A personalized mRNA signature for predicting hypertrophic cardiomyopathy applying machine learning methods

Area of Science:

• Cardiovascular Research
• Bioinformatics
• Genomics

Background:

• Hypertrophic cardiomyopathy (HCM) is a significant cause of cardiac dysfunction and sudden cardiac death.
• Identifying reliable biomarkers for HCM is crucial for timely diagnosis and intervention.

Purpose of the Study:

• To develop a predictive signature for hypertrophic cardiomyopathy (HCM) using bioinformatics and machine learning.
• To identify key genes and pathways involved in HCM pathogenesis.
• To validate the clinical significance of identified genes in a model organism.

Main Methods:

• Differential gene expression analysis of HCM and normal tissue data from public databases.
• Gene Ontology (GO) and KEGG pathway enrichment analysis.
• Weighted Gene Co-expression Network Analysis (WGCNA) and machine learning algorithms (SVM-RFE, LASSO) for hub gene identification.
• Zebrafish model to assess the functional impact of identified hub genes on cardiac development.

Main Results:

• 157 differentially expressed genes (DEGs) were identified between HCM and normal tissues.
• Immune-related pathways were significantly enriched in HCM pathogenesis.
• Three hub genes (FCN3, MYH6, RASD1) were identified as key players in HCM.
• Knockdown of MYH6 and RASD1 in zebrafish led to cardiac malformations, validating their role in HCM.

Conclusions:

• A novel HCM signature was developed using integrated bioinformatics and machine learning approaches.
• The identified hub genes (MYH6, RASD1) are critical for normal cardiac development and function.
• This signature holds potential for improving early diagnosis and therapeutic strategies for HCM.