Preprocessed TCGA Breast Invasive Carcinoma Multi-Omics Dataset with Survival Annotations

Preprocessed multi-omics dataset from TCGA Breast Invasive Carcinoma (BRCA), comprising RNA-seq gene expression, DNA methylation, and copy number variation data for 710 patients across 16,163 genes. The dataset underwent comprehensive preprocessing and quality control, including ComBat batch correction (55% reduction in technical variance), quantile normalization and log-transformation for expression data, β-value to M-value transformation for methylation data, and KNN-based imputation for missing values. All three omics layers are gene-aligned and biologically validated through expected cross-omics correlations. The dataset is fully analysis-ready and suitable for downstream machine learning tasks such as survival prediction, molecular subtyping, and integrative multi-omics studies.