Identifying Potential miRNA Biomarkers for Gastric Cancer Diagnosis Using Machine Learning Variable Selection Approach

Abstract

Aim: This study aimed to accurately identification of potential miRNAs for gastric cancer (GC) diagnosis at the early stages of the disease. Methods: We used GSE106817 data with 2,566 miRNAs to train the machine learning models. We used the Boruta machine learning variable selection approach to identify the strong miRNAs associated with GC in the training sample. We then validated the prediction models in the independent sample GSE113486 data. Finally, an ontological analysis was done on identified miRNAs to eliciting the relevant relationships. Results: Of those 2,874 patients in the training the model, there were 115 (4%) patients with GC. Boruta identified 30 miRNAs as potential biomarkers for GC diagnosis and hsa-miR-1343-3p was at the highest ranking. All of the machine learning algorithms showed that using hsa-miR-1343-3p as a biomarker, GC can be predicted with very high precision (AUC; 100%, sensitivity; 100%, specificity; 100% ROC; 100%, Kappa; 100) using with the cut-off point of 8.2 for hsa-miR-1343-3p. Also, ontological analysis of 30 identified miRNAs approved their strong relationship with cancer associated genes and molecular events. Conclusion: The hsa-miR-1343-3p could be introduced as a valuable target for studies on the GC diagnosis using reliable biomarkers.

Keywords: AUC; GSE106817; GSE113486; boruta algorithm; gastric cancer; hsa-miR-1343-3p; machine learning; miRNA.

FIGURE 1

Boxplot of the selected miRNA from Boruta Algorithm. (A), hsa-miR-1228-5p; (B), hsa-miR-8073; (C), hsa-miR-6746-5p; (D), hsa-miR-5100; (E), hsa-miR-4532; (F): hsa-miR-1343-3p; (G), hsa-miR-1290.

FIGURE 2

Correlation plot of the selected miRNAs. Dark blue and dark red shows the strength of the correlations between miRNAs.

FIGURE 3

Heathmap plot of clustering of 30 selected miRNAs.

FIGURE 4

GeneCodis Ontological analysis. Visualizations generated for 10 top terms of related categories with our identified miRNAs list are presented here for Transcription Factors (A), Co-annotation of miRNAs-based analysis using HMDD v3, MNDR, and TAM2 (B), GO Biological Process (C), GO Molecular Function (D), Co-annotation of KEGG Pathways, Panther Pathways, and WikiPathways databases (E), and Co-annotation of HPO and OMIM databases (F).