Fast and precise single-cell data analysis using a hierarchical autoencoder

A primary challenge in single-cell RNA sequencing (scRNA-seq) studies comes from the massive amount of data and the excess noise level. To address this challenge, we introduce an analysis framework, named single-cell Decomposition using Hierarchical Autoencoder (scDHA), that reliably extracts repres...

Full description

Saved in:
Bibliographic Details
Published in:Nature communications Vol. 12; no. 1; pp. 1029 - 10
Main Authors: Tran, Duc, Nguyen, Hung, Tran, Bang, La Vecchia, Carlo, Luu, Hung N., Nguyen, Tin
Format: Journal Article
Language:English
Published: London Nature Publishing Group UK 15.02.2021
Nature Publishing Group
Nature Portfolio
Subjects:
631/114/1305
631/114/794
631/208/514/1949
Accuracy
Animals
Bayes Theorem
Bayesian analysis
Benchmarking
Cell cycle
Cell Separation - methods
Cerebellum - chemistry
Cerebellum - cytology
Classification
Clustering
Data analysis
Datasets
Decomposition
Embryo, Mammalian
Gene expression
Gene sequencing
Genomics
Humanities and Social Sciences
Humans
Liver - chemistry
Liver - cytology
Lung - chemistry
Lung - cytology
Methods
Mice
Modules
Mouse Embryonic Stem Cells - chemistry
Mouse Embryonic Stem Cells - cytology
multidisciplinary
Neural networks
Neural Networks, Computer
Noise
Noise levels
Pancreas - chemistry
Pancreas - cytology
Representations
Retina - chemistry
Retina - cytology
Ribonucleic acid
RNA
Science
Science (multidisciplinary)
Segregation
Sequence Analysis, RNA - statistics & numerical data
Single-Cell Analysis - methods
Single-Cell Analysis - statistics & numerical data
Transcriptomes
Unsupervised Machine Learning - statistics & numerical data
Visual Cortex - chemistry
Visual Cortex - cytology
Visualization
Zygote - chemistry
Zygote - cytology
ISSN:2041-1723, 2041-1723
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A primary challenge in single-cell RNA sequencing (scRNA-seq) studies comes from the massive amount of data and the excess noise level. To address this challenge, we introduce an analysis framework, named single-cell Decomposition using Hierarchical Autoencoder (scDHA), that reliably extracts representative information of each cell. The scDHA pipeline consists of two core modules. The first module is a non-negative kernel autoencoder able to remove genes or components that have insignificant contributions to the part-based representation of the data. The second module is a stacked Bayesian autoencoder that projects the data onto a low-dimensional space (compressed). To diminish the tendency to overfit of neural networks, we repeatedly perturb the compressed space to learn a more generalized representation of the data. In an extensive analysis, we demonstrate that scDHA outperforms state-of-the-art techniques in many research sub-fields of scRNA-seq analysis, including cell segregation through unsupervised learning, visualization of transcriptome landscape, cell classification, and pseudo-time inference. Accurate analysis of single-cell RNA sequencing (scRNA-seq) data is affected by issues including technical noise and high dropout rate. Here, the authors develop a hierarchical autoencoder, scDHA, which outperforms existing methods in scRNA-seq analyses such as cell segregation and classification.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2041-1723
2041-1723
DOI:10.1038/s41467-021-21312-2