Diagnostic Power of MicroRNAs in Melanoma: Integrating Machine Learning for Enhanced Accuracy and Pathway Analysis

Journal of Cellular and Molecular Medicine, Journal Year: 2025, Volume and Issue: 29(2)

Published: Jan. 1, 2025

ABSTRACT This study identifies microRNAs (miRNAs) with significant discriminatory power in distinguishing melanoma from nevus, notably hsa‐miR‐26a and hsa‐miR‐211, which have exhibited diagnostic potential accuracy of 81% 78% respectively. To enhance accuracy, we integrated miRNAs into various machine‐learning (ML) models. Incorporating AUC scores above 0.70 significantly improved to 94%, a sensitivity 91%. These findings underscore the ML models leverage miRNA data for enhanced diagnosis. Additionally, using miRNet tool, constructed network miRNA–miRNA interactions, revealing 170 key genes pathophysiology. Protein–protein interaction analysis via Cytoscape identified hub including MYC, BRCA1, JUN, AURKB, CDKN2A, DDX5, MAPK14, DDX3X, DDX6, FOXM1 GSK3B. The identification their interactions enhances our understanding molecular mechanisms driving melanoma. Pathway enrichment analyses highlighted pathways associated differentially expressed miRNAs, PI3K/AKT, TGF‐beta signalling pathway cell cycle regulation. are implicated development progression, reinforcing significance findings. functional suggests critical role modulating essential melanoma, suggesting as therapeutic targets.

Language: Английский

Identification of targetable epigenetic vulnerabilities in uveal melanoma

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 11, 2024

Uveal melanoma (UM) is the most prevalent primary intraocular malignancy in adults, which preferentially metastasizes to liver approximately half of all cases. Metastatic UM notoriously resistant therapy and almost uniformly fatal. metastasis strongly associated with mutational inactivation

Language: Английский