cml-biomarker-discovery

This repository hosts a comprehensive Python-based GUI tool designed for differential expression analysis of the RXFP1 gene and classification of chronic myeloid leukemia (CML) samples. It integrates all key components of the analysis pipeline, including preprocessing, statistical testing (t-test, Mann–Whitney U), Random Forest-based machine learning, ROC curve generation, and exportable result reports. The package also includes biomarker discovery scripts based on gene expression data, identification of top-ranked genes, and expression visualization tools. Supplementary files include curated datasets, gene mapping resources, and summary plots. And also newly added cross data validation folder. Inspired by the author's personal experience with CML caregiving, this open-source tool is suitable for both exploratory bioinformatics research and potential clinical translation. It serves as a unified framework for AI-driven biomarker discovery in hematologic malignancies.