GCAN: A data feature learning method for scRNA-seq data

Bai, Jingyu

doi:10.1016/j.compbiolchem.2026.109295

GCAN: A data feature learning method for scRNA-seq data

2026-08-01

0

PRE

AI

DOI：10.1016/j.compbiolchem.2026.109295

Original

Original request for help

Save

Abstract

En 中文

Introduction: Single-cell RNA sequencing (scRNA-seq) data exhibit extreme sparsity, technical noise, complex nonlinear structures that obstruct accurate biological interpretation. Current methods inadequately model intercellular relationships and suffer from feature selection instability. Purpose: (1) Automatically identify biologically relevant features in noisy scRNA-seq data,(2) Model multi scale cellular relationships for robust clustering,(3) Provide interpretable representations for mechanistic insights. Methodology: Adaptive HVG selection: Improved Random Forest to mitigate dropout artifacts. Hybrid graph autoencoder: Fusion of Graph Attention Networks (local interactions) and Graph Convolutional Networks (global neighborhoods). Biologically informed optimization: MMD regularization + Spearman-correlation feature filtering. Results: Evaluated across 17 scRNA-seq datasets: Showed better clustering performance than CellVGAE in experiments (Silhouette Coefficient and Davies-Bouldin Index),Selection of highly variable genes mitigated technical noise while enhancing biological signal retention. Conclusion: GCAN establishes a new paradigm for scRNA-seq analysis by unifying adaptive feature selection with context-aware relational modeling. Its architecture implements adaptive screening of biologically relevant features and enables accurate cell typing.

Keywords:

ScRNA-seq data

Variational auto-encoder

RandomForest

Graph Attention Network

GCAN: A data feature learning method for scRNA-seq data

Abstract

Journal

Organization

Cited Papers