Ultra-Sensitive Automated Profiling of EpCAM Expression on Tumor-Derived Extracellular Vesicles

Abstract

Extracellular vesicles (EVs) are abundant in most biological fluids and considered promising biomarker candidates, but the development of EV biomarker assays is hindered, in part, by their requirement for prior EV purification and the lack of standardized and reproducible EV isolation methods. We now describe a far-field nanoplasmon-enhanced scattering (FF-nPES) assay for the isolation-free characterization of EVs present in small volumes of serum (< 5 µl). In this approach, EVs are captured with a cancer-selective antibody, hybridized with gold nanorods conjugated with an antibody to the EV surface protein CD9, and quantified by their ability to scatter light when analyzed using a fully automated dark-field microscope system. Our results indicate that FF-nPES performs similarly to EV ELISA, when analyzing EV surface expression of epithelial cell adhesion molecule (EpCAM), which has clinical significant as a cancer biomarker. Proof-of-concept FF-nPES data indicate that it can directly analyze EV EpCAM expression from serum samples to distinguish early stage pancreatic ductal adenocarcinoma patients from healthy subjects, detect the development of early stage tumors in a mouse model of spontaneous pancreatic cancer, and monitor tumor growth in patient derived xenograft mouse models of pancreatic cancer. FF-nPES thus appears to exhibit strong potential for the direct analysis of EV membrane biomarkers for disease diagnosis and treatment monitoring.

Keywords: EpCAM; automated microscopy; biomarker profiling; exosome; extracellular vesicles; liquid biopsy.

Figure 1

– Schematic of the isolation-free profiling of EpCAM-expressing EVs in small (1 µl) serum samples using a far-field dark-field (FF-DF) microscope assay, in which both image capture and analysis are automated to reduce assay variability and potential operator bias.

Figure 2

FF-DF image (A) and standard curve (B) of PANC-1 EV dilutions analyzed with an EpCAM capture antibody and an anti-CD9 specific AuNR probe. Data were analyzed as described in the Materials and Methods section and represent mean ± SEM; n = 6 replicates/sample.

Figure 3

(A) Study timeline for the KPC and PDX mouse models. (B) EV EpCAM expression in longitudinal serum samples from a KPC mouse during tumor development. (C–E) EV EpCAM expression and their correlation with tumor size in longitudinal serum samples from PDX mice before and after tumor implantation. (Data were analyzed as described in the Materials and Methods section and represent mean ± SEM; n = 6 replicates/sample). **P-value = 0.0013, ***P-value < 0.0001; ns, P-value = 0.3331.

Figure 4

(A) EV EpCAM expression in serum samples from PDAC patients and healthy donors .**, P-value = 0.0011. (B) ROC curve of the ability to distinguish PDAC and healthy controls based on EV EpCAM signal. (C) Kaplan-Meier curve of overall survival time of patients with above average (high expression) and below average (low expression) serum EV EpCAM signal. (D–F) Difference in EV EpCAM signal in healthy controls and PDAC patients stratified by their histologic grade, tumor stage, and lymph node involvement (Data were analyzed as described in the Materials and Methods section and represent mean ± SEM; n = 6 replicates/sample). (D) **, P-value = 0.0053; ns, P-value = 0.9998. (E) **, P-value = 0.0018; ns, P-value = 0.3182. (F) *, P-value = 0.0299; ns, P-value = 0.9808.