A Computational Method Based on the Integration of Heterogeneous Networks for Predicting Disease-Gene Associations
2011

A New Method for Predicting Disease-Causing Genes

Sample size: 1126 publication 10 minutes Evidence: high

Author Information

Author(s): Guo Xingli, Gao Lin, Wei Chunshui, Yang Xiaofei, Zhao Yi, Dong Anguo

Primary Institution: Xidian University

Hypothesis

Can integrating heterogeneous networks improve the prediction of disease-causing genes?

Conclusion

The proposed method significantly outperforms existing methods in predicting disease-causing genes.

Supporting Evidence

  • The method ranked the correct gene as one of the top ten in 622 of 1,428 cases.
  • It was tested with 10-fold cross-validation on 1,126 diseases.
  • The method was applied to study breast cancer, Alzheimer disease, and diabetes mellitus type 2.

Takeaway

This study created a new way to find genes that cause diseases by looking at how diseases and genes are connected in networks.

Methodology

The method integrates disease similarity and protein-protein interaction networks to compute disease-gene association scores using an iterative algorithm.

Potential Biases

The method may be biased towards well-connected genes in the protein-protein interaction network.

Limitations

The method relies on protein-protein interaction data, which may have low coverage and high false positive rates.

Statistical Information

P-Value

0.0001

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1371/journal.pone.0024171

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication