Cancer subtype classification is crucial for personalized treatment and prognostic assessment. However, effectively integrating multi-omic data remains a challenge 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 extensive experiments on Gastrointestinal Adenocarcinoma (GIAC) and Breast Cancer (BRCA) datasets from TCGA, we demonstrate that MoXGATE outperforms existing methods, achieving state-of-the-art classification accuracy. Ablation studies validate the significance of cross-attention over simple concatenation and highlight the importance of different omics modalities. Moreover, our model generalizes well to unseen cancer types, 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 MoXCA is a promising approach for multi-omic cancer subtype classification, offering both improved accuracy and biological interpretability.