datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
biolatent-brca-tcgaYear: 2025License: TCGA/GDC Data Use PoliciesAuthor: Sepideh Moafi
BioLatent-BRCA-TCGA Dataset
Dataset Summary
A processed transcriptomic dataset derived from TCGA-BRCA RNA-seq data, developed as part of the OmniLatent research project for representation learning on high-dimensional gene-expression data.
The dataset contains 1,231 samples × 23,375 genes with log1p(TPM) transformation and gene filtering applied.
Source and Provenance
Source: NCI… See the full description on the dataset page: https://huggingface.co/datasets/Sepideh2027/biolatent-brca-tcga.TCGA_BRCA_Datasetglm_for_BRCABRCA