Deep Learning Powered Single-cell Clustering Framework with Enhanced Accuracy and Stability

Overview

Journal Sci Rep

Date 2025 Feb 3

PMID 39900656

Authors

Yi Zhang

Xi Feng

Yin Wang

Kai Shi

Affiliations

Soon will be listed here.

Abstract

Single-cell RNA sequencing (scRNA-seq) has revolutionized the field of cellular diversity research. Unsupervised clustering, a key technique in this exploration, allows for the identification of distinct cell types within a population. Graph-based deep clustering methods have shown promise in preserving the structural relationships between cells (nodes) within the data. However, these methods often neglect the inherent distribution of nodes in the graph, leading to incomplete representations of cell populations. Additionally, conventional graph convolutional networks (GCNs) can suffer from oversmoothing, a phenomenon where the network loses the ability to differentiate between samples with similar expression profiles. To address these limitations, we proposed scG-cluster, an innovative deep structural clustering method. This method incorporates two key innovations: (1) Dual-topology adjacency graph: scG-cluster integrates information about node distribution into the traditional adjacency graph used by GCNs. This enriches the graph representation by capturing the spatial relationships between cells in addition to their pairwise similarities. (2) Dual-topology adaptive graph convolutional network (TAGCN): The framework employs a TAGCN architecture with residual concatenation. This network utilizes an attention mechanism to dynamically weight features within the graph, focusing on the most informative aspects for clustering. Additionally, residual connections are implemented to combat oversmoothing, ensuring the network retains the ability to distinguish between subtle differences in cell expression profiles. Furthermore, scG-cluster iteratively refines the clustering centers, leading to enhanced stability and accuracy in the final cluster assignments. Extensive evaluations on six diverse scRNA-seq datasets demonstrate that scG-cluster consistently outperforms existing state-of-the-art methods in terms of both clustering accuracy and scalability. Ablation studies are also conducted to validate the significant contributions of both the residual connections and the attention mechanism to the overall performance of the model. The source code for scG-cluster is publicly available at https://github.com/xixi-wq/scG-cluster .

References

Kharchenko P . The triumphs and limitations of computational methods for scRNA-seq. Nat Methods. 2021; 18(7):723-732. DOI: 10.1038/s41592-021-01171-x. View

Macosko E, Basu A, Satija R, Nemesh J, Shekhar K, Goldman M . Highly Parallel Genome-wide Expression Profiling of Individual Cells Using Nanoliter Droplets. Cell. 2015; 161(5):1202-1214. PMC: 4481139. DOI: 10.1016/j.cell.2015.05.002. View

Zeisel A, Munoz-Manchado A, Codeluppi S, Lonnerberg P, La Manno G, Jureus A . Brain structure. Cell types in the mouse cortex and hippocampus revealed by single-cell RNA-seq. Science. 2015; 347(6226):1138-42. DOI: 10.1126/science.aaa1934. View

Hu H, Li Z, Li X, Yu M, Pan X . ScCAEs: deep clustering of single-cell RNA-seq via convolutional autoencoder embedding and soft K-means. Brief Bioinform. 2021; 23(1). DOI: 10.1093/bib/bbab321. View

Zhang Y, Wang D, Peng M, Tang L, Ouyang J, Xiong F . Single-cell RNA sequencing in cancer research. J Exp Clin Cancer Res. 2021; 40(1):81. PMC: 7919320. DOI: 10.1186/s13046-021-01874-1. View

Datta S, Datta S . Evaluation of clustering algorithms for gene expression data. BMC Bioinformatics. 2007; 7 Suppl 4:S17. PMC: 1780133. DOI: 10.1186/1471-2105-7-S4-S17. View

Balzer M, Ma Z, Zhou J, Abedini A, Susztak K . How to Get Started with Single Cell RNA Sequencing Data Analysis. J Am Soc Nephrol. 2021; 32(6):1279-1292. PMC: 8259643. DOI: 10.1681/ASN.2020121742. View

Park S, Zhao H . Spectral clustering based on learning similarity matrix. Bioinformatics. 2018; 34(12):2069-2076. PMC: 6454479. DOI: 10.1093/bioinformatics/bty050. View

Liu Z, Liang Y, Wang G, Zhang T . scLEGA: an attention-based deep clustering method with a tendency for low expression of genes on single-cell RNA-seq data. Brief Bioinform. 2024; 25(5). PMC: 11281828. DOI: 10.1093/bib/bbae371. View

10.

Liu T, Jia C, Bi Y, Guo X, Zou Q, Li F . scDFN: enhancing single-cell RNA-seq clustering with deep fusion networks. Brief Bioinform. 2024; 25(6). PMC: 11456827. DOI: 10.1093/bib/bbae486. View

11.

Kiselev V, Andrews T, Hemberg M . Challenges in unsupervised clustering of single-cell RNA-seq data. Nat Rev Genet. 2019; 20(5):273-282. DOI: 10.1038/s41576-018-0088-9. View

12.

Wang J, Xia J, Wang H, Su Y, Zheng C . scDCCA: deep contrastive clustering for single-cell RNA-seq data based on auto-encoder network. Brief Bioinform. 2023; 24(1). DOI: 10.1093/bib/bbac625. View

13.

Luo Z, Xu C, Zhang Z, Jin W . A topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder. Sci Rep. 2021; 11(1):20028. PMC: 8501122. DOI: 10.1038/s41598-021-99003-7. View

14.

Zappia L, Phipson B, Oshlack A . Splatter: simulation of single-cell RNA sequencing data. Genome Biol. 2017; 18(1):174. PMC: 5596896. DOI: 10.1186/s13059-017-1305-0. View

15.

Wang J, Ma A, Chang Y, Gong J, Jiang Y, Qi R . scGNN is a novel graph neural network framework for single-cell RNA-Seq analyses. Nat Commun. 2021; 12(1):1882. PMC: 7994447. DOI: 10.1038/s41467-021-22197-x. View

16.

Santos A, Rocha G, de Andrade J . Occurrence of the potent mutagens 2- nitrobenzanthrone and 3-nitrobenzanthrone in fine airborne particles. Sci Rep. 2019; 9(1):1. PMC: 6327027. DOI: 10.1038/s41598-018-37186-2. View

16.

Zanoni I, Tan Y, Gioia M, Broggi A, Ruan J, Shi J . An endogenous caspase-11 ligand elicits interleukin-1 release from living dendritic cells. Science. 2016; 352(6290):1232-6. PMC: 5111085. DOI: 10.1126/science.aaf3036. View

17.

Chen L, Wang W, Zhai Y, Deng M . Deep soft -means clustering with self-training for single-cell RNA sequence data. NAR Genom Bioinform. 2021; 2(2):lqaa039. PMC: 7671315. DOI: 10.1093/nargab/lqaa039. View

18.

Wolf F, Angerer P, Theis F . SCANPY: large-scale single-cell gene expression data analysis. Genome Biol. 2018; 19(1):15. PMC: 5802054. DOI: 10.1186/s13059-017-1382-0. View

19.

Cao J, Packer J, Ramani V, Cusanovich D, Huynh C, Daza R . Comprehensive single-cell transcriptional profiling of a multicellular organism. Science. 2017; 357(6352):661-667. PMC: 5894354. DOI: 10.1126/science.aam8940. View