HCMAF: Hierarchical Feature Aggregation and Cross-Modal Attention Fusion Framework for Multi-Omics Patient Classification
- 1 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (6) , 4932-4942
Abstract
The accumulation of large-scale multi-omics datasets has brought new opportunities for precise disease treatment. However, the inherent complexity of inter- and intra-omics relationships presents considerable obstacles to the precise integration of multi-omics data. Here, we propose a Hierarchical Feature Aggregation and Cross-Modal Attention Fusion (HCMAF) framework to integrate multi-omics data for patient classification and biomarker identification. Specifically, to capture both the specific information inherent in each omics data and complex cross-omics interactions, HCMAF incorporates three innovative modules. The hierarchical feature aggregation graph attention (HGAT) module captures intra-omics topological features through adaptive neighborhood aggregation. The cross-modal attention (CMA) module pinpoints inter-omics complementarity by modeling cross-omics dependencies. Finally, the confidence-driven multi-omics fusion (CMF) module dynamically integrates omics-specific predictions through learnable reliability weights. Comprehensive experiments on four public benchmark datasets show that HCMAF achieves better classification performance and consistently surpasses leading existing methods. Further component analysis confirms the crucial role of the HGAT, CMA and CMF modules in ensuring overall model effectiveness. HCMAF is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/DHUDBlab/HCMAF.Keywords
Funding Information
- National Natural Science Foundation of China (62172088)
- National Natural Science Foundation of China (62272290)
- National Natural Science Foundation of China (62402099)
- Shanghai Rising-Star Program (24YF2701500)
This publication has 40 references indexed in Scilit:
- CENPE is a diagnostic and prognostic biomarker for cervical cancerHeliyon, 2024
- Global and cross-modal feature aggregation for multi-omics data classification and application on drug response predictionInformation Fusion, 2023
- Using machine learning approaches for multi-omics data analysis: A reviewBiotechnology Advances, 2021
- Integration strategies of multi-omics data for machine learning analysisComputational and Structural Biotechnology Journal, 2021
- DeepOmix: A scalable and interpretable multi-omics deep learning framework and application in cancer survival analysisComputational and Structural Biotechnology Journal, 2021
- Apelin/APJ system: A novel promising target for neurodegenerative diseasesJournal of Cellular Physiology, 2019
- Deep Multimodal Fusion: A Hybrid ApproachInternational Journal of Computer Vision, 2017
- Better prediction by use of co‐data: adaptive group‐regularized ridge regressionStatistics in Medicine, 2015
- MiR-21 expression in the tumor cell compartment holds unfavorable prognostic value in gliomasJournal of Neuro-Oncology, 2012
- Support-vector networksMachine Learning, 1995