Genomic characterization of malignant progression in neoplastic pancreatic cysts

Abstract

Intraductal papillary mucinous neoplasms (IPMNs) and mucinous cystic neoplasms (MCNs) are non-invasive neoplasms that are often observed in association with invasive pancreatic cancers, but their origins and evolutionary relationships are poorly understood. In this study, we analyze 148 samples from IPMNs, MCNs, and small associated invasive carcinomas from 18 patients using whole exome or targeted sequencing. Using evolutionary analyses, we establish that both IPMNs and MCNs are direct precursors to pancreatic cancer. Mutations in SMAD4 and TGFBR2 are frequently restricted to invasive carcinoma, while RNF43 alterations are largely in non-invasive lesions. Genomic analyses suggest an average window of over three years between the development of high-grade dysplasia and pancreatic cancer. Taken together, these data establish non-invasive IPMNs and MCNs as origins of invasive pancreatic cancer, identifying potential drivers of invasion, highlighting the complex clonal dynamics prior to malignant transformation, and providing opportunities for early detection and intervention.

Fig. 1. Somatic mutations identified in matched noninvasive and invasive cancer samples.

a In each patient sample, multiple mutations were shared between the noninvasive and invasive cancer samples (gray). In addition, some mutations were limited to the noninvasive (blue/green), while others were limited to the cancer (red/pink). Darker colors indicate alterations that were likely restricted to one component but where sequencing coverage in the second component was limited. The proportions of shared and distinct mutations varied between different lesions. b Somatic mutations in the most frequently mutated genes are categorized as shared between noninvasive and cancer (gray), limited to noninvasive (blue), or limited to cancer (red). Mutations in some genes (such as KRAS) were always shared, while others were enriched in samples from noninvasive (RNF43) or cancer (SMAD4).

Fig. 2. Copy number alterations identified in matched noninvasive and invasive cancer samples.

Chromosomal gains (red) and losses (blue) are shown for each chromosome in each patient, with noninvasive samples on the left and cancer samples on the right.

Fig. 3. Somatic mutations identified in MTP19 and MTP8 in targeted and whole exome sequencing.

We show mutations identified in each sample, including low-grade IPMN (light blue), high-grade IPMN (dark blue), ductal cancer (red), mucinous cancer (pink), and cancerization (purple). The type of sequencing analysis (targeted or whole exome) performed for each sample is indicated in a track on the bottom. Representative images of neoplastic tissue stained by hematoxylin and eosin, as well as isolated regions before and after laser capture microdissection are shown for MTP19 and MTP8.

Fig. 4. Evolutionary reconstruction of samples analyzed by whole exome and targeted sequencing.

In all cases, noninvasive samples (blue/green) precede invasive samples (red/pink) in the evolutionary history. In MTP5, different invasive cancer samples are placed in different regions of the phylogeny, highlighting multiple independent invasion events in this lesion. In MTP19, a sample of cancerization (purple) has descended from invasive cancer samples.