An integrated machine learning framework for developing a transcriptomic analysis and machine learning-based...

Area of Science:

• Genomics
• Computational Biology
• Immunology

Background:

• Gout is common in inflammatory arthritis and frequently co-occurs with sleep disorders (SDs).
• This comorbidity is pronounced in patients with impaired renal function undergoing blood purification, with unknown mechanisms.
• Identifying shared genetic markers could elucidate underlying pathways and aid diagnosis.

Purpose of the Study:

• To identify shared genetic markers between gout and sleep disorders.
• To develop a diagnostic model for gout utilizing sleep disorder-related genes.
• To establish a molecular framework linking gout pathogenesis and sleep disruption.

Main Methods:

• Systematic analysis of transcriptomic datasets from gout and sleep disorder patients.
• Identification and analysis of differentially expressed genes (DEGs) common to both conditions.
• Machine learning model development using shared DEGs for gout diagnosis.

Main Results:

• Eight shared differentially expressed genes (DEGs) were identified between gout and sleep disorders.
• Key pathways implicated include DNA-binding protein serine/threonine kinase activity and JAK/STAT signaling.
• A robust 8-gene diagnostic signature was constructed, offering potential biomarkers for gout.

Conclusions:

• This study reveals a novel molecular connection between gout pathogenesis and sleep disruption.
• The identified shared genes and diagnostic model provide potential tools for early gout diagnosis.
• Findings support precision treatment strategies by linking gout to sleep-related genetic factors.