MoXGATE: Modality-aware cross-attention for multi-omic gastrointestinal cancer sub-type classification

2025-06-08

AI Summary

To address the challenges of high heterogeneity, difficult integration, and class imbalance in multi-omics data (genomic, epigenomic, transcriptomic) for gastrointestinal cancer subtype classification, this paper proposes a modality-aware weighted cross-attention fusion framework. The method employs learnable modality-specific weights to enable cross-omics feature alignment and dynamic interaction, incorporates focal loss to mitigate sample imbalance, and enhances model interpretability and cross-cancer generalizability. Evaluated on the TCGA gastrointestinal adenocarcinoma dataset, the framework achieves 95% classification accuracy—significantly outperforming state-of-the-art approaches. Ablation studies confirm the effectiveness of each component, and successful transfer to breast cancer subtype classification demonstrates its biological relevance and clinical translational potential.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Cancer subtype classification is crucial for personalized treatment and prognostic assessment. However, effectively integrating multi-omic data remains challenging due to the heterogeneous nature of genomic, epigenomic, and transcriptomic features. In this work, we propose Modality-Aware Cross-Attention MoXGATE, a novel deep-learning framework that leverages cross-attention and learnable modality weights to enhance feature fusion across multiple omics sources. Our approach effectively captures inter-modality dependencies, ensuring robust and interpretable integration. Through experiments on Gastrointestinal Adenocarcinoma (GIAC) and Breast Cancer (BRCA) datasets from TCGA, we demonstrate that MoXGATE outperforms existing methods, achieving 95% classification accuracy. Ablation studies validate the effectiveness of cross-attention over simple concatenation and highlight the importance of different omics modalities. Moreover, our model generalizes well to unseen cancer types e.g., breast cancer, underscoring its adaptability. Key contributions include (1) a cross-attention-based multi-omic integration framework, (2) modality-weighted fusion for enhanced interpretability, (3) application of focal loss to mitigate data imbalance, and (4) validation across multiple cancer subtypes. Our results indicate that MoXGATE is a promising approach for multi-omic cancer subtype classification, offering improved performance and biological generalizability.

Problem

• Classifying cancer subtypes using multi-omic data integration
• Overcoming heterogeneity in genomic, epigenomic, and transcriptomic features
• Enhancing interpretability and performance in cancer subtype classification

Innovation

• Modality-aware cross-attention for multi-omic fusion
• Learnable weights enhance interpretable integration
• Focal loss mitigates data imbalance effectively