期刊论文

中文

激光生物学报

1007-7146

2009

18

1

121-127

10.3969/j.issn.1007-7146.2009.01.025

60773021:国家自然科学基金 60603054:国家自然科学基金

本校为其他机构

膜蛋白是生物膜功能的主要体现者,是细胞执行各种功能的物质基础,在细胞中发挥着至关重要的作用.分类预测未知类型的膜蛋白对于生物学相关研究具有指导性意义,是膜蛋白结构与功能研究领域的一项重要基础性工作.针对膜蛋白分类预测问题,利用k子串离散源的方法对膜蛋白序列进行特征提取,并融合最小离散增量方法和加权K近邻算法构建一种新型的膜蛋白分类预测模型,在自检验、Jackknife检验和独立测试集检验三种典型的检验方式下,预测准确率分别为99.95%、86.16%和98.36%.实验结果表明,k子串离散源方法能够有效提取膜蛋白序列的特征信息,与现有方法相比,该分类模型具有较高的分类预测成功率.

Membrane proteins is the main manifestation of biological membrane＇ s function. It plays a crucial role in cells and makes the material basis for cells to implement various functions. The prediction for the type of membrane protein is a crucial fundamental research in the field of the structure and function of membrane protein and will also provide guidance for the related research in biology. In order to predict the type of membrane protein, this paper uses the method of k-substring source of diversity to extract the feature of membrane prote...