Enhanced Single-Cell RNA-seq Embedding through Gene Expression and Data-Driven Gene-Gene Interaction Integration

2025-09-01

AI Summary

High-dimensional sparsity and technical noise in single-cell RNA-seq (scRNA-seq) data impede accurate cell-state representation, while most existing embedding methods neglect gene regulatory interactions. To address this, we propose the Enhanced Cell–Leaf Graph (ECLG), the first method to jointly integrate a gene regulatory network—learned via random forest—with a K-nearest-neighbor cell similarity graph, forming a multi-source collaborative graph structure. ECLG then employs a graph neural network to jointly encode both gene expression profiles and regulatory interaction information. Evaluated on multiple benchmark datasets, ECLG consistently outperforms state-of-the-art tools—including Scanpy, Seurat, and scVI—across key tasks: rare cell-type identification, clustering accuracy, visualization separation, and pseudotemporal ordering inference. By explicitly modeling regulatory logic within a geometric deep learning framework, ECLG establishes a novel, interpretable, and robust paradigm for functional single-cell analysis.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Single-cell RNA sequencing (scRNA-seq) provides unprecedented insights into cellular heterogeneity, enabling detailed analysis of complex biological systems at single-cell resolution. However, the high dimensionality and technical noise inherent in scRNA-seq data pose significant analytical challenges. While current embedding methods focus primarily on gene expression levels, they often overlook crucial gene-gene interactions that govern cellular identity and function. To address this limitation, we present a novel embedding approach that integrates both gene expression profiles and data-driven gene-gene interactions. Our method first constructs a Cell-Leaf Graph (CLG) using random forest models to capture regulatory relationships between genes, while simultaneously building a K-Nearest Neighbor Graph (KNNG) to represent expression similarities between cells. These graphs are then combined into an Enriched Cell-Leaf Graph (ECLG), which serves as input for a graph neural network to compute cell embeddings. By incorporating both expression levels and gene-gene interactions, our approach provides a more comprehensive representation of cellular states. Extensive evaluation across multiple datasets demonstrates that our method enhances the detection of rare cell populations and improves downstream analyses such as visualization, clustering, and trajectory inference. This integrated approach represents a significant advance in single-cell data analysis, offering a more complete framework for understanding cellular diversity and dynamics.

Problem

• Integrating gene expression and interactions for scRNA-seq embedding
• Overcoming high dimensionality and noise in single-cell data
• Improving rare cell detection and downstream analysis accuracy

Innovation

• Integrates gene expression and data-driven gene-gene interactions
• Constructs Enriched Cell-Leaf Graph using random forest models
• Uses graph neural network for comprehensive cell embeddings