Improved Species-Specific Lysine Acetylation Site Prediction Based on a Large Variety of Features Set.
Improved Species-Specific Lysine Acetylation Site Prediction Based on a Large Variety of Features Set.
复制标题
DOI：
10.1371/journal.pone.0155370
复制
发表时间：
2016
期刊：
影响因子：
3.7
通讯作者：
Hu G
中科院分区：
文献类型：
--
作者：
Wuyun Q;Zheng W;Zhang Y;Ruan J;Hu G
赖氨酸乙酰化是一个主要的翻译后修饰。它在许多重要的生物过程中起着至关重要的作用，如基因表达和代谢，并与一些人类疾病有关。为了充分了解乙酰化的调控机制，乙酰化位点的鉴定是首先也是最重要的。然而，蛋白质乙酰化位点的实验鉴定通常既耗时又昂贵。因此，替代计算方法是必要的。在这里，我们开发了一种新的工具，KA-predictor，基于支持向量机（SVM）分类器来预测物种特异性赖氨酸乙酰化位点。我们结合了不同类型的特征，并对每种类型的特征进行了有效的特征选择，形成了模型学习的最终最优特征集。与其他方法相比，我们的预测器对大多数物种具有很强的竞争力。特征贡献分析表明，HSE特征首次被引入赖氨酸乙酰化预测，显著提高了预测性能。特别地，我们从PDB中构建了一个高精度的智人结构数据集，以分析赖氨酸乙酰化位点周围的结构特性。我们的数据集和一个用户友好的KA-predictor本地工具可以在http://sourceforge.net/p/ka-predictor上免费获得。
Lysine acetylation is a major post-translational modification. It plays a vital role in numerous essential biological processes, such as gene expression and metabolism, and is related to some human diseases. To fully understand the regulatory mechanism of acetylation, identification of acetylation sites is first and most important. However, experimental identification of protein acetylation sites is often time consuming and expensive. Therefore, the alternative computational methods are necessary. Here, we developed a novel tool, KA-predictor, to predict species-specific lysine acetylation sites based on support vector machine (SVM) classifier. We incorporated different types of features and employed an efficient feature selection on each type to form the final optimal feature set for model learning. And our predictor was highly competitive for the majority of species when compared with other methods. Feature contribution analysis indicated that HSE features, which were firstly introduced for lysine acetylation prediction, significantly improved the predictive performance. Particularly, we constructed a high-accurate structure dataset of H.sapiens from PDB to analyze the structural properties around lysine acetylation sites. Our datasets and a user-friendly local tool of KA-predictor can be freely available at http://sourceforge.net/p/ka-predictor.