Using Similarity to Classify Ovarian Cancer Samples Based on SELDI-TOF MS Data Binaryzation
A novel classification method for diagnosis of ovarian cancer based on proteomic mass spectrometry data binaryzation are proposed, which analyze data under different threshold value. Five folds crossvalidation similarity classifier was used to establish the diagnostic pattern. Based on the International public ovarian cancer database data experiment indicated that this method could separate the ovarian cancer from the healthy samples with a sensitivity of 98％, a specificity of 95％ and a positive predictive value of 95.15％. The model also identified a list of significant m/z that could be useful for biomarker identification.
Proteomic mass spectrometry binaryzation similarity classification
Wenxue Hong Fengxiang Chang Fengling Chang Jialin Song
Biomedical Engineering department, Yanshan University,Qinhuangdao, 066004
国际会议
The International Colloquium on Onformation Fusion 2007(2007年国际信息融合研讨会)
西安
英文
331-334
2007-08-22（万方平台首次上网日期，不代表论文的发表时间）