基于Gabor滤波和Radon-Legendre矩的蛋白质结构域分类  

Structural Classification of Protein Domain Using Gabor Filter and Radon-Legendre Moment

作　　者：施建宇[1] 张艳宁[2] 

机构地区：[1]西北工业大学生命学院,西安710072 [2]西北工业大学计算机学院,西安710072

出　　处：《模式识别与人工智能》2013年第1期28-33,共6页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金(No.60872145);博士后科学基金(No.201104682)资助项目

摘　　要：提出一种有效的蛋白质结构域结构分类方法,将结构分类问题表示为图像分类问题.将蛋白质结构域的三维结构转换为距离矩阵,并视作灰度图像;从而将结构域的二级结构及拓扑结构,分别映射为此类图像中的不同尺度和方向的局部结构,以及由这些局部结构组成的形状.设计Gabor滤波器来分割这些局部结构,并构造描述二级结构组成的百分比特征.提出一种Radon-Legendre矩来描述形状,并构造描述形状的矩特征.对比实验表明,该方法在结构域分类的识别率和样本数目鲁棒性两个方面均优于其它方法,有效地实现结构域分类.Representing structural classification as image classification, an effective method of structural classification of protein domain is proposed. Firstly, the spatial structure of protein domain is mapped to its distance matrix which is regarded further as gray texture image. As a result, the secondary structure elements （SSE） and the topology of domain are transformed to local geometric structures with variant scales, orientations and the local-structure-composed shape in such image respectively. Then, Gabor filters are designed to segment these local structures out and extract the percentage feature which represents the composition of SSE. After that, Radon-Legendre moment is presented to characterize the local-structure-composed shape and is used as feature of the shape. Finally, the composition feature and the moment feature are combined to perform structural domain classification. The experimental results show that the proposed method achieves effective classification of protein domain and outperforms other methods in both classification accuracy and robustness of sample count.

关 键 词：GABOR滤波 RADON变换 Radon-Legendre矩 蛋白质结构分类 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]