Predicting Disease Genes Using Protein Complex Networks
Author Information
Author(s): Yang Peng, Li Xiaoli, Wu Min, Kwoh Chee-Keong, Ng See-Kiong
Primary Institution: Nanyang Technological University, Singapore
Hypothesis
Can a novel protein complex network improve the prediction of disease genes?
Conclusion
The RWPCN method outperforms traditional approaches in predicting disease genes by utilizing a protein complex network.
Supporting Evidence
- RWPCN was tested on predicting gene-phenotype associations using leave-one-out cross-validation.
- The method outperformed existing approaches in predicting disease genes.
- RWPCN was applied to predict novel disease genes for Breast Cancer and Diabetes.
Takeaway
This study shows that using a network of protein complexes can help scientists find genes that cause diseases more effectively.
Methodology
The study used a Random Walker algorithm on a protein complex network to predict disease genes based on known gene-phenotype associations.
Limitations
The performance of the RWPCN algorithm may be affected by the completeness of the protein complex data.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website