RESUMO
BACKGROUND: Identifying biomarkers may lead to easier detection and a better understanding of pathogenesis of pancreatic ductal adenocarcinoma (PDAC). METHODS: Plasma small extracellular vesicles (sEV) from 106 participants, including 20 healthy controls (HC), 12 chronic pancreatitis (CP) patients, 12 benign pancreatic tumour (BPT) patients, and 58 PDAC patients, were profiled for microRNA (miRNA) sequencing. Three machine learning methods were applied to establish and evaluate the diagnostic model. RESULTS: The plasma sEV miRNA diagnostic signature (d-signature) selected using the three machine learning methods could distinguish PDAC patients from non-PDAC individuals, HC, and benign pancreatic disease (BPD, CP plus BPT) both in training and validation cohort. Combining the d-signature with carbohydrate antigen 19-9 (CA19-9) performed better than with each model alone. Plasma sEV miR-664a-3p was selected by all methods and used to predict PDAC diagnosis with high accuracy combined with CA19-9. Plasma sEV miR-664a-3p was significantly positively associated with the presence of vascular invasion, lower surgery ratio, and poor differentiation. MiR-664a-3p was mainly distributed in the PDAC cancer stroma, including fibers and vessels, and was accompanied by VEGFA expression. Overexpression of miR-664a-3p could promote the epithelial-mesenchymal transition (EMT) and angiogenesis. CONCLUSION: In conclusion, our study demonstrated the potential utility of the sEV-miRNA d-signature in the diagnosis of PDAC via machine learning methods. A novel sEV biomarker, miR-664a-3p, was identified for the diagnosis of PDAC. It can also potentially promote angiogenesis and metastasis, provide insight into PDAC pathogenesis, and reveal novel regulators of this disease.