Data from the article titled "Automatic discovery of 100-miRNA signature for cancer classification using ensemble feature selection". The article discusses a method for identifying a minimal set of miRNAs (microRNAs) that can effectively distinguish between different types of cancer and normal tissues. The researchers used an ensemble feature selection strategy to identify a 100-miRNA signature from a dataset of 8023 samples extracted from The Cancer Genome Atlas (TCGA). This signature was found to be robust and reliable, providing nearly the same classification accuracy as the original dataset with 1046 features. The study demonstrated that this 100-miRNA signature could be used across different platforms and cancer types, making it a valuable tool for cancer diagnosis and research