Grupo de Investigación Clínica y Traslacional, Departamento de Biología Fundamental y Ciencias de la Salud, Instituto Universitario de Investigación en Ciencias de la Salud (IUNICS), Universitat de les Illes Balears, Palma de Mallorca, Spain.
Instituto de Investigación Sanitaria Illes Balears (IdISBa), Palma de Mallorca, Spain.
PLoS One. 2018 Aug 2;13(8):e0201793. doi: 10.1371/journal.pone.0201793. eCollection 2018.
Monoclonal gammopathy of undetermined significance (MGUS) is a plasma cell dyscrasia that can progress to malignant multiple myeloma (MM). Specific molecular biomarkers to classify the MGUS status and discriminate the initial asymptomatic phase of MM have not been identified. We examined the serum peptidome profile of MGUS patients and healthy volunteers using MALDI-TOF mass spectrometry and developed a predictive model for classifying serum samples. The predictive model was built using a support vector machine (SVM) supervised learning method tuned by applying a 20-fold cross-validation scheme. Predicting class labels in a blinded test set containing randomly selected MGUS and healthy control serum samples validated the model. The generalization performance of the predictive model was evaluated by a double cross-validation method that showed 88% average model accuracy, 89% average sensitivity and 86% average specificity. Our model, which classifies unknown serum samples as belonging to either MGUS patients or healthy individuals, can be applied to clinical diagnosis.
意义未明的单克隆丙种球蛋白血症（MGUS）是一种浆细胞异常增生，可进展为恶性多发性骨髓瘤（MM）。尚未确定特定的分子生物标志物来对 MGUS 状态进行分类，并区分 MM 的初始无症状阶段。我们使用 MALDI-TOF 质谱法检测了 MGUS 患者和健康志愿者的血清肽谱，并开发了一种用于分类血清样本的预测模型。该预测模型使用支持向量机（SVM）监督学习方法构建，通过应用 20 倍交叉验证方案进行调整。在包含随机选择的 MGUS 和健康对照血清样本的盲测集上预测类别标签验证了该模型。通过双重交叉验证方法评估了预测模型的泛化性能，该方法显示平均模型准确率为 88%，平均灵敏度为 89%，平均特异性为 86%。我们的模型可将未知血清样本分类为 MGUS 患者或健康个体，可应用于临床诊断。
