Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
Integrating Multi-View Features via Deep Generalized Canonical Correlation Analysis for Single-Cell Clustering. |
| Συγγραφείς: |
Liu W; School of Mathematics and Physics, Wuhan Institute of Technology, Wuhan 430205, China., Zhang W; School of Mathematics and Physics, Wuhan Institute of Technology, Wuhan 430205, China., Zheng X; School of Mathematics and Physics, Wuhan Institute of Technology, Wuhan 430205, China., Li Y; School of Mathematics and Physics, Wuhan Institute of Technology, Wuhan 430205, China. |
| Πηγή: |
International journal of molecular sciences [Int J Mol Sci] 2026 Jun 27; Vol. 27 (13). Date of Electronic Publication: 2026 Jun 27. |
| Τύπος έκδοσης: |
Journal Article |
| Γλώσσα: |
English |
| Στοιχεία περιοδικού: |
Publisher: MDPI Country of Publication: Switzerland NLM ID: 101092791 Publication Model: Electronic Cited Medium: Internet ISSN: 1422-0067 (Electronic) Linking ISSN: 14220067 NLM ISO Abbreviation: Int J Mol Sci Subsets: MEDLINE |
| Imprint Name(s): |
Original Publication: Basel, Switzerland : MDPI, [2000- |
| Ιατρικοί όροι (MeSH): |
Single-Cell Analysis*/methods, Sequence Analysis, RNA/methods ; Clustering Algorithms ; Autoencoder ; Principal Component Analysis ; Cluster Analysis ; Humans ; Algorithms ; Single-Cell Gene Expression Analysis ; Animals |
| Περίληψη: |
Single-cell RNA sequencing data are characterized by high dimensionality, sparsity, and strong nonlinearity, hindering conventional single-view clustering methods from capturing linear and nonlinear feature subspaces simultaneously. Features from distinct dimensionality reduction approaches are inherently complementary: PCA (Principal Component Analysis) preserves global linear structures, UMAP (Uniform Manifold Approximation and Projection) maintains topology and local neighborhoods, and PHATE (Potential of Heat-diffusion for Affinity-based Trajectory Embedding) depicts gradual transitions in cell differentiation. To fuse these complementary sources, we adopt an inter-view correlation maximization paradigm. Canonical Correlation Analysis (CCA) integrates two views by maximizing projection correlation but is limited to pairwise scenarios. We extend it to Generalized Canonical Correlation Analysis (GCCA) for multi-view alignment and introduce a deep autoencoder to construct the DeepGCCA (Deep Generalized Canonical Correlation Analysis) framework. This method generates three views via PCA, UMAP, and PHATE, extracts nonlinear latent features with the autoencoder, projects multi-view representations into a unified subspace under weighted GCCA constraints, and performs K-means clustering. Experiments on the two simulated and three real single-cell datasets evaluated in this study show that DeepGCCA demonstrates competitive performance against all single-view baselines and performs favorably compared to several widely adopted methods. Moreover, downstream marker gene analysis supports the biological interpretability of the resulting clusters within these datasets. Within the scope of this benchmark, DeepGCCA provides a valuable reference for high-precision clustering of single-cell transcriptomic data, offering practical insights into multi-view integration and biological interpretability. |
| Grant Information: |
12401649 National Natural Science Foundation of China; 12426649 National Natural Science Foundation of China; 12571543 National Natural Science Foundation of China; 12001408 National Natural Science Foundation of China; 12161039 National Natural Science Foundation of China; 20224BAB201011 Jiangxi Provincial Department of Science and Technology; K2024045 Wuhan Institute of Technology |
| Contributed Indexing: |
Keywords: deep generalized canonical correlation analysis; multi-view clustering; single-cell RNA sequencing; subspace learning; unsupervised clustering |
| Entry Date(s): |
Date Created: 20260715 Date Completed: 20260715 Latest Revision: 20260726 |
| Update Code: |
20260726 |
| PubMed Central ID: |
PMC13361346 |
| DOI: |
10.3390/ijms27135819 |
| PMID: |
42450091 |
| Βάση Δεδομένων: |
MEDLINE |