Scalable analysis of cell-type composition from single-cell transcriptomics using deep recurrent learning

Recent advances in large-scale single-cell RNA-seq enable fine-grained characterization of phenotypically distinct cellular states in heterogeneous tissues. We present scScope, a scalable deep-learning-based approach that can accurately and rapidly identify cell-type composition from millions of noi...

Full description

Saved in:
Bibliographic Details
Published inNature methods Vol. 16; no. 4; pp. 311 - 314
Main Authors Deng, Yue, Bao, Feng, Dai, Qionghai, Wu, Lani F., Altschuler, Steven J.
Format Journal Article
LanguageEnglish
Published New York Nature Publishing Group US 01.04.2019
Nature Publishing Group
Subjects
631/114/1305
631/114/2397
631/114/794
Accuracy
Algorithms
Animals
Bioinformatics
Biological Microscopy
Biological Techniques
Biomedical and Life Sciences
Biomedical Engineering/Biotechnology
Brain Mapping
Brief Communication
Cluster Analysis
Composition
Computational Biology - methods
Computer Simulation
Databases, Genetic
Datasets
Deep Learning
Gene expression
Gene Expression Profiling
Genes
Inflammation
Information science
Intestines - cytology
Leukocytes, Mononuclear - cytology
Life Sciences
Machine learning
Mice
Phenotype
Principal Component Analysis
Proteomics
Reproducibility of Results
Retina
Retina - metabolism
Ribonucleic acid
RNA
RNA - analysis
RNA - genetics
RNA sequencing
Sequence Analysis, RNA
Single-Cell Analysis
Software
Software packages
Sparsity
Surgery
Technology
Transcriptome
Online AccessGet full text

Cover

More Information
Summary:Recent advances in large-scale single-cell RNA-seq enable fine-grained characterization of phenotypically distinct cellular states in heterogeneous tissues. We present scScope, a scalable deep-learning-based approach that can accurately and rapidly identify cell-type composition from millions of noisy single-cell gene-expression profiles. scScope uses a recurrent network to remove batch effects and iteratively impute zero values in scRNA-seq data.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
These authors contributed equally to this work.
Y.D., F.B. and Q.D. developed the deep learning algorithms. Y.D. and F.B. conducted experimental analysis on both simulated and biological datasets. The manuscript was written by Y.D., F.B., L.F.W. and S.J.A. All authors read and approved the manuscript.
Author Contributions
ISSN:1548-7091
1548-7105
1548-7105
DOI:10.1038/s41592-019-0353-7