基于相似度图的凝胶图像间蛋白点特征分析  

Analysis of Protein Spot Characteristics Based on Similarity Map

作　　者：熊邦书[1] 张郝东 欧巧凤[1] 叶毅嘉 

机构地区：[1]南昌航空大学无损检测技术教育部重点实验室,江西南昌330063

出　　处：《中国医学影像学杂志》2015年第10期775-779,784,共6页Chinese Journal of Medical Imaging

基　　金：国家自然科学基金项目(61163047);江西省自然科学基金项目(20114BAB201036);江西省教育厅科技项目(GJJ14532);南昌航空大学江西省图像处理与模式识别重点实验室基金项目(TX201504005);江西省2013年度研究生创新专项资金项目(YC2013-S219)

摘　　要：针对现有凝胶图像间蛋白点匹配方法在选择特征时,没有直观和统一标准的问题,本文提出了基于相似度图的蛋白点特征分析方法。首先给出相似度图的定义和生成方法;其次利用相似度图法分析坐标相似度、形状上下文相似度和形态参数相似度等5种常用特征的特点及优劣;最后根据特征分析结果提出一种多特征综合利用的乘积法,相比均值法具有更好的匹配效果。为验证相似度图和多特征综合乘积法的有效性,开展了多种图源的凝胶图像蛋白点匹配实验,结果表明,相似度图能够直观、有效地反映蛋白点特征的匹配性能,对多特征的选择和综合利用具有很好的指导意义。There are no intuitive and unified standards for selecting features in existing protein gel image point matching method, for which an analysis method based on similarity map is proposed. Firstly, the definition and generation methods of similarity map were presented. Secondly, trait and merits of features such as coordinate similarity, shapecontext similarity and morphology similarity were analyzed using similarity map method. Finally, comprehensive utilization of multi-features named product-method which has a better effect than mean-method was proposed based on the results. Many experiments using different 2-DE gel images were carried out to prove the validity of similarity map and product-method. The results showed that similarity map could be used for intuitional, effective analysis of matching performance and to guide the selection and comprehensive utilization of multi-features.

关 键 词：凝胶电泳图像 蛋白点匹配 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]