Sadgae: doubly enhanced graph autoencoder with self-adaptive cell graph for single-cell RNA-Seq clustering

Xiang-Hui Liu Yanmei Hu Sheng-Lin Yang Jie Wei Xiangtao Li

Aug 2026 · International Journal of Data Science and Analysis · Vol 22 · 0 citations · 35 references

TL;DR

SaDGAE, an unsupervised deep graph autoencoder (GAE) framework that jointly models gene expression patterns and cell–cell relationships, achieves strong and competitive clustering performance, yielding biologically interpretable clusters and accurately recovering known marker gene patterns.

DOI Semantic Scholar

View source

Similar papers

Jul 2026

scDFVA: Single-Cell Deep Clustering by Fusing Variational Graph Attention Autoencoder and ZINB-Based Autoencoder

Experiments indicated that scDFVA outperformed several other competing methods, demonstrating that the method is beneficial in single-cell clustering.

Ge Zhang, Maohua Qin, Xuye Kou et al. · J. Comput. Biol. · 0 citations

Jul 2026

AGTformer: Synergistic global transformer and adaptive graph gating for Accurate scRNA-seq clustering.

Single-cell RNA sequencing (scRNA-seq) enables transcriptomic profiling at single-cell resolution, but accurate identification of cell subpopulations remains challenging because of the high dimensionality, sparsity, and dropout effects of scRNA-seq data. Existing deep learning-based clustering methods have shown promis...

Yuanyuan Dang, Wenqiang Liu, Hao Li et al. · Computational biology and ch... · 0 citations

Aug 2026

scLGGCL: Label-Guided Graph Contrastive Learning for Single-Cell Fusion Clustering.

The framework integrates three modules: dual-reconstruction to fuse attribute-structure information, contrastive learning under label guidance to extract semantic similarities, and deep embedding clustering to enable iterative optimization.

Wen-Jing Su, Baojuan Qin, Junliang Shang et al. · Interdisciplinary Sciences C... · 0 citations

GraphFusionNN: an AI-Driven Framework for Context-Aware Cell Type Prediction Using Graphs, Spatial Features, and Embeddings

Experiments demonstrate that the GraphFusionNN fusion strategy— integrating graph topology, spatial context, and external embeddings—significantly improves classification accuracy, macro-F1, and robustness compared to single-modality models.

Unknown authors · 0 citations

Open access Aug 2026

BatchRefiner: fast, significant improvement in batch integration of single-cell embeddings with ensemble refinement

This work introduces ensemble refinement for scRNA-seq and scATAC-seq embeddings, inspired by ensemble methods from statistical machine learning, and implements BatchRefiner, a fast post-processing tool to enhance batch integration.

Daniel E. Schäffer, Helen Kang, E. D. Aksu et al. · bioRxiv · 0 citations

Open access Aug 2026

Learning Discrete Cell and Niche Codes from Spatial Transcriptomics Using Dual Residual Vector Quantization

SQUINT is presented, a graph vector-quantized variational autoencoder that learns two disjoint codebooks per cell from a shared architecture that outperforms or is competitive with strong baselines on identification and achieves the most faithful cross-section integration.

Sebastian Birk, Arpit Merchant, Amirhossein Vahidi et al. · bioRxiv · 0 citations