijing, China
Pages
875-878
Publication year
2019
Publication date
Sep 2019
ISSN
15487091
e-ISSN
15487105
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2282779171
Copyright
Copyright Nature Publishing Group Sep 2019