Hypoxia- and Lactylation-Associated Gene Signature for Lung Adenocarcinoma Prognosis

A gene expression signature model for lung adenocarcinoma prognosis, constructed using LASSO, XGBoost, and Random Forest algorithms. The dataset was created by Guannan Wang and last updated on May 1, 2026. It integrates single-cell RNA-seq data and includes experimental validation of the core gene PABPC1.

Use Cases

• Predicting patient prognosis based on a hypoxia- and lactylation-related gene signature.
• Characterizing the immune landscape of lung adenocarcinoma subtypes.
• Predicting immunotherapy response using TIDE-based analysis.
• Performing drug sensitivity analysis for potential therapeutic implications.
• Assessing cell-type-specific gene expression using integrated single-cell RNA-seq data.

Strengths

• Model constructed using multiple machine learning algorithms (LASSO, XGBoost, Random Forest).
• Includes experimental validation via qRT-PCR, CCK-8, and other assays on two LUAD cell lines.
• Integrates single-cell RNA-seq data for cell-type-specific analysis.

Limitations

• The number of rows and specific columns are unknown, limiting assessment of dataset scale and structure.
• The primary data file is a PDF (810.9 KB), which likely contains summarized results rather than raw, analyzable data tables.
• Column-level documentation is absent; field semantics must be inferred after download.

Provenance

Source

figshare

Collection Method

Constructed via bioinformatic analysis of gene expression data and validated with cell-based experiments.

Freshness

Last updated 2026-05-01 05:24:51; freshness should be verified.