Related Experiment Video
Updated: Aug 13, 2026
DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
Published on: December 15, 2023
A Novel Cancer Driver Genes Identification Method Based on Self-Supervised Dual Masked Graph Autoencoder
Pi-Jing Wei1, Xinhao Guo1, Wenjun Li1
1The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Institute of Physical Science and Information Technology, Anhui University, 111 Jiulong Road, Hefei, 230601, China.
Identifying cancer driver genes is crucial for understanding cancer development. This study introduces SDMGAE, a novel self-supervised graph autoencoder method that accurately identifies cancer driver genes using protein-protein interaction networks without labeled data.
Area of Science:
- Genomics
- Bioinformatics
- Computational Biology
Background:
- Identifying cancer driver genes is essential for understanding cancer mechanisms and advancing research.
- High-throughput molecular technologies have spurred the development of cancer driver gene identification from multi-omics data.
- Accurate identification of cancer driver genes remains challenging due to the scarcity of labeled data.
Purpose of the Study:
- To present SDMGAE, a Self-supervised Dual Masked Graph AutoEncoder-based method for cancer driver gene identification.
- To leverage graph autoencoders and self-supervised learning for enhanced driver gene discovery.
- To address the challenge of limited labeled data in cancer driver gene identification.
Main Methods:
- SDMGAE integrates a self-supervised graph learning module and a driver gene prediction module.
- The self-supervised graph learning module masks nodes and edges in protein-protein interaction (PPI) networks to capture node and structural information.
- A graph autoencoder reconstructs the PPI network, followed by logistic regression on pre-trained graph neural network encoder embeddings for prediction.
Main Results:
- SDMGAE demonstrated improved performance in cancer driver gene detection across 10 cancer types.
- Benchmarking experiments confirmed the effectiveness of SDMGAE compared to existing state-of-the-art methods.
- The method successfully utilizes unlabeled PPI network data for driver gene identification.
Conclusions:
- SDMGAE offers a robust and effective approach for identifying cancer driver genes.
- The self-supervised dual masked graph autoencoder framework advances the field of computational cancer genomics.
- This method holds promise for accelerating cancer research by improving the accuracy of driver gene discovery.
