Search

Cox proportional hazard regression analysis on a comparison between Cluster 1 and other clusters as selected by cluster analysis of the methylation status of mucin genes MUC1, MUC2, and MUC4 in non-neoplastic regions (A) and neoplastic regions (B). Red solid line: Cluster 1, black dashed line: other clusters.

Cox proportional hazard regression analysis on a comparison between Cluster 1 and Cluster 2 selected by cluster analysis of mRNA expression levels of MUC1, MUC2, and MUC4 in non-neoplastic regions (A) and neoplastic regions (B). Red solid line: Cluster 1, black dashed line: Cluster 2.

Purpose:Pancreatic cancer remains a disease of high mortality despite advanced diagnostic techniques. Mucins (MUC) play crucial roles in carcinogenesis and tumor invasion in pancreatic cancers. MUC1 and MUC4 expression are related to the aggressive behavior of human neoplasms and a poor patient outcome. In contrast, MUC2 is a tumor suppressor, and we have previously reported that MUC2 is a favorable prognostic factor in pancreatic neoplasia. This study investigates whether the methylation status of three mucin genes from postoperative tissue specimens from patients with pancreatic neoplasms could serve as a predictive biomarker for outcome after surgery.Experimental Design:We evaluated the methylation status of MUC1, MUC2, and MUC4 promoter regions in pancreatic tissue samples from 191 patients with various pancreatic lesions using methylation-specific electrophoresis. Then, integrating these results and clinicopathologic features, we used support vector machine-, neural network-, and multinomial-based methods to develop a prognostic classifier.Results:Significant differences were identified between the positive- and negative-prediction classifiers of patients in 5-year overall survival (OS) in the cross-validation test. Multivariate analysis revealed that these prognostic classifiers were independent prognostic factors analyzed by not only neoplastic tissues but also nonneoplastic tissues. These classifiers had higher predictive accuracy for OS than tumor size, lymph node metastasis, distant metastasis, and age and can complement the prognostic value of the TNM staging system.Conclusions:Analysis of epigenetic changes in mucin genes may be of diagnostic utility and one of the prognostic predictors for patients with pancreatic ductal adenocarcinoma.

Difference in the expression level of mucins between Cluster 1 and other clusters selected by cluster analysis of the methylation status of mucin genes MUC1, MUC2, and MUC4. Expression levels show relative quantification (log10).

Univariate and multivariate analyses for overall survival (Cox proportional hazard model).

Prognosis prediction by machine learning classifier in the k-fold CV test. Cox proportional hazard regression analysis for the comparison between the positive and negative groups selected by each classifier. Red solid line: predicted high-risk group (positive), blue line: other groups (negative). (A) 3-fold cross-validation test. (B) 4-fold cross-validation test. The insets show p-value (p) and hazard ratio (HR) of each test.

Comparison of feature between training and test cohort.

Comparison of SVM predict ability among these kernels in LOOCV