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

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

Keywords: bioinformatics; machine learning; melanoma; microRNA.

FIGURE 1

Predictive partition analysis (PPA) shows the most differentiating markers predicting melanoma diagnosis.

FIGURE 2

MicroRNAs–genes interaction and enrichment analysis. (A) The miRNA–miRNA interactions all considered microRNAs and related genes. The pink circles represent all predicted target genes, and the blue ones represent the microRNAs implicated in cancer‐related pathways. The lines represent the connection of components. (B) Well‐known target genes for melanoma in associations with the considered differentially expressed miRNAs (DEMs). (C) Gene Ontology (GO) enrichment and KEGG pathway analysis of the differentially expressed genes (DEGs), including biological process (red bars), cellular components (green bars), molecular function (blue bars).

FIGURE 3

Reactome signal transduction of R‐HSA‐162582 (https://reactome.org/content/detail/R‐HSA‐162582).

FIGURE 4

Protein–protein interaction (PPI) network between all of the target genes of considered miRNAs. (A) Common differentially expressed genes (DEGs) and PPI network constructed by Cytoscape database and module analysis, the central circle with darker blue represents the hub genes introduced in this study; (B) the molecular complex detection (MCODE) analysis of top two cluster of highly interconnected genes; (C) 119 drug–gene interaction pairs based on the DGIdb predictions of the module genes, purple square indicates the DEGs and green square indicates the drugs.