ViSTA data

This dataset is part of the manuscript with the following title- "ViSTA: Variant-integrated Sequence Transformer Architecture learns DNA mutational contexts for breast cancer subtyping" The dataset contains the following folders- ft_ViSTA: finetuned ViSTA model pt_ViSTA: pretrained ViSTA model ViSTA-main: ViSTA codeData: 1) Input data (variant integrated sequences, TCGA-BRCA) to finetune the ViSTA model; 2) CPTAC and METABRIC cohorts for independent evaluation; 3) TNBC/non-TNBC cohort information for downstream testing