Key factor screening in mouse NASH model using single-cell sequencing combined with machine learning.

Area of Science:

• Hepatology and Immunology
• Genomics and Bioinformatics

Background:

• Nonalcoholic steatohepatitis (NASH) is a complex liver disease with poorly understood genetic drivers.
• Identifying key genes is crucial for developing targeted therapies.

Purpose of the Study:

• To pinpoint and analyze genes critical to nonalcoholic steatohepatitis (NASH) progression.
• To leverage single-cell RNA sequencing (scRNA-seq) and machine learning for gene discovery.

Main Methods:

• scRNA-seq analysis to compare cell populations in Chow and NASH groups.
• High dimensional Weighted Gene Co-expression Network Analysis (hdWGCNA) to identify NASH-related gene modules.
• Machine learning and deep learning (CNNs) to identify core genes and their correlation with immune cells.

Main Results:

• Distinct Kupffer cell populations identified between Chow and NASH groups.
• Heightened signaling interactions involving hepatic macrophages in NASH.
• 150 NASH-associated genes identified, with 16 core genes highlighted by machine learning.
• Close correlation established between core genes and immune cells.

Conclusions:

• scRNA-seq and machine learning effectively identify NASH-related genes from large datasets.
• This approach provides a foundation for discovering novel therapeutic targets for NASH.