Identification of Glycolysis-Related Diagnostic Biomarkers for Amyotrophic Lateral Sclerosis Using Machine Learning

Area of Science:

• Neuroscience
• Metabolic Disorders
• Genetics

Background:

• Glycometabolism alterations are linked to amyotrophic lateral sclerosis (ALS) pathogenesis.
• Molecular mechanisms connecting glycometabolism and ALS are not well understood.
• Reliable ALS biomarkers are needed for early diagnosis and improved patient outcomes.

Purpose of the Study:

• Investigate the causal relationship between blood glucose levels and ALS risk.
• Identify potential diagnostic biomarkers for ALS.
• Elucidate the role of specific genes in ALS pathogenesis.

Main Methods:

• Two-sample Mendelian randomization analysis.
• Differential gene expression analysis.
• Machine learning algorithms (gradient boosting tree) and correlation analyses.
• Bulk and single-cell RNA sequencing validation.

Main Results:

• A significant negative causal relationship was found between blood glucose levels and ALS risk.
• A predictive model for ALS diagnosis achieved an AUC of 0.8782.
• COL5A1 and VCAN were identified as key genes in ALS pathogenesis, potentially via glycolytic pathways.

Conclusions:

• Novel insights into glycometabolism's role in ALS pathogenesis.
• COL5A1 and VCAN are promising diagnostic biomarkers for ALS.
• Further validation in larger datasets and clinical trials is required for clinical translation.