Molecular Pathway and Immune Profile Analysis of IPMN-Derived Versus PanIN-Derived Pancreatic Ductal Adenocarcinomas

Abstract

Intraductal papillary mucinous neoplasms (IPMN) are commonly detected pancreatic cysts that may transform into pancreatic ductal adenocarcinoma (PDAC). Predicting which IPMNs will progress to PDAC remains a clinical challenge. Moreover, identifying those clinically evident IPMNs for which a surveillance approach is best is a dire clinical need. Therefore, we aimed to identify molecular signatures that distinguished between PDAC with and without clinical evidence of an IPMN to identify novel molecular pathways related to IPMN-derived PDAC that could help guide biomarker development. Data from the Oncology Research Information Exchange Network (ORIEN) multi-institute sequencing project were utilized to analyze 66 PDAC cases from Moffitt Cancer Center and The Ohio State University Wexner Medical Center, for which tumor whole transcriptome sequencing datasets were generated. Cases were classified based on whether a tumor had originated from an IPMN (n = 16) or presumably through the pancreatic intraepithelial neoplasia (PanIN) pathway (n = 50). We then performed differential expression and pathway analysis using Gene-Set Enrichment Analysis (GSEA) and Pathway Analysis with Down-weighted Genes (PADOG) algorithms. We also analyzed immune profiles using the Tumor-Immune Microenvironment Deconvolution web portal for Bulk Transcriptomics (TIMEx). Both GSEA and TIMEx indicate that PanIN-derived PDAC tumors enrich inflammatory pathways (complement, hedgehog signaling, coagulation, inflammatory response, apical surface, IL-2/STAT5, IL-6/STAT3, EMT, KRAS signaling, apical junction, IFN-gamma, allograft rejection) and are comparatively richer in almost all immune cell types than those from IPMN-derived PDAC. IPMN-derived tumors were enriched for metabolic and energy-generating pathways (oxidative phosphorylation, unfolded protein response, pancreas beta cells, adipogenesis, fatty acid metabolism, protein secretion), and the most significantly upregulated genes (padj < 0.001) included mucin 2 (MUC2) and gastrokine-2 (GKN2). Further, the metabolic-linked gene signature enriched in the IPMN-derived samples is associated with a cluster of early-stage and long-survival (top 4th quartile) PDAC cases from The Cancer Genome Atlas (TCGA) expression database. Our data suggest that IPMN-derived and PanIN-derived PDACs differ in the expression of immune profiles and metabolic pathways. These initial findings warrant validation and follow-up to develop biomarker-based strategies for early PDAC detection and treatment.

Keywords: IPMN; PanIN; pancreatic ductal adenocarcinoma; transcriptomics.

Figure 1

Flowchart of all eligible samples analyzed. Sample types are denoted in red font. A total of 66 samples were included in the analytic dataset (16 IPMN-derived and 50 PanIN-derived tumors). Abbreviations: FFPE, formalin-fixed paraffin-embedded; QC, quality control; MCC, Moffitt Cancer Center; and OSU, The Ohio State University.

Figure 2

Expression profiles differ between IPMN- and PanIN-derived tumors. Figure 2 shows a volcano plot of differential expression (x-axis) for IPMN-derived versus PanIN-derived tumors. PanIN-derived tumors were used as the reference and thus have negative fold change values.

Figure 3

PanIN-derived tumors are enriched for genes in inflammatory pathways, whereas IPMN-derived tumors are enriched for genes in energy production/metabolism pathways. (A,B) Bar graph of the normalized enrichment score (NES) on the x-axis versus the GSEA “Hallmark” pathways (A) or immune cell signatures (B) on the y-axis. Gene sets with a p-value of >0.05 are excluded.

Figure 4

IPMN-derived metabolic gene sets cluster in The Cancer Genome Atlas data with Stage I and low-grade tumors: Heatmaps showing patient samples (y-axis) and genes in IPMN-derived and non-IPMN-derived gene sets (x-axis). Hierarchical clustering was performed on gene sets. Patients were annotated based on disease-specific survival (DSSurvival, based on quartiles), stage (AJCC), and grade (1, 2, 3, 4 or not graded (GX)).