Inferring Gene-Phenotype Associations via Global Protein Complex Network Propagation Disease Gene Prediction on Protein Complex Network
2011

Predicting Disease Genes Using Protein Complex Networks

publication Evidence: high

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)

10.1371/journal.pone.0021502

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication