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.

[1]  Xin Li,et al.  Protein classification with imbalanced data , 2007, Proteins.

[2]  Ralph Snyderman,et al.  Prospective health care: the second transformation of medicine , 2006, Genome Biology.

[3]  D. Eisenberg,et al.  Protein function in the post-genomic era , 2000, Nature.

[4]  Bernhard Schölkopf,et al.  Feature selection and transduction for prediction of molecular bioactivity for drug design , 2003, Bioinform..

[5]  Xing-Ming Zhao,et al.  Gene function prediction using labeled and unlabeled data , 2008, BMC Bioinformatics.

[6]  Teresa M. Przytycka,et al.  DOMINE: a database of protein domain interactions , 2007, Nucleic Acids Res..

[7]  Gary D Bader,et al.  Global Mapping of the Yeast Genetic Interaction Network , 2004, Science.

[8]  Robert D. Finn,et al.  iPfam: visualization of protein?Cprotein interactions in PDB at domain and amino acid resolutions , 2005, Bioinform..

[9]  Ioannis Xenarios,et al.  DIP: the Database of Interacting Proteins , 2000, Nucleic Acids Res..

[10]  Ting Chen,et al.  An integrated approach to the prediction of domain-domain interactions , 2006, BMC Bioinformatics.

[11]  Kazuyuki Aihara,et al.  Protein domain annotation with integration of heterogeneous information sources , 2008, Proteins.

[12]  Robert B. Russell,et al.  3did: interacting protein domains of known three-dimensional structure , 2004, Nucleic Acids Res..

[13]  Nianjun Liu,et al.  Inferring protein-protein interactions through high-throughput interaction data from diverse organisms , 2005, Bioinform..

[14]  Raja Jothi,et al.  Co-evolutionary analysis of domains in interacting proteins reveals insights into domain-domain interactions mediating protein-protein interactions. , 2006, Journal of molecular biology.

[15]  E. Sprinzak,et al.  Correlated sequence-signatures as markers of protein-protein interaction. , 2001, Journal of molecular biology.

[16]  Christopher J. Lee,et al.  Inferring protein domain interactions from databases of interacting proteins , 2005, Genome Biology.

[17]  Ziv Bar-Joseph,et al.  Evaluation of different biological data and computational classification methods for use in protein interaction prediction , 2006, Proteins.

[18]  K. Guimaraes,et al.  Predicting domain-domain interactions using a parsimony approach , 2006, Genome Biology.

[19]  Minghua Deng,et al.  Inferring Domain–Domain Interactions From Protein–Protein Interactions , 2002 .

[20]  Zohar Itzhaki,et al.  Evolutionary conservation of domain-domain interactions , 2006, Genome Biology.