Topological Data Analysis for Identification of MicroRNAs As Biomarkers for Human Performance
Abstract
Micro-RNAs (miRNA) are non-coding RNAs that play a crucial role in regulating gene expression and have been linked to various physiological processes, including physical performance. However, miRNA expression profiles are highly nonlinear and high-dimensional, making it difficult to analyze them using conventional statistical methods. This seedling aims to explore the potential use of topological data analysis (TDA) as a robust approach to analyzing microRNAs (miRNAs) associated with human performance. TDA can capture the complex topological structure of miRNA expression data, identify important topological features, and integrate related features and metadata from multiple sources, thereby improving the reliability and robustness of the analysis. We propose the development of a deep topological machine learning algorithm based on TDA, combined with hierarchical decomposition, to uncover differences and relationships in miRNA expression patterns in subjects with traditional and high-intensity training. We hypothesize that using TDA, we will be able to provide richer insights into the functional role and signaling pathways of miRNAs identified for physical performance.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Mar 07, 2024
- Source ID
- FA95502310578
Entities
People
- Rajesh R Naik
Organizations
- Air Force Office of Scientific Research
- United States Air Force