Machine Learning Multi-Omics Data for Insomnia-Aggravated Sepsis Lung Injury

621.1 KB of multi-omics data identifies genes linking insomnia to sepsis-induced acute lung injury. The dataset, authored by Jinquan Zhang and last updated in 2026, results from Mendelian randomization, WGCNA, and machine learning analysis. It includes 1,294 co-dysregulated genes and three prioritized hub genes validated via single-cell RNA sequencing and in vivo experiments.

Use Cases

• Validate causal gene signatures for sepsis susceptibility based on Mendelian randomization results.
• Train diagnostic classifiers for acute lung injury using the identified hub genes ISG20, MYO1F, and PTPN6.
• Perform immune infiltration analysis based on macrophage-localized gene expression patterns.
• Conduct functional enrichment analysis on pathways like tuberculosis infection and chemokine signaling.
• Replicate machine learning model interpretability using SHAP on the refined gene signature.

Strengths

• Includes 1,294 co-dysregulated genes identified through weighted gene co-expression network analysis.
• Results are validated through multiple methods, including single-cell RNA sequencing and in vivo/vitro experiments.
• Machine learning analysis with SHAP interpretability identified three robust hub genes.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data may reflect bias inherent to the specific experimental models and omics platforms used.

Provenance

Source

Jinquan Zhang via figshare.

Collection Method

Integrative multi-omics analysis and machine learning on preclinical models and genetic data.

Freshness

Last updated 2026-06-01 04:17:32; freshness should be verified.