Prediction of lysine ubiquitination with mRMR feature selection and analysis

Abstract

Ubiquitination, one of the most important post-translational modifications of proteins, occurs when ubiquitin (a small 76-amino acid protein) is attached to lysine on a target protein. It often commits the labeled protein to degradation and plays important roles in regulating many cellular processes implicated in a variety of diseases. Since ubiquitination is rapid and reversible, it is time-consuming and labor-intensive to identify ubiquitination sites using conventional experimental approaches. To efficiently discover lysine-ubiquitination sites, a sequence-based predictor of ubiquitination site was developed based on nearest neighbor algorithm. We used the maximum relevance and minimum redundancy principle to identify the key features and the incremental feature selection procedure to optimize the prediction engine. PSSM conservation scores, amino acid factors and disorder scores of the surrounding sequence formed the optimized 456 features. The Mathew's correlation coefficient (MCC) of our ubiquitination site predictor achieved 0.142 by jackknife cross-validation test on a large benchmark dataset. In independent test, the MCC of our method was 0.139, higher than the existing ubiquitination site predictor UbiPred and UbPred. The MCCs of UbiPred and UbPred on the same test set were 0.135 and 0.117, respectively. Our analysis shows that the conservation of amino acids at and around lysine plays an important role in ubiquitination site prediction. What's more, disorder and ubiquitination have a strong relevance. These findings might provide useful insights for studying the mechanisms of ubiquitination and modulating the ubiquitination pathway, potentially leading to potential therapeutic strategies in the future.

Incorporating key position and amino acid residue features to identify general and species-specific Ubiquitin conjugation sites

“…In this work, it would be difficult to prove definitively that a particular lysine residue is not ubiquitylated under any conditions. However, almost all researchers (Cai et al, 2012;Chen et al, 2011;Lee et al, 2011;Radivojac et al, 2010) of ubiquitylation prediction use a strategy in which any lysine residue that is not marked by any ubiquitylation information on the same protein is a non-ubiquitylation site. In addition, Radivojac et al (2010) concluded that this strategy did not significantly influence the prediction performance for a model of yeast.…”

“…Recently, Cai et al (2012) presented a method based on multi-sequence features and the nearest neighbor algorithm. These computational methods can be divided into two categories: methods of ubiquitylation site prediction for single species and multispecies.…”

Crosstissue Coexpression Network of Aging

“…Minimum-Redundancy-Maximum-Relevance (mRMR) (Peng et al, 2005) is a widely used method for feature selection (Cai et al, 2011;Huang et al, 2010cHuang et al, , 2011bHuang et al, , 2011c. The mRMR program we used was downloaded from http:// penglab.janelia.org/proj/mRMR/.…”

Integrated Analysis of miRNA and Gene Networks on Cancer Expression Data

“…mRMR approach requires the features to be maximally dissimilar to each other in order to expand the representative power of the feature set. And it has been proved effective and frequently used to analyze the importance of different features [27,28]. However, most of expression datasets only have few samples with high dimensions of genes.…”