An improved prediction of catalytic residues in enzyme structures - PubMed (original) (raw)
. 2008 May;21(5):295-302.
doi: 10.1093/protein/gzn003. Epub 2008 Feb 20.
Affiliations
- PMID: 18287176
- DOI: 10.1093/protein/gzn003
An improved prediction of catalytic residues in enzyme structures
Yu-Rong Tang et al. Protein Eng Des Sel. 2008 May.
Abstract
The protein databases contain a huge number of function unknown proteins, including many proteins with newly determined 3D structures resulted from the Structural Genomics Projects. To accelerate experiment-based assignment of function, de novo prediction of protein functional sites, like active sites in enzymes, becomes increasingly important. Here, we attempted to improve the prediction of catalytic residues in enzyme structures by seeking and refining different encodings (i.e. residue properties) as well as employing new machine learning algorithms. In particular, considering that catalytic residues can often reveal specific network centrality when representing enzyme structure as a residue contact network, the corresponding measurement (i.e. closeness centrality) was used as one of the most important encodings in our new predictor. Meanwhile, a genetic algorithm integrated neural network (GANN) was also employed. Thanks to the above strategies, our GANN predictor demonstrated a high accuracy of 91.2% in the prediction of catalytic residues based on balanced datasets (i.e. the 1:1 ratio of catalytic to non-catalytic residues). When the GANN method was optimally applied to real enzyme structures, 73.9% of the tested structures had the active site correctly located. Compared with two existing methods, the proposed GANN method also demonstrated a better performance.
Similar articles
- GANNPhos: a new phosphorylation site predictor based on a genetic algorithm integrated neural network.
Tang YR, Chen YZ, Canchaya CA, Zhang Z. Tang YR, et al. Protein Eng Des Sel. 2007 Aug;20(8):405-12. doi: 10.1093/protein/gzm035. Epub 2007 Jul 24. Protein Eng Des Sel. 2007. PMID: 17652129 - Identification of catalytic residues from protein structure using support vector machine with sequence and structural features.
Pugalenthi G, Kumar KK, Suganthan PN, Gangal R. Pugalenthi G, et al. Biochem Biophys Res Commun. 2008 Mar 14;367(3):630-4. doi: 10.1016/j.bbrc.2008.01.038. Epub 2008 Jan 17. Biochem Biophys Res Commun. 2008. PMID: 18206645 - Computed protonation properties: unique capabilities for protein functional site prediction.
Murga LF, Wei Y, Ondrechen MJ. Murga LF, et al. Genome Inform. 2007;19:107-18. Genome Inform. 2007. PMID: 18546509 - Understanding nature's catalytic toolkit.
Gutteridge A, Thornton JM. Gutteridge A, et al. Trends Biochem Sci. 2005 Nov;30(11):622-9. doi: 10.1016/j.tibs.2005.09.006. Epub 2005 Oct 7. Trends Biochem Sci. 2005. PMID: 16214343 Review. - Searching for functional sites in protein structures.
Jones S, Thornton JM. Jones S, et al. Curr Opin Chem Biol. 2004 Feb;8(1):3-7. doi: 10.1016/j.cbpa.2003.11.001. Curr Opin Chem Biol. 2004. PMID: 15036149 Review.
Cited by
- Enzyme function and evolution through the lens of bioinformatics.
Ribeiro AJM, Riziotis IG, Borkakoti N, Thornton JM. Ribeiro AJM, et al. Biochem J. 2023 Nov 29;480(22):1845-1863. doi: 10.1042/BCJ20220405. Biochem J. 2023. PMID: 37991346 Free PMC article. Review. - CSmetaPred: a consensus method for prediction of catalytic residues.
Choudhary P, Kumar S, Bachhawat AK, Pandit SB. Choudhary P, et al. BMC Bioinformatics. 2017 Dec 22;18(1):583. doi: 10.1186/s12859-017-1987-z. BMC Bioinformatics. 2017. PMID: 29273005 Free PMC article. - CRHunter: integrating multifaceted information to predict catalytic residues in enzymes.
Sun J, Wang J, Xiong D, Hu J, Liu R. Sun J, et al. Sci Rep. 2016 Sep 26;6:34044. doi: 10.1038/srep34044. Sci Rep. 2016. PMID: 27665935 Free PMC article. - Cutoff lensing: predicting catalytic sites in enzymes.
Aubailly S, Piazza F. Aubailly S, et al. Sci Rep. 2015 Oct 8;5:14874. doi: 10.1038/srep14874. Sci Rep. 2015. PMID: 26445900 Free PMC article.
Publication types
MeSH terms
Substances
LinkOut - more resources
Full Text Sources