Graph designs for deep learning-based multi-omics integration
Muhtasim Noor Alif1, Khandakar Tanvir Ahmed1, Sudipto Baul1
1Department of Computer Science, University of Central Florida, 4000 Central Florida Blvd., Orlando, FL 32816, United States.
Briefings in Bioinformatics
|July 31, 2026
Summary
Integrating multi-omics data is challenging. Graph-based deep learning offers a flexible framework for analyzing complex biological interactions and relationships, aiding in data interpretation and discovery.
Area of Science:
- Computational Biology
- Bioinformatics
- Systems Biology
Background:
- Modern sequencing enables multi-omic data generation from single biological systems.
- Integrating diverse omics data into a unified model presents significant challenges.
- Graph-based deep learning provides a flexible approach to model complex molecular interactions and sample relationships.
Purpose of the Study:
- To review graph construction and usage in multi-omics deep learning models.
- To organize and analyze different methodological approaches.
- To provide insights for developing new multi-omics studies.
Main Methods:
- Surveying graph construction and deep learning applications in multi-omics.
- Organizing methods by node schema, edge semantics, interaction type, integration strategy, graph context, and model architecture.
- Analyzing methods across bulk, single-cell, and spatial omics data.
Main Results:
- Summarizing strengths and weaknesses of various design choices.
- Evaluating methods based on interpretability, data needs, robustness, and task suitability.
- Identifying key considerations for prediction and mechanism-oriented discovery.
Conclusions:
- Graph-based deep learning is a powerful strategy for multi-omics integration.
- A practical pipeline for graph construction, curation, and evaluation is proposed.
- This framework serves as a foundation for future multi-omics research.
