Diagnostic plasma small extracellular vesicles miRNA signatures for pancreatic cancer using machine learning methods

Incorporation of explainable artificial intelligence in ensemble machine learning-driven pancreatic cancer diagnosis

Despite the strides made in medical science, pancreatic cancer continues to be a threat, highlighting the urgent need for creative strategies to address this concern. Recently, a potential approach that has attracted significant attention is using machine learning in clinical decision-making. This research aims to analyze six machine learning algorithms, and an ensemble voting classifier, develop hybrid models for the early detection of pancreatic cancer based on several clinical characteristics and interpret their performance with Shapley Additive Explanations (SHAP). A publicly available dataset composed of 590 patient urine samples was utilized to develop six conventional models for the classification of cancerous from non-cancerous pancreatic cases through the analysis of specific attributes. An ensemble voting classifier was developed from the best-performed single models, which were later hybridized to form six novel hybrid models. The ensemble voting classifier outperformed all stand-alone models with an accuracy of 96.61% and a precision of 98.72%. The six novel hybrid models exhibited higher performance than single models with voting classifier random forest hybridized model outperforming others with an AUC of 99.05% (95% confidence interval (CI): 0.93-1.00) and an interpretation was given by SHAP showing top influential features in pancreatic cancer diagnosis that exhibited the greatest positive SHAP values. Employing rapid sophisticated models with high accuracy and precision holds significant promise in facilitating the effective detection of various diseases, including pancreatic cancer.

Blood circulating miRNAs as pancreatic cancer biomarkers: An evidence from pooled analysis and bioinformatics study

Pancreatic cancer (PC) is one of the deadliest cancers, characterized by a poor prognosis. Currently, there are no screening programs for the early detection of PC, and existing diagnostic methods are primarily limited to high-risk individuals. Biomarkers such as CA19-9 have not significantly improved early diagnosis, making the identification of new potential biomarkers crucial for routine clinical practice. Among the candidate biomarkers, miRNAs have been most extensively studied due to their role in regulating gene expression (either as oncomiRs or tumor suppressor miRNAs) and their potential for minimally invasive analysis through liquid biopsy techniques. This review aims to summarize the current literature on blood-circulating miRNAs and their diagnostic value in PC detection, considering the context of CA19-9 and benign pancreatic diseases. The data from the collected studies were curated through both statistical and bioinformatics analyses to identify the most promising miRNAs with optimal diagnostic accuracy for PC detection and to assess their role in the molecular processes leading to tumor development.

Small Extracellular Vesicles from Young Healthy Human Plasma Inhibit Cardiac Fibrosis After Myocardial Infarction via miR-664a-3p Targeting SMAD4

Purpose

Cardiac fibrosis, a key contributor to ventricular pathologic remodeling and heart failure, currently lacks effective therapeutic approaches.

Patients and Methods

Small extracellular vesicles from young healthy human plasma (Young-sEVs) were characterized via protein marker, transmission electron microscopy, and nanoparticle tracking analysis, then applied in cellular models and mouse models of cardiac fibrosis. Western blotting and qRT-PCR were used to identify protective signaling pathways in cardiac fibroblasts (CFs).

Results

Young-sEVs significantly inhibited cardiac fibrosis and subsequent cardiac dysfunction post-myocardial infarction (MI) in mice. The main findings included that echocardiographic assessments four weeks post-MI indicated that Young-sEVs improved left ventricular ejection fraction (LVEF) and fractional shortening (LVFS), and reduced left ventricular internal diameter in diastole (LVIDd) and systole (LVIDs). Treatment with Young-sEVs also decreased Masson-positive fibroblast areas and collagen synthesis in cardiac tissue. However, sEVs from the old control group did not achieve the above effect. Consistent with in vivo results, Young-sEVs could also inhibit the proliferation, migration, and collagen synthesis of CFs in the TGF-β1-induced cellular fibrosis model. High-throughput microRNA (miRNA) sequencing and qRT-PCR analysis revealed that miR-664a-3p was abundant in Young-sEVs. The high expression of miR-664a-3p significantly inhibited the proliferation, migration, and collagen synthesis of TGF-β1-induced CFs. However, suppressing the expression of miR-664a-3p in Young-sEVs eliminated their therapeutic effect on cardiac fibrosis in mice. Further studies confirmed SMAD4 as a direct downstream target of miR-664a-3p, whose overexpression could reverse the anti-fibrotic effects of miR-664a-3p.

Conclusion

In summary, these findings firstly revealed that Young-sEVs could directly bind to the 3'-untranslated region of SMAD4 mRNA through miR-664a-3p, thereby inhibiting the TGF-β/SMAD4 signaling pathway to protect heart from fibrosis and improve cardiac function. Considering the ease of obtaining plasma-derived sEVs, our study offers a promising therapeutic strategy for heart failure, with the potential for rapid clinical translation in the near future.

MicroRNAs in Pancreatic Cancer: Advances in Biomarker Discovery and Therapeutic Implications

Pancreatic cancer remains a formidable malignancy characterized by high mortality rates, primarily attributable to late-stage diagnosis and a dearth of effective therapeutic interventions. The identification of reliable biomarkers holds paramount importance in enhancing early detection, prognostic evaluation, and targeted treatment modalities. Small non-coding RNAs, particularly microRNAs, have emerged as promising candidates for pancreatic cancer biomarkers in recent years. In this review, we delve into the evolving role of cellular and circulating miRNAs, including exosomal miRNAs, in the diagnosis, prognosis, and therapeutic targeting of pancreatic cancer. Drawing upon the latest research advancements in omics data-driven biomarker discovery, we also perform a case study using public datasets and address commonly identified research discrepancies, challenges, and limitations. Lastly, we discuss analytical approaches that integrate multimodal analyses incorporating clinical and molecular features, presenting new insights into identifying robust miRNA-centric biomarkers.