基于非线性降维算法的膜蛋白类型识别  

Membrane Protein Types Prediction Based On Nonlinear Dimensionality Reduction Method

作　　者：王立鹏[1] 袁占亭[1] 陈旭辉[1] 周智芳[2] 

机构地区：[1]兰州理工大学电气工程与信息工程学院,兰州730050 [2]兰州理工大学石油化工学院,兰州730050

出　　处：《微计算机信息》2010年第10期20-21,43,共3页Control & Automation

摘　　要：众所周知,研究未知膜蛋白的类型可对基础研究和药物发现提供有用的线索。在后基因组时代,伴随着蛋白质序列数量的剧增,用实验方法确定膜蛋白类型太过昂贵和费时。因此,研究出一种能够自动发现可能的膜蛋白的计算方法变得很重要。鉴于这种情况,曾有人采用DC(Dipeptide Composition)方法表示蛋白质序列并取得了很好的预测结果。然而,采用这种表示方法得到的特征维数很高,冗余很大,使得预测系统十分复杂。为了解决这个问题,本文采用非线性降维算法KPCA(Kernel Principle component analysis),通过从高维的DC(Dipeptide Composition)特征空间中提取出低维的重要特征来简化该系统,采用K-NN(K-nearest neighbor)分类器从约简后的低维特征中预测膜蛋白类型。实验结果表明,使用KPCA方法预测膜蛋白类型非常有效。Knowing type of an uncharacterized membrane protein often provides a useful clue in both basic research and drug discovery.With the explosion of protein sequences generated in the post genomic era,determination of membrane proteins types by experimental methods is expensive and time consuming.It therefore becomes important to develop an automated method to find the possible type of membrane protein.In view of this,the DC （Dipeptide Composition） is introduced to represent the protein sample.However,a high dimensional disaster may be caused by using this representation method.Thus,a nonlinear dimensionality reduction algorithm KPCA （Kernel Principle component analysis） is introduced to extract the indispensable features from the high-dimensional DC space,respectively.Based on the reduced low-dimensional features,K-NN （K-nearest neighbor） classifier is introduced to identify the types of membrane proteins.Finally,experiment results show that using the proposed method to cope with prediction of membrane proteins types is very effective.

关 键 词：KPCA 膜蛋白 二肽组成 降维算法 生物信息学 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] Q734[自动化与计算机技术—控制科学与工程]