Graph Transformer-Based Pathway Embedding for Cancer Prognosis

2026-04-17

AI Summary

Existing pathway representation methods struggle to learn shared latent representations of genes, limiting both the expressiveness and biological fidelity of cancer prognosis prediction. This work proposes PATH, a novel approach that introduces, for the first time, a patient-conditioned modulation mechanism to dynamically generate personalized gene embeddings by integrating copy number variation and mutation signals while preserving the stable biological identity of genes. Furthermore, PATH incorporates a pathway-guided graph Transformer to model inter-pathway interactions. Evaluated on pan-cancer metastasis prediction, PATH achieves an F1 score of 0.8766, representing an 8.8% improvement over the current state-of-the-art multi-omics methods, and uncovers disease-state-specific pathway rewiring patterns along with key regulatory pathways.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Machine Learning: Graph-based Machine Learning
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Accurate prediction of cancer progression remains a challenge due to the high heterogeneity of molecular omics data across patients. While biologically informed models have improved the interpretability of these predictions, a persistent limitation lies in how they encode individual genes to construct pathway representations. Existing hierarchical models typically derive gene features by directly mapping raw molecular inputs, whereas integration frameworks often rely on simple statistical aggregations of patient-level signals. These approaches often fail to explicitly learn a shared base representation for each gene, thereby limiting the expressiveness and biological accuracy of downstream pathway embeddings. To address this, we introduce PATH, a modulation-based, patient-conditioned gene embedding strategy. PATH represents a paradigm shift by starting from a shared base embedding for each gene, preserving a stable biological identity across the population, and then dynamically adapting it using patient-specific copy number variation (CNV) and mutation signals. This allows the model to capture subtle individual molecular variations while maintaining a consistent latent understanding of the gene itself. We integrate PATH into a graph transformer framework that models interactions among biologically connected pathways through pathway-guided attention. Across pancancer metastasis prediction, PATH achieves an F1 score of 0.8766, representing an 8.8 percent improvement over the current SOTA multi-omics benchmarks. Beyond superior predictive accuracy, our approach identifies biologically meaningful pathways and, crucially, reveals disease-state-specific pathway rewiring, offering new insights into the evolving pathway-pathway interactions that drive cancer progression.

Problem

• pathway embedding
• gene representation
• cancer prognosis
• molecular heterogeneity
• biological interpretability

Innovation

• Pathway Embedding
• Graph Transformer
• Patient-Conditioned Modulation
• Gene Representation
• Multi-omics Integration