Identifying and Diagnosing Lytic Cell Death Genes in Atherosclerosis Using Machine Learning and Bioinformatics

Area of Science:

• Biomedical research
• Molecular biology
• Computational biology

Background:

• Lytic cell death (LCD) is increasingly recognized for its role in chronic inflammatory conditions like atherosclerosis (AS).
• Understanding the precise mechanisms of LCD in AS is crucial for developing new therapeutic strategies.
• This study leverages advanced bioinformatics and machine learning to explore LCD's involvement in AS pathogenesis.

Purpose of the Study:

• To investigate the role and mechanism of lytic cell death in atherosclerosis.
• To identify key genes and pathways associated with LCD in AS using machine learning.
• To develop a diagnostic model for AS based on LCD-related features.

Main Methods:

• Utilized gene expression data and single-cell sequencing from the GEO database.
• Identified differentially expressed genes (DEGs) and LCD-associated DEGs (LCDEGs).
• Developed and validated an artificial neural network (ANN) model for AS diagnosis and staging using ROC curves.

Main Results:

• The ANN model demonstrated high accuracy in distinguishing normal from AS cases and in identifying early versus advanced stages.
• Consensus clustering revealed two AS subtypes: C1 (non-immune, early-stage) and C2 (immune, advanced-stage).
• LCDEG activity was elevated in macrophages, particularly in the "inflammation" subtype, suggesting a macrophage-mediated mechanism.

Conclusions:

• Lytic cell death is implicated in atherosclerosis, primarily through a macrophage-mediated pathway.
• The study identified cytochrome B-245β chain (CYBB) as a potential diagnostic biomarker for AS.
• These findings highlight the clinical potential of targeting LCD in AS management.