AproPhos:基于AdaBoost方法的蛋白质磷酸化修饰预测系统

AproPhos:Protein Phosphorylation Prediction Based on AdaBoost

磷酸化是最重要的蛋白质翻译后修饰之一,随着蛋白质磷酸化修饰数据不断积累,利用已有数据进行蛋白质磷酸化修饰位点预测的条件日益成熟。利用修饰位点附近氨基酸性质取代氨基酸种类作为特征,对现有516种氨基酸性质做了详细分析和筛选,提出了采用AdaBoost方法进行特征选择和分类器训练的磷酸化修饰位点预测系统AproPhos,该系统在特异性高于已有预测系统(约2%)的基础上,大大提高了预测的灵敏度(约10%),使磷酸化位点预测方法用于提高磷酸化蛋白质质谱鉴定效率成为可能,并有发现磷酸化修饰位点氨基酸性质分布的潜力。

Protein phosphorylation is one of the most important post-translational modifications （PTMs）. With the recent increase in protein phosphorylated sites identified, in silico prediction of potential phosphorylation sites may facilitate the identification of phosphorylated protein. A new phosphorylated sites prediction method named AproPhos uses amino acid properties as features and applies AdaBoost to feature selection and classification. Different from other prediction methods with lower sensitivity, our method shows about 10% higher sensitivity as well as about 2% higher specificity. So it may enhance the efficiency of phosphorylated protein identification with tandem mass spectra.