Long Non-Coding RNAs and Alzheimer's Disease: Towards Personalized Diagnosis

Area of Science:

• Neuroscience
• Genetics
• Biomarker Discovery

Background:

• Alzheimer's disease (AD) is a progressive neurodegenerative disorder and the most common cause of dementia.
• Current AD diagnosis relies on a combination of clinical assessments and imaging, lacking a definitive single test, especially in diverse populations.
• Exosomes and their RNA cargo, particularly long non-coding RNAs (lncRNAs), are implicated in AD pathogenesis but their diagnostic potential is underexplored.

Purpose of the Study:

• To investigate the potential of lncRNAs as diagnostic markers for Alzheimer's disease.
• To identify differentially expressed lncRNAs in individuals with AD compared to controls.
• To develop and validate machine learning models for AD diagnosis based on lncRNA expression profiles.

Main Methods:

• Clinical, cognitive, and genetic characterization of 15 AD patients and 15 controls from Barranquilla, Colombia.
• Quantification of 28,909 lncRNAs using advanced bioinformatics and analytics.
• Application of Machine Learning (ML) models to identify diagnostic lncRNA signatures.

Main Results:

• Eighteen differentially expressed lncRNAs were identified, with 18 linked to pivotal AD-related genes.
• Two specific lncRNAs, ENST00000608936 and ENST00000433747, emerged as strong diagnostic candidates.
• ML models demonstrated >95% sensitivity, specificity, and accuracy for AD diagnosis in both training and testing datasets.

Conclusions:

• lncRNA expression profiles hold significant promise for advancing personalized Alzheimer's disease diagnosis.
• The identified lncRNAs offer potential for early detection and follow-up strategies, particularly in understudied communities.
• This study highlights a novel, data-driven approach to biomarker discovery for AD.