Lactylation-Related Gene Biomarkers in Acute Myeloid Leukemia

Zhibo Guo's 2026 research provides a dataset of seven hub lactylation-related genes (LRGs) identified in acute myeloid leukemia. The data, derived from TCGA and GEO databases, includes prognostic biomarkers like GZMB and LSP1 validated through Mendelian randomization. It supports the development of machine learning models for AML prognosis.

Use Cases

• Train machine learning models like GLM or LASSO-logistic to predict AML prognosis using the seven hub LRGs (LSP1, MPO, GZMB, SPINK2, HLA-DRB1, HLA-DRA, POU2F2).
• Analyze the relationship between immune cell infiltration, assessed via CIBERSORT, and key LRG expression levels.
• Perform molecular docking simulations to screen drug candidates targeting the validated hub genes GZMB and LSP1.
• Validate lactylation-related gene signatures using the DALEX package across four machine learning models on external GEO datasets.

Strengths

• Identifies seven specific hub lactylation-related genes (LRGs) with functional enrichment in immune pathways.
• Includes two genes (GZMB and LSP1) validated through a two-sample Mendelian randomization analysis.
• Data is derived from authoritative public sources, including The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO).

Limitations

• The dataset is very small at 19.5 KB, indicating limited scope and likely containing only summary or key results, not raw expression data.
• Specific row and column counts, sample sizes, and detailed patient-level data are unavailable.
• Findings are specific to acute myeloid leukemia, limiting generalizability to other cancers or conditions.

Provenance

Source

Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) databases.

Collection Method

Computational analysis using Seurat, limma, WGCNA, and machine learning algorithms (LASSO-logistic, SVM-RFE, Boruta) on RNA and single-cell sequencing data.

Freshness

Last updated in March 2026, indicating recent analysis.