Single Cell Transcriptomics Genomics Based on Machine Learning Algorithm: Constructing and Validating Neutrophil...

Area of Science:

• Immunology
• Pulmonology
• Genetics

Background:

• Neutrophil extracellular traps (NETs) are implicated in chronic inflammatory diseases.
• Limited research exists on NET characteristics in diverse chronic obstructive pulmonary disease (COPD) patient populations.
• Understanding NETs in COPD is crucial for disease management.

Purpose of the Study:

• To identify NET signature genes specific to different COPD patient groups.
• To develop predictive models for COPD based on NET gene expression.
• To lay the groundwork for personalized therapeutic approaches in COPD.

Main Methods:

• Analysis of single-cell RNA sequencing data from COPD and non-COPD individuals.
• Identification of differentially expressed neutrophil genes.
• Application of machine learning to construct predictive models (Model A for smokers, Model B for non-smokers).

Main Results:

• 165 neutrophil characteristic genes identified in COPD patients.
• Validated models (A: CD63, RNASE2, ERAP2; B: GRIPAP1, NHS, EGFLAM, GLUL) showed significant diagnostic efficacy (AUC: 60.24-87.22).
• Elevated RNASE2 and NHS expression observed in severe COPD patients' alveolar lavage fluid.

Conclusions:

• Novel NET signature gene models were developed for distinct COPD subgroups (smoking and non-smoking).
• The models demonstrated validated specificity and predictive capabilities.
• These findings provide a basis for developing personalized treatment strategies for COPD patients.