Identification of Novel Diagnostic Markers for Atherosclerosis Using Machine-Learning Algorithms
1Department of Neurosurgery, The First Hospital of China Medical University, Liaoning, China.
Summary
This study identifies four key genes (IBSP, PI16, MYOC, IGLL5) involved in atherosclerosis by analyzing immune cell infiltration and gene expression. These genes show promise as diagnostic markers for atherosclerosis, potentially aiding in targeted therapies.
Area of Science:
- Cardiovascular Research
- Molecular Biology
- Bioinformatics
Background:
- Atherosclerosis (AS) is a chronic inflammatory disease.
- Understanding immune-cell infiltration is crucial for AS pathogenesis.
- Novel diagnostic markers are needed for effective AS management.
Purpose of the Study:
- To identify diagnostic genes related to immune-cell infiltration in atherosclerosis.
- To elucidate molecular processes underlying AS development.
- To explore potential therapeutic targets for AS.
Main Methods:
- Utilized Gene Expression Omnibus datasets for differential gene expression analysis.
- Applied gene set enrichment analysis to identify inflammation-related pathways.
- Employed machine-learning algorithms and ROC curves to identify and validate diagnostic genes.
Main Results:
- Identified 3,307 differentially expressed genes (DEGs), predominantly enriched in inflammatory pathways.
- Discovered four core genes (IBSP, PI16, MYOC, IGLL5) through machine learning, all linked to inflammation.
- Validated the diagnostic potential of these genes using ROC curves with high area under the curve values.
Conclusions:
- IBSP, PI16, MYOC, and IGLL5 are implicated in AS pathogenesis via inflammatory pathways.
- These genes represent novel diagnostic markers for atherosclerosis.
- The identified genes are potential targets for developing new AS-specific therapies.
