论文部分内容阅读
目的:筛选肾癌特异相关蛋白质,建立用于肾癌诊断的分类树模型,为进一步临床应用奠定基础。方法:采集肾癌患者48例与正常人83例血清,用表面增强激光解吸/电离飞行时间质谱分别检测其蛋白表达谱,用BioMarker Wizard软件筛选出差异蛋白,再用BioMarker Patterns软件建立肾癌诊断最优分类树模型。结果:在48例肾癌患者、83例正常人血清中共检测出44个差异蛋白质峰,在质荷比从2 800到16 100的差异蛋白中有21个蛋白质相对含量差异有统计学意义(P<0.05),从中选出12个差异蛋白建立分类树模型,用于鉴别肾癌患者与正常人,该模型在学习模式下的诊断准确率、灵敏度和特异性分别为98.47%(129/131),97.91%(47/48),98.79%(82/83),在测试模式下这3项指标分别为87.02%(114/131),85.42%(41/48),87.95%(73/83)。结论:肾癌血清蛋白质指纹图谱诊断模型具有一定优越性,为肾癌早期诊断提供了新途径。
Objective: To screen specific proteins related to renal cancer and establish a classification tree model for the diagnosis of renal cell carcinoma, which lays the foundation for further clinical application. Methods: Serum samples were collected from 48 patients with renal cell carcinoma and 83 normal individuals. The protein profiles were detected by surface-enhanced laser desorption / ionization time-of-flight mass spectrometry. The differential proteins were screened by BioMarker Wizard software and BioMarker Patterns software was used to establish the diagnosis of renal cell carcinoma Optimal classification tree model. RESULTS: Forty-four differential protein peaks were detected in serum of 48 patients with renal cell carcinoma and 83 normal individuals. There was a significant difference in the relative content of 21 proteins in the protein with a mass-to-charge ratio of 2 800 to 16 100 (P <0.05). Twelve differential proteins were selected to establish a classification tree model for differentiating patients with renal cell carcinoma from normal subjects. The diagnostic accuracy, sensitivity and specificity of the model in learning mode were 98.47% (129/131) , 97.91% (47/48) and 98.79% (82/83), respectively. The three indicators were 87.02% (114/131), 85.42% (41/48) and 87.95% (73/83) . Conclusion: The diagnostic model of serum protein fingerprinting of kidney cancer has some advantages and provides a new way for the early diagnosis of renal cell carcinoma.