摘要
蛋白质相互作用网络(Protein-Protein Interaction,PPI)聚类结果的评价方法的研究是检测PPI网络功能模块聚类结果正确与否的关键。介绍并分析了4种有代表性的PPI网络聚类的评价方法,即p-value、匹配统计量、基于准确率和查全率的综合评价以及基于层结构的hF-measure,在此基础上考虑了主错误划分类与该预测类的相似性,提出了新的罚分函数和新的Sf-measure评价方法。仿真结果表明了各评价方法的特点及Sf-measure评价方法的有效性及合理性。
The research in evaluating clustering results for PPI （Protein-Protein Interaction） network is the key to de- tect clustering results of function module in PPI network. The four typical methods evaluating clusters of PPI （protein- protein interaction） network were introduced and analyzed in this paper,which are p-value, matching statistics, f-meas- ure based on recall and precision and hF-measure based on hierarchical structure. Besides, considering the similarity be- tween the main error classification and the cluster predicted, a new penalty function and the new Sf-measure evaluation method were put forward lately. The simulation results show the features of various evaluation methods and the ration- ality and effectivity of Sf-measure method.
出处
《计算机科学》
CSCD
北大核心
2013年第12期254-258,共5页
Computer Science
基金
国家自然科学基金青年基金(61100164
61173190)
教育部留学回国人员科研启动基金(教外司留[2012]1707号)
陕西省2010年自然科学基础研究计划青年基金(2010JQ8034)资助
