scGraphDap: Integrating Functional State Pseudo-Labels and Graph Structure Learning for Robust Cell Type Annotation in Tumor Microenvironments.

Abstract

The tumor microenvironment is a dynamic ecosystem where cellular interactions drive cancer progression. However, inferring cell-cell communication from non-spatial scRNA-seq data remains challenging due to incomplete ligand-receptor databases and noisy cell type annotations. Here, we propose scGraphDap, a graph neural network framework that integrates functional state pseudo-labels and graph structure learning to improve both cell type annotation and CCC inference. By leveraging pathway activity scores (e.g., angiogenesis, apoptosis) as pseudo-labels, scGraphDap optimizes cell-cell graphs to capture functional proximity beyond geometric similarity. Furthermore, a graph domain adaptation module aligns cell embeddings across patients, enhancing cross-individual generalization. Evaluated on 38,667 cells from 15 patients across three cancers, scGraphDap achieved an average accuracy of 82.82% . Statistical validation confirmed its ability to recover disease-specific gene interactions (e.g., STAT3-CD274 in breast invasive carcinoma) without prior knowledge.