基于序列关联的蛋白质亚细胞定位识别

Recognition of Subcellular Localization of Proteins Using of Sequences Fusion

摘要: 对未知蛋白的功能注释是蛋白质组学的主要目标。一个关键的注释是蛋白质亚细胞定位的预测。应用基于序列关联的二次判别分析方法进行蛋白质亚细胞定位预测，对4个植物定位类型进行5-fold交叉检验。

Abstract: Functional annotation of unknown proteins is a major goal in proteomics. A key annotation is the prediction of a protein’s subcellular localization. We used the method of Increment of Diversity with Quad-ratic Discriminant analysis (IDQD) to predict subcellular localization of proteins which are recognized by the four plant categories and three non-plant and obtained accuracy 87.4(±0.5)% and 91.2(±0.2)%, respectively in 5-fold cross-validation test. Our result is better than comparable existing methods.