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

Journal: Nature methods

PMID: 30886411

Abstract

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.

Authors

Yue Deng

School of Artificial Intelligence, Beihang University, Beijing 100191, China.
Feng Bao
Qionghai Dai
Lani F Wu

Department of Pharmaceutical Chemistry, University of California at San Francisco, San Francisco, CA 94158, USA.
Steven J Altschuler

Department of Pharmaceutical Chemistry, University of California at San Francisco, San Francisco, CA 94158, USA.

Keywords

Algorithms Animals Brain Mapping Cluster Analysis Computational Biology Computer Simulation Databases, Genetic Deep Learning Gene Expression Profiling Inflammation Intestines Leukocytes, Mononuclear Mice Phenotype Principal Component Analysis Reproducibility of Results Retina RNA Sequence Analysis, RNA Single-Cell Analysis Software Transcriptome

External Resources

View on PubMed Access via DOI PubMed (30886411)

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

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals