Identifying Acetylation Protein by fusing its PseAAC and Functional Domain Annotation Running Title: Identifying Acetylation Protein

摘要

Acetylation is one of post-translational modification (PTM), which is a reaction, usually with acetic acid, that introduces an acetyl radical into an organic compound. To understand the mechanism of acetylation profoundly, it is necessary to identify acetylation protein correctly in biological systems. Although high throughput experimental studies using mass spectrometry have identified many acetylation sites, the vast majority of acetylation sites remain undiscovered, even in well studied systems. To reduce experiment cost and improve the effectiveness and efficiency of acetylation site identification, computational (in silico) methods have been introduced and developed based on informatics techniques. In fact, if there is an approach can predict whether a query protein may be acetylated or may not, it is no doubt a very meaningful and effective method for this issue. In this study, we developed a novel computational method for predicting acetylation proteins by extracting features from sequence conservation information via grey system model and KNN scores based on functional domain annotation (FDA) and subcellular localization information. Together with the detailed features analysis and application of Relief feature selection algorithm, the paper also showed the results of 5-fold cross-validation on three datasets. The achieved accuracies are all satisfactory, as the mean performance, the accuracy is 77.10%, the Matthew’s correlation coefficient is 0.5457, and the AUC value is 0.8389. These works might guide the related experimental validation and provide useful insights for studying the mechanisms of acetylation, and the proposed method is looking forward to give a powerful help for further studies of other PTM process. Furthermore, a user-friendly web-server for “iACetyP” has been established, and is accessible at http://www.jci-bioinfo.cn/iAcetyP.