High-Dimensional Cancer Microarray Gene Expression Datasets

This dataset comprises gene expression profiles from four distinct cancer types: Brain Tumor (CNS), Diffuse Large B-cell Lymphoma (DLBCL), Leukemia, and Prostate Cancer. The files include both .csv and .arff formats suitable for machine learning and bioinformatics analysis. Each dataset contains samples from cancer and control tissues, with features representing gene expression levels obtained from microarray experiments. This data was used to identify potential cancer-causing genes through preprocessing, gene ranking, metaheuristic-based feature selection, and classification. The aim is to support cancer research, gene discovery, and benchmark studies in computational biology.