Graph Structure Learning for Tumor Microenvironment with Cell Type Annotation from non-spatial scRNA-seq data

TL;DR

This paper introduces a graph neural network model, scGSL, that improves cell type annotation and cell interaction analysis in tumor microenvironments from non-spatial scRNA-seq data, outperforming existing methods.

Contribution

The study presents a novel GNN-based approach, scGSL, for accurate cell type prediction and gene interaction identification in TME, addressing spatial and ligand-receptor data limitations.

Findings

Achieved 84.83% accuracy in cell type prediction

Robustly identified biologically meaningful gene interactions

Significant expression differences validated across cancers

Abstract

The exploration of cellular heterogeneity within the tumor microenvironment (TME) via single-cell RNA sequencing (scRNA-seq) is essential for understanding cancer progression and response to therapy. Current scRNA-seq approaches, however, lack spatial context and rely on incomplete datasets of ligand-receptor interactions (LRIs), limiting accurate cell type annotation and cell-cell communication (CCC) inference. This study addresses these challenges using a novel graph neural network (GNN) model that enhances cell type prediction and cell interaction analysis. Our study utilized a dataset consisting of 49,020 cells from 19 patients across three cancer types: Leukemia, Breast Invasive Carcinoma, and Colorectal Cancer. The proposed scGSL model demonstrated robust performance, achieving an average accuracy of 84.83%, precision of 86.23%, recall of 81.51%, and an F1 score of 80.92% across all datasets. These metrics represent a significant enhancement over existing methods, which typically exhibit lower performance metrics. Additionally, by reviewing existing literature on gene interactions within the TME, the scGSL model proves to robustly identify biologically meaningful gene interactions in an unsupervised manner, validated by significant expression differences in key gene pairs across various cancers. The source code and data used in this paper can be found in https://github.com/LiYuechao1998/scGSL.