Jump to main content
Jump to site search

Issue 3, 2015
Previous Article Next Article

PredHydroxy: computational prediction of protein hydroxylation site locations based on the primary structure

Author affiliations

Abstract

Compared to well-known and extensively studied protein phosphorylation, protein hydroxylation attracts much less attention and the molecular mechanism of the hydroxylation is still incompletely understood. And yet annotation of hydroxylation in proteomes is a first-critical step toward decoding protein function and understanding their physiological roles that have been implicated in the pathological processes and providing useful information for the drug designs of various diseases related with hydroxylation. In this work, we present a novel method called PredHydroxy to automate the prediction of the proline and lysine hydroxylation sites based on position weight amino acids composition, 8 high-quality amino acid indices and support vector machines. The PredHydroxy achieved a promising performance with an area under the receiver operating characteristic curve (AUC) of 82.72% and a Matthew's correlation coefficient (MCC) of 69.03% for hydroxyproline as well as an AUC of 87.41% and a MCC of 66.68% for hydroxylysine in jackknife cross-validation. The results obtained from both the cross validation and independent tests suggest that the PredHydroxy might be a powerful and complementary tool for further experimental investigation of protein hydroxylation. Feature analyses demonstrate that hydroxylation and non-hydroxylation have distinct location-specific differences; alpha and turn propensity is of importance for the hydroxylation of proline and lysine residues. A user-friendly server is freely available on the web at: http://bioinfo.ncu.edu.cn/PredHydroxy.aspx.

Graphical abstract: PredHydroxy: computational prediction of protein hydroxylation site locations based on the primary structure

Back to tab navigation

Supplementary files

Publication details

The article was received on 01 Nov 2014, accepted on 15 Dec 2014 and first published on 15 Dec 2014


Article type: Paper
DOI: 10.1039/C4MB00646A
Citation: Mol. BioSyst., 2015,11, 819-825
  •   Request permissions

    PredHydroxy: computational prediction of protein hydroxylation site locations based on the primary structure

    S. Shi, X. Chen, H. Xu and J. Qiu, Mol. BioSyst., 2015, 11, 819
    DOI: 10.1039/C4MB00646A

Search articles by author

Spotlight

Advertisements