应用血清蛋白质指纹图谱筛选类风湿关节炎的血清标志物

Identification of serum biomarkers for rheumatoid arthritis using protein fingerprint

目的用表面增强激光解吸电离飞行时间质谱(SELDI-TOF-MS)和蛋白质芯片技术检测类风湿关节炎(RA)患者血清蛋白质指纹图谱,探讨基于人工神经网络的蛋白质指纹图谱模型对RA血清诊断标志物的筛选。方法用H4蛋白芯片结合SELDI-TOF-MS测定了141例血清标本的蛋白质指纹图谱,其中RA 90例,系统性红斑狼疮(SLE)20例,健康志愿者31名。将筛选出的血清蛋白质指纹图谱作为输入,建立人工神经网络预测模型,用随机抽取的93例标本(RA 60例,SLE 13例,健康志愿者20名)作为训练组,进行训练与交叉验证,并用另外测试组48例(RA 30例,SLE 7例,健康志愿者11名)的血清标本盲法验证该模型,同时与抗环瓜氨酸肽(抗CCP)抗体检测结果进行比较。结果利用从训练组得出的基于人工神经网络的血清蛋白质指纹图谱模型,对测试组的48例未知血清进行预测,结果显示,对RA检测的敏感性为90%(27/30),特异性为90.9%(9/11),阳性率为90.2%(37/41),明显高于抗CCP抗体检测结果。结论血清蛋白质指纹图谱可有效筛选RA血清中特异性蛋白标志物,基于人工神经网络的血清蛋白质质谱模型较以往传统方法具有更高的敏感性和特异性。

Objective To identify serum biomarkers for rheumatoid arthritis （RA） by protein fingerprint pattern. Methods One hundred and forty-one serum samples of 90 RA patients, 20 systemic lupus erythematosus （SLE） patients, and 31 healthy individuals were randomly divided into training set （n=93, 60 RA patients, 13 SLE patients and 20 healthy individuals） and test set （n=48, 30 RA patients, 7 SLE patients and 11 healthy individuals）. They were detected by surface enhanced laser desorption/ionization-time of flight-mass spectrometry （SELDI-TOF-MS）. The protein fingerprint pattern obtained from SELDI-TOF was trained by a multi-layer artificial neural network （ANN） to establish a diagnostic model. Results The detective model obtained by ANN was used to detect the 48 unknown serum samples. The sensitivity and specificity for RA detection was 90% and 90.9% respectively. Conclusion In comparison with traditional methods, SELDI- TOF-MS could identify new serum biomarkers in RA. Combined with ANN, it provides high sensitivity and specificity for RA diagnosis.