Title |
CRF-based models of protein surfaces improve protein-protein interaction site predictions
|
---|---|
Published in |
BMC Bioinformatics, August 2014
|
DOI | 10.1186/1471-2105-15-277 |
Pubmed ID | |
Authors |
Zhijie Dong, Keyu Wang, Truong Khanh Linh Dang, Mehmet Gültas, Marlon Welter, Torsten Wierschin, Mario Stanke, Stephan Waack |
Abstract |
The identification of protein-protein interaction sites is a computationally challenging task and importantfor understanding the biology of protein complexes. There is a rich literature in this field. A broadclass of approaches assign to each candidate residue a real-valued score that measures how likely it isthat the residue belongs to the interface. The prediction is obtained by thresholding this score.Some probabilistic models classify the residues on the basis of the posterior probabilities. In thispaper, we introduce pairwise conditional random fields (pCRFs) in which edges are not restrictedto the backbone as in the case of linear-chain CRFs utilized by Li et al. (2007). In fact, any 3Dneighborhoodrelation can be modeled. On grounds of a generalized Viterbi inference algorithm anda piecewise training process for pCRFs, we demonstrate how to utilize pCRFs to enhance a givenresidue-wise score-based protein-protein interface predictor on the surface of the protein under study.The features of the pCRF are solely based on the interface predictions scores of the predictor theperformance of which shall be improved. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
Norway | 1 | 50% |
Unknown | 1 | 50% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Scientists | 1 | 50% |
Members of the public | 1 | 50% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
United Kingdom | 2 | 7% |
Germany | 1 | 4% |
Unknown | 24 | 89% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 7 | 26% |
Researcher | 4 | 15% |
Student > Postgraduate | 3 | 11% |
Student > Bachelor | 3 | 11% |
Other | 2 | 7% |
Other | 4 | 15% |
Unknown | 4 | 15% |
Readers by discipline | Count | As % |
---|---|---|
Computer Science | 10 | 37% |
Agricultural and Biological Sciences | 4 | 15% |
Biochemistry, Genetics and Molecular Biology | 3 | 11% |
Arts and Humanities | 1 | 4% |
Mathematics | 1 | 4% |
Other | 2 | 7% |
Unknown | 6 | 22% |