应用SELDI-TOF-MS技术初步建立结直肠癌分类树模型

Identification of colorectal cancer patients by serum protein profile using surfaceenhanced laser desorption/ionization time-of-flight mass spectrometry

目的:分析结直肠癌期患者血清蛋白质组变化,初步建立结直肠癌期分类树模型.方法:将335例血清样本(其中结直肠癌患者169例,健康人166例)随机分为训练组和测试组,将血清样本加至IMAC30-Cu2+蛋白芯片,利用SELDI-TOF-MS得到血清蛋白质谱,利用Biomarker Wizard软件进行蛋白峰值鉴定和聚类.利用Biomarker Pattern以训练组建立由1个差异蛋白组成的结直肠癌期分类树模型,以测试组进行独立样本的双盲验证.另外,应用电化学发光免疫测定法检测测试组血清样本CEA.结果:软件识别了59个质峰,其中由质荷比为5765的蛋白构成的分类树模型可以有效鉴别结直肠癌患者与正常人,灵敏度和特异度分别是98.81%及100.00%,经双盲验证其灵敏度,特异度及阳性预测值分别是97.65%,98.80%及98.81%.CEA的灵敏度及特异度低于SELDI分类树模型(P<0.05).结论:SELDI-TOF-MS检测得到的血清蛋白质组分类树模型可以准确的鉴别结直肠癌患者与正常人,对结直肠癌的筛查有重要的意义.

AIM： To establish a serum protein fingerprinting technique coupled with a pattern-matching algorithm to distinguish colorectal cancer from healthy individuals. METHODS： Serum samples were applied to metal affinity protein chips to generate mass spectra by surface-enhanced laser desorption/ionization time-of-flight mass spectrometry （SELDI-TOF- MS）. Protein peak identification and clustering were performed using the Biomarker Wizard software. Proteomic spectra of serum samples from 84 colorectal cancer patients and age- and sex-matched 83 healthy individuals were used as a training set and a classification tree with 1 distinct protein masses was generated by using Biomarker Pattern software. The validity of the classification tree was then challenged with a blind test set including another 85 colorectal cancer patients and 83 healthy individuals. We additionally determined carcinoembryonic antigen （CEA） in all the serum samples included in the blind test set using an electrochemiluminescent immunoassay. RESULTS： The software identified an average of 59 mass peaks/spectrum and 1 of the identified peaks at 5765 was used to construct the classification tree. The classification tree separated effectively colorectal cancer from healthy individuals, with a sensitivity of 98.81% and a specificity of 100.00%. The blind test challenged the model with a sensitivity of 97.65% and a specificity of 98.80%, and a positive predictive value of 98.81%, respectively. The specificity and sensitivity provided by CEA were significantly lower than that of the SELDI marker pattern （P 〈 0.05）. CONCLUSION： SELDI-TOF-MS technique can correctly distinguish colorectal cancer patients from healthy individuals and shows great potential for the development of a screening test for the detection of colorectal cancer.