Related Experiment Video
Updated: Oct 14, 2025
09:47
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
1.3K
Application of Machine Learning and Weighted Gene Co-expression Network Algorithm to Explore the Hub Genes in the
Keping Chai1, Jiawei Liang2, Xiaolin Zhang3
1Department of Pediatrics, Zhejiang Hospital, Hangzhou, China.
Frontiers in Aging Neuroscience
|November 4, 2021
Summary
Aging accelerates neurodegeneration and dementia by altering gene expression in the frontal cortex. This study identifies key genes like MAPT and SYN1 linked to aging, offering potential therapeutic targets for age-related cognitive decline.
Area of Science:
- Neuroscience
- Genetics
- Computational Biology
Background:
- Aging is a primary risk factor for neurodegenerative diseases and dementia.
- The precise mechanisms by which aging contributes to these conditions remain largely unknown.
- Understanding age-related molecular changes is crucial for developing effective interventions.
Purpose of the Study:
- To investigate the relationship between aging and gene expression patterns in the human frontal cortex.
- To identify potential biomarkers and therapeutic targets for age-related neurodegeneration and dementia.
- To leverage machine learning and network analysis to uncover aging-associated molecular pathways.
Main Methods:
- Utilized transcriptional profiling data from the human frontal cortex across a wide age range (26-106 years).
- Employed Self-Organizing Feature Map (SOM) to identify age-downregulated gene clusters.
- Applied Weighted Gene Co-expression Network Analysis (WGCNA) to identify age-correlated gene modules.
- Integrated differentially expressed genes (DEGs) with WGCNA modules and used Random Forest for significant gene identification.
Main Results:
- Identified a 'greenyellow' module negatively correlated with age, enriched in long-term potentiation and calcium signaling pathways.
- Discovered significant overlapping genes between age-downregulated DEGs and the 'greenyellow' module.
- Pinpointed key co-expressed genes including MAPT, KLHDC3, RAP2A, RAP2B, ELAVL2, and SYN1 as highly correlated with aging.
Conclusions:
- Aging significantly impacts gene expression in the human frontal cortex, particularly affecting pathways involved in synaptic function.
- Identified specific genes (MAPT, KLHDC3, RAP2A, RAP2B, ELAVL2, SYN1) as potential molecular indicators and therapeutic targets for age-related neurodegeneration.
- Machine learning and WGCNA provide powerful tools for dissecting complex age-related molecular changes in the brain.
Keywords:
SOM (self-organization map)WGCNA (weighted gene co-expression network analyses)aging brainmachine learningrandom forest
