EUVIMEDOpdag EUVIMED
Crossref

MOFNet: a deep learning framework for multi-omics data fusion in cancer subtype classification

Guangji Zhang, Chunxiao Zhang, Pengpai Li, Duanchen Sun, Zhixia Yang, Zhi-Ping Liu

Molecular Omics · 2025

DOI: 10.1039/d5mo00221d ↗

At a glance

Journal article in Molecular Omics, 2025. Written by Guangji Zhang and 5 co-authors. Institution: Department of Biomedical Engineering, School of Control Science and Engineering, Shandong University, Jinan, Shandong 250061, China. zpliu@sdu.edu.cn. Major MEDLINE topics: Deep Learning, Neoplasms, Genomics, Computational Biology. Cited 8 times so far (Crossref); 47 references. Funded by: National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background: cancer exhibits high molecular and clinical heterogeneity, making accurate subtyping essential for personalized treatment. Traditional single-omics approaches often fail to capture this complexity. Multi-omics integration offers a more holistic understanding, but many existing methods either lack interpretability or fail to model cross-omics correlations effectively. Methods: we developed MOFNet, a novel supervised deep learning framework for multi-omics integration, incorporating a similarity graph pooling (SGO) module and a view correlation discovery network (VCDN). MOFNet processes omics data—including mRNA expression, DNA methylation, and miRNA expression—via omics-specific graph learning and cross-omics label space fusion. Three cancer types—breast cancer (BRCA), low-grade glioma (LGG), and stomach adenocarcinoma (STAD)—were analyzed using datasets from the cancer genome atlas (TCGA). Statistical evaluation was performed using accuracy, weighted F1 score, and macro F1 score across stratified training/testing splits.

Results

MOFNet achieved superior performance across all datasets. For BRCA, it obtained an accuracy of 85.17%, F1_weighted of 85.36%, and macro F1 of 80.93%, outperforming all baseline models by up to 18.25%. In LGG and STAD, MOFNet also showed robust gains, with maximum improvements of 23.72% and 21.56%, respectively. Omics ablation studies demonstrated enhanced performance with multi-omics integration. Functional enrichment analysis revealed that MOFNet-identified key features were involved in biologically relevant pathways such as cell cycle regulation, synaptic signaling, and ion transport.

Conclusions

MOFNet enables scalable and interpretable multi-omics data fusion for cancer subtype classification, significantly improving predictive accuracy while retaining only 25% of input features. The integration of SGO and VCDN modules offers both biological interpretability and computational efficiency. These results suggest MOFNet's promising application in precision oncology and biomarker discovery.

Subjects

MeSH terms (MEDLINE)

Deep LearningNeoplasmsGenomicsComputational BiologyHumansDNA MethylationFemaleBreast NeoplasmsGene Expression Regulation, NeoplasticMicroRNAsMultiomics

Substances

MicroRNAs

Authors and institutions

  • Department of Biomedical Engineering, School of Control Science and Engineering, Shandong University, Jinan, Shandong 250061, China. zpliu@sdu.edu.cn.
  • School of Bioengineering, Dalian University of Technology, Dalian, Liaoning 116024, China.
  • National Center for Applied Mathematics, Shandong University, Jinan, Shandong 250100, China. dcsun@sdu.edu.cn.
  • College of Mathematics and Systems Science, Xinjiang University, Ürümqi, Xinjiang 830046, China. yangzhx@xju.edu.cn.

Funding

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China

Cite

APA

Zhang, G., Zhang, C., Li, P., Sun, D., Yang, Z., & Liu, Z. P. (2025). MOFNet: a deep learning framework for multi-omics data fusion in cancer subtype classification. Molecular Omics. https://doi.org/10.1039/d5mo00221d

Vancouver

Zhang G, Zhang C, Li P, Sun D, Yang Z, Liu ZP. MOFNet: a deep learning framework for multi-omics data fusion in cancer subtype classification. Molecular Omics. 2025. doi:10.1039/d5mo00221d

BibTeX
@article{Zhang2025,
  author = {Zhang, Guangji and Zhang, Chunxiao and Li, Pengpai and Sun, Duanchen and Yang, Zhixia and Liu, Zhi-Ping},
  title = {MOFNet: a deep learning framework for multi-omics data fusion in cancer subtype classification},
  journal = {Molecular Omics},
  year = {2025},
  doi = {10.1039/d5mo00221d}
}
Start for free →