Learning interpretable cellular and gene signature embeddings from single-cell transcriptomic data

The advent of single-cell RNA sequencing (scRNA-seq) technologies has revolutionized transcriptomic studies. However, large-scale integrative analysis of scRNA-seq data remains a challenge largely due to unwanted batch effects and the limited transferabilty, interpretability, and scalability of the...

Full description

Saved in:
Bibliographic Details
Published in:Nature communications Vol. 12; no. 1; pp. 5261 - 15
Main Authors: Zhao, Yifan, Cai, Huiyu, Zhang, Zuobai, Tang, Jian, Li, Yue
Format: Journal Article
Language:English
Published: London Nature Publishing Group UK 06.09.2021
Nature Publishing Group
Nature Portfolio
Subjects:
631/114/1305
631/114/2404
Alzheimer Disease - genetics
Alzheimer Disease - pathology
Animals
Clustering
Coders
Computer applications
Computer science
Data analysis
Databases, Genetic
Datasets
Depressive Disorder, Major - genetics
Depressive Disorder, Major - pathology
Gene expression
Gene Expression Profiling - methods
Gene Expression Profiling - statistics & numerical data
Gene sequencing
Gene set enrichment analysis
Genes, Mitochondrial
Humanities and Social Sciences
Humans
Learning
Mathematical analysis
Mice
Models, Genetic
multidisciplinary
Neural networks
Neural Networks, Computer
Retina - cytology
Retina - physiology
Ribonucleic acid
RNA
RNA, Small Cytoplasmic
Science
Science (multidisciplinary)
Sequence Analysis, RNA - methods
Sequence Analysis, RNA - statistics & numerical data
Single-Cell Analysis - methods
Transcriptomics
Transfer learning
ISSN:2041-1723, 2041-1723
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The advent of single-cell RNA sequencing (scRNA-seq) technologies has revolutionized transcriptomic studies. However, large-scale integrative analysis of scRNA-seq data remains a challenge largely due to unwanted batch effects and the limited transferabilty, interpretability, and scalability of the existing computational methods. We present single-cell Embedded Topic Model (scETM). Our key contribution is the utilization of a transferable neural-network-based encoder while having an interpretable linear decoder via a matrix tri-factorization. In particular, scETM simultaneously learns an encoder network to infer cell type mixture and a set of highly interpretable gene embeddings, topic embeddings, and batch-effect linear intercepts from multiple scRNA-seq datasets. scETM is scalable to over 10 6 cells and confers remarkable cross-tissue and cross-species zero-shot transfer-learning performance. Using gene set enrichment analysis, we find that scETM-learned topics are enriched in biologically meaningful and disease-related pathways. Lastly, scETM enables the incorporation of known gene sets into the gene embeddings, thereby directly learning the associations between pathways and topics via the topic embeddings. Computational single-cell RNA-seq analyses often face challenges in scalability, model interpretability, and confounders. Here, we show a new model to address these challenges by learning meaningful embeddings from the data that simultaneously refine gene signatures and cell functions in diverse conditions.
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/s41467-021-25534-2