A Global Reference Balanced Gene Expression Dataset for Acute Lymphoblastic Leukemia Subtypes

This dataset presents a global reference and balanced gene expression resource for Acute Lymphoblastic Leukemia (ALL) subtypes. It was constructed by integrating 13 publicly available GEO microarray datasets, resulting in a unified and harmonized dataset covering 258 samples across 9 ALL subtypes and normal controls. The dataset includes 54,675 genes and is balanced to ensure fair representation of each subtype, making it suitable for use in machine learning, biomarker discovery, and translational leukemia research. Files provided include both the balanced dataset and the complete dataset with metadata, enabling reproducibility and global benchmarking in leukemia genomics research.