A computational framework for identifying cytoskeletal genes associated with age-related diseases.

Abstract

The cytoskeleton comprises polymers from protein filaments shaped in an organized structure. This structure contributes significantly to the cell's function and viability. Decades of research have implicated that the cytoskeleton's dynamic nature is associated with downstream signaling events that further regulate cellular activity and control aging and neurodegeneration. This study aims to investigate the transcriptional changes of the cytoskeletal genes and their regulators in five age-related diseases: Hypertrophic Cardiomyopathy (HCM), Coronary Artery Disease (CAD), Alzheimer's disease (AD), Idiopathic Dilated Cardiomyopathy (IDCM), and Type 2 Diabetes Mellitus (T2DM). An integrative approach of machine learning-based models and differential expression analysis was employed to identify potential biomarkers based on the cytoskeletal genes. Multiple machine-learning algorithms were used, where the Support Vector machines (SVM) classifier achieved the highest accuracy. The study highlighted 17 genes involved in the cytoskeleton's structure and regulation associated with age-related diseases. The results provide a holistic overview of the role of transcriptionally dysregulated cytoskeletal genes in age-related diseases. This study pinpoints cytoskeletal genes and regulators of the cytoskeleton that can be utilized as potential markers and drug targets.