Genomewide Expression Profiling Identifies a Novel miRNA-based Signature for the Detection of Peritoneal Metastasis in Patients With Gastric Cancer

Abstract

Objective: This study aimed to conduct a genomewide transcriptomic profiling to develop a microRNA (miRNA)-based signature for the identification of peritoneal metastasis (PM) in patients with gastric cancer (GC).

Summary background data: Even though PM in patients with GC has long been recognized to associate with poor prognosis, currently there is lack of availability of molecular biomarkers for its robust diagnosis.

Methods: We performed a systematic biomarker discovery by analyzing miRNA expression profiles in primary tumors from GC patients with and without PM, and subsequently validated the expression of candidate miRNA biomarkers in 3 independent clinical cohorts of 354 patients with advanced GC.

Results: Five miRNAs (miR-30a-5p, -134-5p, -337-3p, -659-3p, and -3917) were identified during the initial discovery phase; three of which (miR-30a-5p, -659-3p, and -3917) were significantly overexpressed in the primary tumors from PM-positive patients in the testing cohort (P = 0.002, 0.04, and 0.007, respectively), and distinguished patients with versus without peritoneal metastasis with the value of area under the curve (AUC) of 0.82. Furthermore, high expression of these miRNAs also associated with poor prognosis (hazard ratio = 2.18, P = 0.04). The efficacy of the combination miRNA signature was subsequently validated in an independent validation cohort (AUC = 0.74). Finally, our miRNA signature when combined together with the macroscopic Borrmann's type score offered a much superior diagnostic in all 3 cohorts (AUC = 0.87, 0.76, and 0.79, respectively).

Conclusions: We have established an miRNA-based signature that have a potential to identify peritoneal metastasis in GC patients.

Figure 1:. Identification of candidate miRNAs in primary tumors from gastric cancer patients with peritoneal metastasis.

(A) Schematic of the study design for biomarker discovery and validation in various patient cohorts. (B) Heatmap illustrating differentially expressed miRNAs between peritoneal metastasis positive and negative samples identified from the miRNA-microarray dataset. (C) Differentially expressed candidate miRNAs between stage IV and stage IB-III GC patients in the TCGA dataset. Abbreviations; PM, peritoneal metastasis. *p<0.05, by Mann-Whitney U test.

Figure 2:. Candidate miRNAs were differentially expressed in peritoneal metastasis positive patients in the testing cohort.

(A) Detection potential of miRNA candidates represented by receiver operating characteristic (ROC) curves. (B) The waterfall plot representing risk score of PM positive and negative patients based on the combined miRNAs signature. (C) ROC curve of the combined miRNA signature for the detection of PM. Abbreviations; Sen, sensitivity; Spe, specificity. (D) Kaplan-Meier analysis for overall survival (OS) between two groups dichotomized by Youden’s index for PM in individual overexpressing miRNAs.

Figure 3:. Diagnostic potentialof peritoneal metastasis detection and prognostic significance of combined miRNA signature in validation cohort and performance evaluation cohort.

The box plot representing risk scores of PM positive and negative patients in the validation (A), and the performance evaluation cohort (D). ROC curves for the detection of PM in validation (B), and performance evaluation cohort (E). Kaplan-Meier analysis for OS between two groups dichotomized by Youden’s index for PM based on the combined miRNA signature in validation cohort (C), and the performance evaluation cohort (F). Abbreviations; PM, peritoneal metastasis; Sen, sensitivity; Spe, specificity. **p< 0.01, ***p< 0.01 by Mann-Whitney U test.

Figure 4:. Diagnostic accuracy of peritoneal metastasis detection of combined miRNA signature and tumor macroscopic type in each clinical cohort.

ROC curves derived from the combination miRNA signature, tumor macroscopic type, and their combination for detection of PM in the testing (A), validation (B), and performance evaluation cohort (C). Nomogram and their predicted probability plots in the performance evaluation cohort (Figure D, and E). Cost-benefit curves for PM detection in the performance evaluation cohort (Figure H).