Triad-LMF: A Hierarchical Low-Rank Multimodal Fusion Framework for Robust Cancer Subtype Classification Using Multi-Omics Data
Tan, X.; Chen, X.; Ren, Z.; Tian, R.; Jiang, M.; Yang, D.; Guo, X.
Show abstract
Cancer heterogeneity poses a major challenge for accurate molecular subtype classification. Conventional methods often fail to exploit complementary information across multiple omics modalities, leading to overfitting on high-dimensional data and limited representation of subtype heterogeneity. To address this, we propose Triad-LMF, a multiomics integration framework based on low-rank multimodal fusion to improve classification accuracy. Triad-LMF harmonizes heterogeneous omics data and integrates information through a two-stage hierarchical fusion strategy. Local Pairwise Fusion and Global Triadic Fusion are combined via the Two-Feature and Three-Way LMF modules, enabling a gradual transition from local modality interactions to global feature integration. Experimental results show that Triad-LMF consistently outperforms existing methods. UMAP visualization confirms enhanced subtype separability, and SHAP-based analysis highlights biologically meaningful features. Across independent datasets, Triad-LMF demonstrates strong generalization, offering a robust and interpretable framework for multiomics-driven cancer subtype classification.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- ConvNTC: Convolutional neural tensor completion for predicting the disease-related miRNA pairs and cell-related drug pairs 96%
- Species-Agnostic Transfer Learning for Cross-species Transcriptomics Data Integration without Gene Orthology 95%
- Gene Expression Prediction from Histology Images via Hypergraph Neural Networks 95%
Similar papers in this journal
- ISMI-VAE: A Deep Learning Model for Classifying Disease Cells Using Gene Expression and SNV Data 95%
- BenchXAI: Comprehensive Benchmarking of Post-hoc Explainable AI Methods on Multi-Modal Biomedical Data 94%
- Predicting Disease-gene Associations through Self-supervised Mutual Infomax Graph Convolution Network 94%
Similar papers in this journal
- iDRKAN: Interpretable miRNA-Disease Association Prediction Based on Dual-Graph Representation Learning and Kolmogorov-Arnold Network 94%
- Trans-Driver: a deep learning approach for cancer driver gene discovery with multi-omics data 94%
- Learning universal knowledge graph embedding for predicting biomedical pairwise interactions 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.