Integration of expression datasets to identify biomarkers for accurate Gleason scoring in Prostate Cancer -- Supplementary data

This dataset contains expression data from multiple sources used to identify biomarker candidates for prostate cancer aggressiveness. The data includes transcriptional expression levels, patient metadata, and other relevant features utilized in our machine-learning models. The training dataset was extracted from the repository described at Matos-Filipe, et al. (2022) [1]. Raw ML metrics from models gaussian Naïve Bayes classifiers using this dataset are available in [1] Matos-Filipe, P, et al. "The usage of transcriptomics datasets as sources of Real-World Data for clinical trialling". bioRxiv (2022). doi: https://doi.org/10.1101/2022.11.10.515995