Data denoising with transfer learning in single-cell transcriptomics

被引：127

作者：

Wang, Jingshu ^{[1
]}

Agarwal, Divyansh ^{[2
]}

Huang, Mo ^{[1
]}

Hu, Gang ^{[3
]}

Zhou, Zilu ^{[2
]}

Ye, Chengzhong ^{[4
]}

Zhang, Nancy R. ^{[1
]}

机构：

[1] Univ Penn, Dept Stat, Philadelphia, PA 19104 USA

[2] Univ Penn, Grad Grp Genom & Computat Biol, Philadelphia, PA 19104 USA

[3] Nankai Univ, Sch Math Sci, Tianjin, Peoples R China

[4] Tsinghua Univ, Sch Med, Beijing, Peoples R China

来源：

NATURE METHODS | 2019年 / 16卷 / 09期

基金：

美国国家科学基金会;

关键词：

MOUSE;

D O I：

10.1038/s41592-019-0537-1

中图分类号：

Q5 [生物化学];

学科分类号：

071010 ; 081704 ;

摘要：

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.

引用

页码：875 / +

页数：6

共 21 条

[1]

Andrews Tallulah S, 2018, F1000Res, V7, P1740, DOI 10.12688/f1000research.16613.1

[2] Single-Cell Map of Diverse Immune Phenotypes in the Breast Tumor Microenvironment [J].

Azizi, Elham ;

Carr, Ambrose J. ;

Plitas, George ;

Cornish, Andrew E. ;

Konopacki, Catherine ;

Prabhakaran, Sandhya ;

Nainys, Juozas ;

Wu, Kenmin ;

Kiseliovas, Vaidotas ;

Setty, Manu ;

Choi, Kristy ;

Fromme, Rachel M. ;

Phuong Dao ;

McKenney, Peter T. ;

Wasti, Ruby C. ;

Kadaveru, Krishna ;

Mazutis, Linas ;

Rudensky, Alexander Y. ;

Pe'er, Dana .

CELL, 2018, 174 (05) :1293-+

[3] Human cerebral organoids recapitulate gene expression programs of fetal neocortex development [J].

Camp, J. Gray ;

Badsha, Farhath ;

Florio, Marta ;

Kanton, Sabina ;

Gerber, Tobias ;

Wilsch-Braeuninger, Michaela ;

Lewitus, Eric ;

Sykes, Alex ;

Hevers, Wulf ;

Lancaster, Madeline ;

Knoblich, Juergen A. ;

Lachmann, Robert ;

Paeaebo, Svante ;

Huttner, Wieland B. ;

Treutlein, Barbara .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2015, 112 (51) :15672-15677

[4] Single-cell RNA-seq denoising using a deep count autoencoder [J].

Eraslan, Goekcen ;

Simon, Lukas M. ;

Mircea, Maria ;

Mueller, Nikola S. ;

Theis, Fabian J. .

NATURE COMMUNICATIONS, 2019, 10 (1)

[5]

Gong W., 2018, BMC BIOINFORMATICS, V19, P1

[6] Mapping the Mouse Cell Atlas by Microwell-Seq [J].

Han, Xiaoping ;

Wang, Renying ;

Zhou, Yincong ;

Fei, Lijiang ;

Sun, Huiyu ;

Lai, Shujing ;

Saadatpour, Assieh ;

Zhou, Zimin ;

Chen, Haide ;

Ye, Fang ;

Huang, Daosheng ;

Xu, Yang ;

Huang, Wentao ;

Jiang, Mengmeng ;

Jiang, Xinyi ;

Mao, Jie ;

Chen, Yao ;

Lu, Chenyu ;

Xie, Jin ;

Fang, Qun ;

Wang, Yibin ;

Yue, Rui ;

Li, Tiefeng ;

Huang, He ;

Orkin, Stuart H. ;

Yuan, Guo-Cheng ;

Chen, Ming ;

Guo, Guoji .

CELL, 2018, 172 (05) :1091-+

[7] Reducing the dimensionality of data with neural networks [J].

Hinton, G. E. ;

Salakhutdinov, R. R. .

SCIENCE, 2006, 313 (5786) :504-507

[8] SAVER: gene expression recovery for single-cell RNA sequencing [J].

Huang, Mo ;

Wang, Jingshu ;

Torre, Eduardo ;

Dueck, Hannah ;

Shaffer, Sydney ;

Bonasio, Roberto ;

Murray, John I. ;

Raj, Arjun ;

Li, Mingyao ;

Zhang, Nancy R. .

NATURE METHODS, 2018, 15 (07) :539-+

[9] Characterizing noise structure in single-cell RNA-seq distinguishes genuine from technical stochastic allelic expression [J].

Kim, Jong Kyoung ;

Kolodziejczyk, Aleksandra A. ;

Illicic, Tomislav ;

Teichmann, Sarah A. ;

Marioni, John C. .

NATURE COMMUNICATIONS, 2015, 6

[10] Molecular Diversity of Midbrain Development in Mouse, Human, and Stem Cells [J].

La Manno, Gioele ;

Gyllborg, Daniel ;

Codeluppi, Simone ;

Nishimura, Kaneyasu ;

Salto, Carmen ;

Zeisel, Amit ;

Borm, Lars E. ;

Stott, Simon R. W. ;

Toledo, Enrique M. ;

Villaescusa, J. Carlos ;

Lonnerberg, Peter ;

Ryge, Jesper ;

Barker, Roger A. ;

Arenas, Ernest ;

Linnarsson, Sten .

CELL, 2016, 167 (02) :566-+

← 1 2 3 →