Domain-Domain Interaction Identification with a Feature Selection Approach
The protein-protein interactions (PPIs) are generally assumed to be mediated by domain-domain interactions (DDIs). Many computational methods have been proposed based on this assumption to predict DDIs from available data of PPIs. However, most of the existing methods are generative methods that consider only PPI data without taking into account non-PPIs. In this paper, we propose a novel discriminative method for predicting DDIs from both PPIs and non-PPIs, which improves the prediction reliability. In particular, the DDI identification is formalized as a feature selection problem, which is equivalent to the parsimonious principle and is able to predict both DDIs and PPIs in a systematic and accurate manner. The numerical results on benchmark dataset demonstrate that formulating DDI prediction as a feature selection problem can predict DDIs from PPIs in a reliable way, which in turn is able to verify and further predict PPIs based on inferred DDIs.
KeywordsDiscriminative approach domain-domain interaction feature selection protein-protein interaction
- 3.Zhao, X., Wang, Y., Chen, L., Aihara, K.: Protein domain annotation with integration of heterogeneous information sources. Proteins: Structure, Function, and Bioinformatics (in press, 2008)Google Scholar
- 7.Riley, R., Lee, C., Sabatti, C., Eisenberg, D.: Inferring protein domain interactions from databases of interacting proteins. Genome Biol. 6(10) (2005)Google Scholar
- 18.Stein, A., Russell, R., Aloy, P.: 3did: interacting protein domains of known three-dimensional structure. Nucl. Acids Res. 33(suppl.1), D413–417 (2005)Google Scholar