Related Experiment Video
Updated: Aug 15, 2026
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
Published on: October 24, 2012
GCAN: A data feature learning method for scRNA-seq data
Jingyu Bai1, Li Xu1
1College of Computer Science and Technology, Harbin Engineering University, 145 Liaoyuan Street, Harbin, 150001, Heilongjiang, China.
Introduction:
Single-cell RNA sequencing (scRNA-seq) data exhibit extreme sparsity, technical noise, and 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 our 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.