Category: Huntington's Disease
Objective: This study explores histone modifications, an underexplored aspect of HD’s epigenetics, aiming to uncover markers influencing disease severity and onset for potential therapeutic targets.
Background: Huntington’s disease (HD) arises from genetic mutations in the HTT gene, but its variable manifestations suggest a significant role for epigenetic factors.
Method: We collected chromatin immunoprecipitation sequencing (ChIP-seq) data from neuronal cells derived from 100 HD patients and matched controls, focusing on key histone modifications known to impact gene expression, such as H3K4me3 and H3K27ac. This study integrates epigenetic data with whole-genome sequencing to identify correlations between histone modification patterns and HD clinical features, including age of onset and progression rate. Convolutional neural networks (CNNs) were employed for pattern recognition in histone modification peaks, while random forest (RF) algorithms integrated genomic and epigenetic data for predictive modeling. Model validation utilized a stratified cross-validation approach to ensure robustness and generalizability.
Results: Distinct histone modification patterns were associated with earlier HD onset and rapid progression, particularly H3K27ac near the HTT gene and genes related to neuronal survival and inflammation. The CNN-RF hybrid model achieved 88% accuracy in classifying early versus late onset, with an AUC of 0.94 and a mean absolute error of 2.3 years for onset prediction. Additionally, epigenetic changes correlated with a 30% increase in disease progression rate.
Conclusion: This study explores the use of machine learning to analyze HD’s complex epigenetic landscape, revealing novel histone modification patterns influencing disease onset and progression. By identifying specific epigenetic markers and genes for potential therapeutic targeting, it opens avenues for personalized medicine in HD and contributes to understanding epigenetic mechanisms in neurodegenerative diseases.
To cite this abstract in AMA style:
R. Fajar, E. Syfaruddin, S. Putri. Machine Learning-Driven Exploration of Epigenetic Patterns in Huntington’s Disease: Understanding Histone Modification Dynamics [abstract]. Mov Disord. 2024; 39 (suppl 1). https://www.mdsabstracts.org/abstract/machine-learning-driven-exploration-of-epigenetic-patterns-in-huntingtons-disease-understanding-histone-modification-dynamics/. Accessed October 4, 2024.« Back to 2024 International Congress
MDS Abstracts - https://www.mdsabstracts.org/abstract/machine-learning-driven-exploration-of-epigenetic-patterns-in-huntingtons-disease-understanding-histone-modification-dynamics/