Jump to main content
Jump to site search

Issue 9, 2013
Previous Article Next Article

ZincExplorer: an accurate hybrid method to improve the prediction of zinc-binding sites from protein sequences

Author affiliations

Abstract

As one of the most important trace elements within an organism, zinc has been shown to be involved in numerous biological processes and closely implicated in various diseases. The zinc ion is important for proteins to perform their functional roles. To provide in-depth functional annotation of zinc-binding proteins, an initial but crucial step is the accurate recognition of zinc-binding sites. Motivated by the biological importance of zinc, we propose a new method called ZincExplorer to predict zinc-binding sites from protein sequences. ZincExplorer is a hybrid method that can accurately predict zinc-binding sites from protein sequences. It integrates the outputs of three different types of predictors, namely, SVM-, cluster- and template-based predictors. Four types of zinc-binding amino acids CHEDs (i.e. CYS, HIS, ASP and GLU) could be predicted using ZincExplorer. It achieved a high AURPC (Area Under Recall–Precision Curve) of 0.851, and a precision of 85.6% (specificity = 98.4%, MCC = 0.747) at the 70.0% recall for the CHEDs on the 5-fold cross-validation test. When tested on an independent dataset containing 2023 zinc-binding CHEDs and 14 493 non-zinc-binding CHEDs, it achieved about 3–8% higher AURPC in comparison to two other sequence-based predictors. Moreover, ZincExplorer could also identify the interdependent relationships (IRs) of the predicted zinc-binding sites bound to the same zinc ion, which makes it a useful tool for providing in-depth zinc-binding site annotation.

Graphical abstract: ZincExplorer: an accurate hybrid method to improve the prediction of zinc-binding sites from protein sequences

Back to tab navigation

Supplementary files

Publication details

The article was received on 14 Mar 2013, accepted on 26 Jun 2013 and first published on 27 Jun 2013


Article type: Method
DOI: 10.1039/C3MB70100J
Citation: Mol. BioSyst., 2013,9, 2213-2222
  •   Request permissions

    ZincExplorer: an accurate hybrid method to improve the prediction of zinc-binding sites from protein sequences

    Z. Chen, Y. Wang, Y. Zhai, J. Song and Z. Zhang, Mol. BioSyst., 2013, 9, 2213
    DOI: 10.1039/C3MB70100J

Search articles by author

Spotlight

Advertisements