中文摘要：

目的筛选并建立新疆维吾尔族。肾癌血清蛋白指纹图谱诊断模型。方法采用弱阳离子交换蛋白质芯片（CMl0蛋白芯片）及表面增强激光解析电离飞行时间质谱（SELDI—TOF—MS）技术对45例维吾尔族肾癌患者和45例正常对照者血清指纹图谱进行检测，结果用ZUCI一蛋白芯片数据分析系统软件包进行分析，通过支持向量机运算建立区分。肾癌蛋白指纹图谱诊断模型，留一法交叉验证作用评估模型，判别效果。结果两组血清中筛选出M／Z为4296、4305、5914、5935、6116、6887、8085、8142、8573共9个差异有统计学意义（P〈0．05）的标志蛋白，所建立的诊断模型诊断肾癌的灵敏性为100％（45／45），特异性为91％（41／45）。进一步用50例未知血清标本盲法测试该模型，双盲验证后的灵敏性和特异性分别为93％（28／30）和85％（17／20）。结论SELDI—TOF—MS结合支持向量机建立维吾尔族肾癌血清蛋白质指纹图谱模型具有较高的敏感性与特异性，值得进一步研究和应用。

英文摘要：

Objective To screen and build diagnostic model of Uygur＇s renal cancer in Xinjiang by surface-enhanced laser desorption/ionization time of flight mass spectrometry （ SELDI-TOF-MS）. Methods SELDI-TOF-MS and CMIO protein chip were used to detect the serum protein patterns of 45 cases of Uygur with renal cancer and 45 normal controls of Uygur. The data was analyzed and the diagnostic model was es- tablished by using ZUCI-protein chip data analyze system software package. The data of spectra were ana- lyzed by support vector machine （SVM） to establish a diagnostic model which was evaluated and validated by leave one cross validation. Results Nine protein markers were identified with the relative molecular weights of 4296, 4305, 5914, 5935, 6116, 6887, 8085, 8142, 8573. The differences of these protein markers between renal cancer patients and controls were statistically significant （ P 〈 0.05 ）. The detective model could differentiate renal cancer from healthy controls with the sensitivity of 100% （45/45）, and spe- cificity of 91% （41/45）. The sensitivity and specificity of double blind confirmation procedure were 93% （28/30） and 85% （17/20）, respectively. Conclusion The predictive models of Uygur＇s renal cancer in Xinjiang established by the differences of serum protein fingerprint could be a highly specific and sensitive diagnostic tool for renal cell carcinoma.