TF-DWGNet: A Directed Weighted Graph Neural Network with Tensor Fusion for Multi-Omics Cancer Subtype Classification

TL;DR

The paper addresses multi-omics cancer subtype classification by modeling heterogeneous data with directed weighted graphs and higher-order modality interactions. TF-DWGNet introduces a supervised tree-based graph construction per modality and a low-rank tensor fusion (CP decomposition) to capture unimodal, bimodal, and trimodal interactions in an end-to-end framework. It provides built-in interpretability via feature- and modality-level scores and demonstrates superior performance on BRCA, UCEC, and KIPAN compared with state-of-the-art baselines. The approach offers scalable, modality-flexible integration with meaningful biomarker insights to support precision oncology.

Abstract

Integration and analysis of multi-omics data provide valuable insights for improving cancer subtype classification. However, such data are inherently heterogeneous, high-dimensional, and exhibit complex intra- and inter-modality dependencies. Graph neural networks (GNNs) offer a principled framework for modeling these structures, but existing approaches often rely on prior knowledge or predefined similarity networks that produce undirected or unweighted graphs and fail to capture task-specific directionality and interaction strength. Interpretability at both the modality and feature levels also remains limited. To address these challenges, we propose TF-DWGNet, a novel Graph Neural Network framework that combines tree-based Directed Weighted graph construction with Tensor Fusion for multiclass cancer subtype classification. TF-DWGNet introduces two key innovations: (i) a supervised tree-based strategy that constructs directed, weighted graphs tailored to each omics modality, and (ii) a tensor fusion mechanism that captures unimodal, bimodal, and trimodal interactions using low-rank decomposition for computational efficiency. Experiments on three real-world cancer datasets demonstrate that TF-DWGNet consistently outperforms state-of-the-art baselines across multiple metrics and statistical tests. In addition, the model provides biologically meaningful insights through modality-level contribution scores and ranked feature importance. These results highlight that TF-DWGNet is an effective and interpretable solution for multi-omics integration in cancer research.

Figures (4)

• Figure 1: Overview of the TF-DWGNet framework, consisting of four key modules: (i) a XGBoost module for feature selection and supervised construction of directed weighted graphs within each omics modality; (ii) a GNN module that learns unimodal embeddings by jointly encoding graph topology and reduced feature matrices; (iii) a tensor fusion module that models unimodal, bimodal, and trimodal interactions, followed by low-rank CP decomposition; and (iv) a deep residual network for classification. All modules are trained on the training split only; validation and test sets use the learned graphs and parameters without information leakage. TF-DWGNet forms a fully supervised, end-to-end pipeline from raw multi-omics inputs to subtype predictions.
• Figure 2: Histograms of DNA methylation, mRNA, and miRNA feature values in the preprocessed BRCA, UCEC, and KIPAN datasets. All features are scaled to the range [0, 1]. The heterogeneous distributions across modalities and datasets highlight the distinct biological characteristics captured by each omics type.
• Figure 3: Performance comparison of TF-DWGNet and baseline models across 20 independent seeds on the BRCA dataset using violin plots. Each violin displays score distributions, individual values (dots), and medians (white diamonds). Results are shown for (A) Accuracy, (B) F1-weighted, and (C) F1-macro.
• Figure 4: Relative importance of different omics types (DNA methylation, mRNA, and miRNA) in TF-DWGNet's classification performance across BRCA, UCEC, and KIPAN. Each bar reflects the normalized contribution of an omics graph, automatically learned by the model.

Theorems & Definitions (3)

• definition 1: Rank-One Tensors
• definition 2: Tensor Rank
• proposition 1