doi: 10.1007/s10930-009-9192-1.
Improved prediction of protein binding sites from sequences using genetic algorithm
Affiliations
- PMID: 19629657
- DOI: 10.1007/s10930-009-9192-1
Item in Clipboard
Improved prediction of protein binding sites from sequences using genetic algorithm
Protein J.
2009 Aug.
Abstract
We undertook this project in response to the rapidly increasing number of protein structures with unknown functions in the Protein Data Bank. Here, we combined a genetic algorithm with a support vector machine to predict protein-protein binding sites. In an experiment on a testing dataset, we predicted the binding sites for 66% of our datasets, made up of 50 testing hetero-complexes. This classifier achieved greater sensitivity (60.17%), specificity (58.17%), accuracy (64.08%), and F-measure (54.79%), and a higher correlation coefficient (0.2502) than those of the support vector machine. This result can be used to guide biologists in designing specific experiments for protein analysis.
Similar articles
-
Improved prediction of protein-protein binding sites using a support vector machines approach.Bioinformatics. 2005 Apr 15;21(8):1487-94. doi: 10.1093/bioinformatics/bti242. Epub 2004 Dec 21. Bioinformatics. 2005. PMID: 15613384
-
An evolution based classifier for prediction of protein interfaces without using protein structures.Bioinformatics. 2005 May 15;21(10):2496-501. doi: 10.1093/bioinformatics/bti340. Epub 2005 Feb 22. Bioinformatics. 2005. PMID: 15728113
-
Prediction of protein binding sites in protein structures using hidden Markov support vector machine.BMC Bioinformatics. 2009 Nov 20;10:381. doi: 10.1186/1471-2105-10-381. BMC Bioinformatics. 2009. PMID: 19925685 Free PMC article.
-
Toward a "structural BLAST": using structural relationships to infer function.Protein Sci. 2013 Apr;22(4):359-66. doi: 10.1002/pro.2225. Epub 2013 Feb 21. Protein Sci. 2013. PMID: 23349097 Free PMC article. Review.
-
Weak protein complexes: challenging to study but essential for life.FEBS J. 2014 Apr;281(8):1948-9. doi: 10.1111/febs.12744. FEBS J. 2014. PMID: 24860873 Free PMC article. Review. No abstract available.
Cited by
-
A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites.Front Genet. 2021 Oct 26;12:752732. doi: 10.3389/fgene.2021.752732. eCollection 2021. Front Genet. 2021. PMID: 34764983 Free PMC article.
-
SCRIBER: accurate and partner type-specific prediction of protein-binding residues from proteins sequences.Bioinformatics. 2019 Jul 15;35(14):i343-i353. doi: 10.1093/bioinformatics/btz324. Bioinformatics. 2019. PMID: 31510679 Free PMC article.
-
Sequence-based identification of interface residues by an integrative profile combining hydrophobic and evolutionary information.BMC Bioinformatics. 2010 Jul 28;11:402. doi: 10.1186/1471-2105-11-402. BMC Bioinformatics. 2010. PMID: 20667087 Free PMC article.
References
Publication types
MeSH terms
Substances
LinkOut - more resources
Full Text Sources
