Predicting lung aging using scRNA-Seq data.

Area of Science:

• Genomics
• Computational Biology
• Aging Research

Background:

• Single-cell RNA sequencing (scRNA-Seq) provides high-resolution gene expression data.
• Accurate age prediction from scRNA-Seq can inform disease susceptibility and identify aging biomarkers.
• Existing methods for age prediction using scRNA-Seq have limitations.

Purpose of the Study:

• To develop a novel regression model, PolyEN, for accurate age prediction from scRNA-Seq data.
• To identify key cell types and genes associated with lung aging in smokers and non-smokers.
• To evaluate PolyEN's performance against existing age prediction methodologies.

Main Methods:

• Development of PolyEN, a regression model that learns continuous temporal expression representations.
• Integration of gene expression data to predict chronological age.
• Profiling and analysis of existing and newly generated lung aging scRNA-Seq datasets.

Main Results:

• PolyEN demonstrated superior performance in age prediction compared to existing methods.
• Lung epithelial cells were identified as significant predictors of age in non-smokers.
• Lung endothelial cells were found to be the most effective predictors of chronological age in smokers.

Conclusions:

• PolyEN offers an advanced approach for age prediction using scRNA-Seq data.
• The study highlights cell-type-specific differences in lung aging between smokers and non-smokers.
• This work contributes to understanding the molecular mechanisms of lung aging and its relationship with smoking status.