预测外膜蛋白的核最近邻算法(英文)

Predicting outer membrane proteins based on kernel nearest neighbor algorithm

外膜蛋白由于其位于细菌的表面,从而对于抗生素和疫苗开发具有重要的研究价值.如何准确地将外膜蛋白从球蛋白和内膜蛋白等中识别出来对于从基因组序列中确认外膜蛋白以及预测其二级、三级结构都是一项重要的研究任务.近年来人们已经提出了若干从蛋白质序列出发预测外膜蛋白的方法.本文利用1种新的核方法,即核最近邻算法,结合蛋白质序列的子序列分布预测外膜蛋白,并和支持向量机方法、传统的最近邻算法进行了比较.结果表明本文算法不亚于已有的预测方法,而且新算法更为简洁、容易实现.同时我们发现残基顺序在外膜蛋白预测中具有重要作用.

Outer membrane proteins （OMPs） are of primary research interest for antibiotic and vaccine drug design as they are on the surface of the bacteria. Discriminating outer membrane proteins from other folding types of globular and inner membrane proteins is an important task both for discriminating outer membrane proteins from genomic sequences and for the successful prediction of their secondary and tertiary structures. Recently, several methods have been proposed for discriminating OMPs from protein sequences. In this paper, we use kernel nearest neighbor algorithm, another ＇kernel approach＇, to identify OMPs based on subsequence distribution of protein sequences. We compare the proposed methods with SVM methods and traditional nearest neighbor algorithm .The results show that the new methods can compete with the previous methods. Furthermore, the new method is simple and easy to realize computationally. At the same time, it is observed that the residue order plays important roles on the classification of OMPs.