Learning to predict protein-protein interactions from protein sequences
- PMID: 14555619
- DOI: 10.1093/bioinformatics/btg352
Learning to predict protein-protein interactions from protein sequences
Abstract
In order to understand the molecular machinery of the cell, we need to know about the multitude of protein-protein interactions that allow the cell to function. High-throughput technologies provide some data about these interactions, but so far that data is fairly noisy. Therefore, computational techniques for predicting protein-protein interactions could be of significant value. One approach to predicting interactions in silico is to produce from first principles a detailed model of a candidate interaction. We take an alternative approach, employing a relatively simple model that learns dynamically from a large collection of data. In this work, we describe an attraction-repulsion model, in which the interaction between a pair of proteins is represented as the sum of attractive and repulsive forces associated with small, domain- or motif-sized features along the length of each protein. The model is discriminative, learning simultaneously from known interactions and from pairs of proteins that are known (or suspected) not to interact. The model is efficient to compute and scales well to very large collections of data. In a cross-validated comparison using known yeast interactions, the attraction-repulsion method performs better than several competing techniques.
Similar articles
-
Predicting disulfide connectivity from protein sequence using multiple sequence feature vectors and secondary structure.Bioinformatics. 2007 Dec 1;23(23):3147-54. doi: 10.1093/bioinformatics/btm505. Epub 2007 Oct 17. Bioinformatics. 2007. PMID: 17942444
-
An integrated approach to the prediction of domain-domain interactions.BMC Bioinformatics. 2006 May 25;7:269. doi: 10.1186/1471-2105-7-269. BMC Bioinformatics. 2006. PMID: 16725050 Free PMC article.
-
Structure-templated predictions of novel protein interactions from sequence information.PLoS Comput Biol. 2007 Sep;3(9):1783-9. doi: 10.1371/journal.pcbi.0030182. PLoS Comput Biol. 2007. PMID: 17892321 Free PMC article.
-
Predicting protein function from sequence and structural data.Curr Opin Struct Biol. 2005 Jun;15(3):275-84. doi: 10.1016/j.sbi.2005.04.003. Curr Opin Struct Biol. 2005. PMID: 15963890 Review.
-
Deciphering protein-protein interactions. Part II. Computational methods to predict protein and domain interaction partners.PLoS Comput Biol. 2007 Apr 27;3(4):e43. doi: 10.1371/journal.pcbi.0030043. PLoS Comput Biol. 2007. PMID: 17465672 Free PMC article. Review.
Cited by
-
Protein-protein interaction sites prediction by ensemble random forests with synthetic minority oversampling technique.Bioinformatics. 2019 Jul 15;35(14):2395-2402. doi: 10.1093/bioinformatics/bty995. Bioinformatics. 2019. PMID: 30520961 Free PMC article.
-
Phylogeny-guided interaction mapping in seven eukaryotes.BMC Bioinformatics. 2009 Nov 30;10:393. doi: 10.1186/1471-2105-10-393. BMC Bioinformatics. 2009. PMID: 19948065 Free PMC article.
-
PPCM: Combing Multiple Classifiers to Improve Protein-Protein Interaction Prediction.Int J Genomics. 2015;2015:608042. doi: 10.1155/2015/608042. Epub 2015 Oct 11. Int J Genomics. 2015. PMID: 26539460 Free PMC article.
-
Improved cytokine-receptor interaction prediction by exploiting the negative sample space.BMC Bioinformatics. 2020 Oct 31;21(1):493. doi: 10.1186/s12859-020-03835-5. BMC Bioinformatics. 2020. PMID: 33129275 Free PMC article.
-
Prediction of protein-protein interaction with pairwise kernel support vector machine.Int J Mol Sci. 2014 Feb 21;15(2):3220-33. doi: 10.3390/ijms15023220. Int J Mol Sci. 2014. PMID: 24566145 Free PMC article.
Publication types
MeSH terms
Substances
Grants and funding
LinkOut - more resources
Full Text Sources
Other Literature Sources
