Integrative multi-platform gene expression and machine learning analysis for glioblastoma biomarker discovery with...

Area of Science:

• Oncology
• Genomics
• Bioinformatics

Background:

• Glioblastoma (GBM) is an aggressive brain tumor with a poor prognosis.
• Identifying critical genes is essential for understanding glioma development.

Purpose of the Study:

• To identify genes crucial for glioma development.
• To assess the diagnostic and therapeutic potential of these genes in GBM.

Main Methods:

• Integrated analysis of microarray and RNA-Seq datasets.
• Utilized LASSO regression and seven machine learning classifiers for feature selection.
• Validated classifier performance on unseen datasets and biomarkers via qPCR.

Main Results:

• Identified PLOD1, COL4A2, and COL5A2 as key genes.
• PLOD1 was significantly associated with poor glioblastoma prognosis.
• High PLOD1 expression strongly correlates with GBM, indicating its potential as a diagnostic biomarker.

Conclusions:

• An integrative machine learning approach effectively discovered biomarkers for GBM.
• Findings support personalized treatment strategies for glioblastoma patients.