The State of the Art on Blood MicroRNAs in Pancreatic Ductal Adenocarcinoma

Development of a Diagnostic Model for Pancreatic Ductal Adenocarcinoma Using Machine Learning and Blood-Based miRNAs

INTRODUCTION

Pancreatic ductal adenocarcinoma (PDAC) has the lowest survival rate among all major cancers due to a lack of symptoms in early stages, early detection tools, and optimal therapies for late-stage patients. Thus, effective and non-invasive diagnostic tests are greatly needed. Recently, circulating miRNAs have been reported to be altered in PDAC. They are promising biomarkers because of stability in the blood, ease of non-invasive detection, and convenient screening methods. This study aimed to use blood-based miRNA biomarkers and various analysis methods in the development of a machine-learning (ML) model for PDAC.

METHODS

Blood-based miRNAs associated with PDAC were collected from open sources. miRNA sequences, targeted genes, and involved pathways were used to construct a set of descriptors for an ML model.

RESULTS

Bioinformatics analysis revealed that most genes in pancreatic cancer and insulin signaling pathways were targeted by the PDAC-related miRNAs. The best-performing ML model with the Random Forest classifier was able to achieve an accuracy of 88.4%. Model evaluations of an independent PDAC-associated miRNAs test set had 100% accuracy while non-cancer miRNAs had 52.4% accuracy, indicating specificity to PDAC.

CONCLUSIONS

Our results suggest an ML model developed using blood-based miRNA biomarkers' target gene, pathway, and sequence features could be potentially implicated in PDAC diagnostics.

Circulating miRNAs as Noninvasive Biomarkers for PDAC Diagnosis and Prognosis in Mexico

Among malignant neoplasms, pancreatic ductal adenocarcinoma (PDAC) has one of the highest fatality rates due to its late detection. Therefore, it is essential to discover a noninvasive, early, specific, and sensitive diagnostic method. MicroRNAs (miRNAs) are attractive biomarkers because they are accessible, highly specific, and sensitive. It is crucial to find miRNAs that could be used as possible biomarkers because PDAC is the eighth most common cause of cancer death in Mexico. With the help of microRNA microarrays, differentially expressed miRNAs (DEmiRNAs) were found in PDAC tissues. The presence of these DEmiRNAs in the plasma of Mexican patients with PDAC was determined using RT-qPCR. Receiver operating characteristic curve analysis was performed to determine the diagnostic capacity of these DEmiRNAs. Gene Expression Omnibus datasets (GEO) were employed to verify our results. The Prisma V8 statistical analysis program was used. Four DEmiRNAs in plasma from PDAC patients and microarray tissues were found. Serum samples from patients with PDAC were used to validate their overexpression in GEO databases. We discovered a new panel of the two miRNAs miR-222-3p and miR-221-3p that could be used to diagnose PDAC, and when miR-221-3p and miR-222-3p were overexpressed, survival rates decreased. Therefore, miR-222-3p and miR-221-3p might be employed as noninvasive indicators for the diagnosis and survival of PDAC in Mexican patients.

Early Diagnosis of Pancreatic Cancer: Clinical Premonitions, Timely Precursor Detection and Increased Curative-Intent Surgery

BACKGROUND

The overall poor prognosis in pancreatic cancer is related to late clinical detection. Early diagnosis remains a considerable challenge in pancreatic cancer. Unfortunately, the onset of clinical symptoms in patients usually indicate advanced disease or presence of metastasis.

ANALYSIS AND RESULTS

Currently, there are no designated diagnostic or screening tests for pancreatic cancer in clinical use. Thus, identifying risk groups, preclinical risk factors or surveillance strategies to facilitate early detection is a target for ongoing research. Hereditary genetic syndromes are a obvious, but small group at risk, and warrants close surveillance as suggested by society guidelines. Screening for pancreatic cancer in asymptomatic individuals is currently associated with the risk of false positive tests and, thus, risk of harms that outweigh benefits. The promise of cancer biomarkers and use of 'omics' technology (genomic, transcriptomics, metabolomics etc.) has yet to see a clinical breakthrough. Several proposed biomarker studies for early cancer detection lack external validation or, when externally validated, have shown considerably lower accuracy than in the original data. Biopsies or tissues are often taken at the time of diagnosis in research studies, hence invalidating the value of a time-dependent lag of the biomarker to detect a pre-clinical, asymptomatic yet operable cancer. New technologies will be essential for early diagnosis, with emerging data from image-based radiomics approaches, artificial intelligence and machine learning suggesting avenues for improved detection.

CONCLUSIONS

Early detection may come from analytics of various body fluids (eg 'liquid biopsies' from blood or urine). In this review we present some the technological platforms that are explored for their ability to detect pancreatic cancer, some of which may eventually change the prospects and outcomes of patients with pancreatic cancer.

Plasma-Derived Exosome MiR-19b Acts as a Diagnostic Marker for Pancreatic Cancer

Background

Diagnosis of pancreatic cancer (Pca) is challenging. This study investigated the value of plasma-derived exosome miR-19b (Exo-miR-19b) in diagnosing patients with Pca.

Methods

Plasma was collected from 62 patients with Pca, 30 patients with other pancreatic tumor (OPT), 23 patients with chronic pancreatitis (CP), and 53 healthy volunteers. MiR-19b levels in plasma-derived exosomes were detected.

Results

Plasma-derived Exo-miR-19b levels normalized using miR-1228 were significantly lower in Pca patients than in patients with OPT, CP patients, and healthy volunteers. The diagnostic values of Exo-miR-19b normalized using miR-1228 were superior to those of serum cancer antigen 19-9 (CA19-9) in differentiating Pca patients from healthy volunteers (area under the curve (AUC): 0.942 vs. 0.813, p = 0.0054), potentially better than those of CA19-9 in differentiating Pca patients from CP patients (AUC: 0.898 vs. 0.792, p = 0.0720), and equivalent to those of CA19-9 in differentiating Pca patients from patients with OPT (AUC: 0.810 vs. 0.793, p = 0.8206). When normalized using Caenorhabditis elegans miR-39 (cel-miR-39), Exo-miR-19b levels in Pca patients were significantly higher than those in patients with OPT, CP patients, and healthy volunteers. The diagnostic values of Exo-miR-19b normalized using cel-miR-39 were equivalent to those of CA19-9 in differentiating Pca patients from healthy volunteers (AUC: 0.781 vs. 0.813, p = 0.6118) and CP patients (AUC: 0.672 vs. 0.792, p = 0.1235), while they were inferior to those of CA19-9 in differentiating Pca patients from patients with OPT (AUC: 0.631 vs. 0.793, p = 0.0353).

Conclusion

Plasma-derived Exo-miR-19b is a promising diagnostic marker for Pca. The diagnostic value of plasma-derived Exo-miR-19b normalized using miR-1228 is superior to that of serum CA19-9 in differentiating patients with Pca from healthy volunteers.

Extracellular Vesicle-Dependent Cross-Talk in Cancer-Focus on Pancreatic Cancer

Extracellular vesicles (EVs) like exosomes and shed microvesicles are generated by many different cells. However, among all the cells, cancer cells are now recognized to secrete more EVs than healthy cells. Tumor-derived EVs can be isolated from biofluids such as blood, urine, ascitic fluid, and saliva. Their numerous components (nucleic acids, proteins, and lipids) possess many pleiotropic functions involved in cancer progression. The tumor-derived EVs generated under the influence of tumor microenvironment play distant roles and promote cellular communication by directly interacting with different cells. Moreover, they modulate extracellular matrix remodeling and tumor progression. Tumor-derived EVs are involved in pre-metastatic niche formation, dependent on the EV-associated protein receptors, and in cancer chemoresistance as they transfer drug-resistance-related genes to recipient cells. Recent advances in preclinical and clinical fields suggest their potential use as biomarkers for diagnosis and prognosis as well as for drug delivery in cancer. In this Review, we discuss EV characteristics and pro-tumor capacities, and highlight the future crucial impact of tumor-derived EVs in pancreatic cancer diagnosis and prognosis.