scGSDR: Harnessing Gene Semantics for Single-Cell Pharmacological Profiling

2025-02-02

AI Summary

To address inaccurate drug response prediction arising from tumor heterogeneity revealed by single-cell sequencing, this paper proposes scGSDR—a novel single-cell drug response prediction model. scGSDR is the first to integrate gene semantic embeddings derived from biological knowledge bases (GO and KEGG pathways) into single-cell drug response modeling. It introduces an interpretable cell–pathway attention module enabling both single-agent and combination therapy prediction, and adopts a dual-stream architecture that synergistically leverages graph neural networks and attention mechanisms to jointly model scRNA-seq and bulk RNA-seq data. Across 16 benchmark experiments covering 11 drugs, scGSDR achieves statistically significant improvements in AUROC, AUPR, and F1-score over state-of-the-art methods. Biologically, it successfully identifies known resistance-associated genes—including BCL2, PIK3CA, and NFKB1—demonstrating strong biological interpretability and mechanistic insight capability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Learning to Search
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

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

Abstract

The rise of single-cell sequencing technologies has revolutionized the exploration of drug resistance, revealing the crucial role of cellular heterogeneity in advancing precision medicine. By building computational models from existing single-cell drug response data, we can rapidly annotate cellular responses to drugs in subsequent trials. To this end, we developed scGSDR, a model that integrates two computational pipelines grounded in the knowledge of cellular states and gene signaling pathways, both essential for understanding biological gene semantics. scGSDR enhances predictive performance by incorporating gene semantics and employs an interpretability module to identify key pathways contributing to drug resistance phenotypes. Our extensive validation, which included 16 experiments covering 11 drugs, demonstrates scGSDR's superior predictive accuracy, when trained with either bulk-seq or scRNA-seq data, achieving high AUROC, AUPR, and F1 Scores. The model's application has extended from single-drug predictions to scenarios involving drug combinations. Leveraging pathways of known drug target genes, we found that scGSDR's cell-pathway attention scores are biologically interpretable, which helped us identify other potential drug-related genes. Literature review of top-ranking genes in our predictions such as BCL2, CCND1, the AKT family, and PIK3CA for PLX4720; and ICAM1, VCAM1, NFKB1, NFKBIA, and RAC1 for Paclitaxel confirmed their relevance. In conclusion, scGSDR, by incorporating gene semantics, enhances predictive modeling of cellular responses to diverse drugs, proving invaluable for scenarios involving both single drug and combination therapies and effectively identifying key resistance-related pathways, thus advancing precision medicine and targeted therapy development.

Problem

• Enhance predictive modeling of drug responses
• Identify key drug resistance pathways
• Advance precision medicine with gene semantics

Innovation

• Integrates gene semantics pathways
• Employs interpretability module identification
• Superior predictive accuracy demonstrated