scCompressSA: dual-channel self-attention based deep autoencoder model for single-cell clustering by compressing gene–gene interactions

Background Single-cell clustering has played an important role in exploring the molecular mechanisms about cell differentiation and human diseases. Due to highly-stochastic transcriptomics data, accurate detection of cell types is still challenged, especially for RNA-sequencing data from human being...

Full description

Saved in:
Bibliographic Details
Published in:BMC genomics Vol. 25; no. 1; pp. 423 - 12
Main Authors: Zhang, Wei, Yu, Ruochen, Xu, Zeqi, Li, Junnan, Gao, Wenhao, Jiang, Mingfeng, Dai, Qi
Format: Journal Article
Language:English
Published: London BioMed Central 29.04.2024
BioMed Central Ltd
Springer Nature B.V
BMC
Subjects:
Algorithms
Animal Genetics and Genomics
Artificial neural networks
Biomedical and Life Sciences
Cell differentiation
Cells
Cluster Analysis
Clustering
Coefficient compression
Computational Biology - methods
Cross correlation
Data compression
Deep Learning
Differentiation (biology)
Dual-channel self-attention mechanism
Epistasis, Genetic
Gene expression
Gene Expression Profiling - methods
Gene Regulatory Networks
Gene sequencing
Genes
Genetic aspects
Genetic research
Humans
Life Sciences
Methods
Microarrays
Microbial Genetics and Genomics
Molecular modelling
Neural networks
Neural Networks, Computer
Plant Genetics and Genomics
Probability distribution
Proteomics
Regression analysis
RNA
RNA sequencing
Sequence Analysis, RNA - methods
Single-Cell Analysis - methods
Single-cell RNA sequencing (scRNA-seq)
Static gene–gene interactions
Temporal variations
Topology
Transcriptomics
China
Single-cell RNA sequencing (scRNA-seq)
Static gene–gene interactions
Dual-channel self-attention mechanism
Coefficient compression
ISSN:1471-2164, 1471-2164
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background Single-cell clustering has played an important role in exploring the molecular mechanisms about cell differentiation and human diseases. Due to highly-stochastic transcriptomics data, accurate detection of cell types is still challenged, especially for RNA-sequencing data from human beings. In this case, deep neural networks have been increasingly employed to mine cell type specific patterns and have outperformed statistic approaches in cell clustering. Results Using cross-correlation to capture gene–gene interactions, this study proposes the scCompressSA method to integrate topological patterns from scRNA-seq data, with support of self-attention (SA) based coefficient compression (CC) block. This SA-based CC block is able to extract and employ static gene–gene interactions from scRNA-seq data. This proposed scCompressSA method has enhanced clustering accuracy in multiple benchmark scRNA-seq datasets by integrating topological and temporal features. Conclusion Static gene–gene interactions have been extracted as temporal features to boost clustering performance in single-cell clustering For the scCompressSA method, dual-channel SA based CC block is able to integrate topological features and has exhibited extraordinary detection accuracy compared with previous clustering approaches that only employ temporal patterns.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1471-2164
1471-2164
DOI:10.1186/s12864-024-10286-2