MORE: a multi-omics data-driven hypergraph integration network for biomedical data classification and biomarker identification
2024

MORE: A New Method for Integrating Multi-Omics Data

publication Evidence: high

Author Information

Author(s): Wang Yuhan, Wang Zhikang, Yu Xuan, Wang Xiaoyu, Song Jiangning, Yu Dong-Jun, Ge Fang

Primary Institution: Nanjing University of Science and Technology

Hypothesis

The study proposes a novel approach for integrating multi-omics data to improve biomedical data classification and biomarker identification.

Conclusion

The MORE method outperformed existing multi-omics integration approaches and effectively identified disease-related biomarkers.

Supporting Evidence

  • MORE significantly outperformed existing multi-omics integration methods in three classification tasks.
  • MORE identified a greater variety of disease-related biomarkers compared to existing methods.
  • The model combining three types of omics data achieved the best classification performance.

Takeaway

The MORE method helps scientists combine different types of biological data to find important clues about diseases.

Methodology

The study used a multi-omics hypergraph integration approach that includes modules for encoding omics-specific features and integrating information across modalities.

Limitations

The method may struggle with modeling other data types, such as medical images and clinical reports.

Digital Object Identifier (DOI)

10.1093/bib/bbae658

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication