EVENFLOW Personalised Medicine use case: Breast Invasive Carcinoma datasets collection

These datasets contain the synthetic data generated with a VAE from the TCGA-BRCA dataset. The file Static_BRCA.csv contains a pre-processed version of the bulk-RNASeq dataset from TCGA-BRCA. Two synthetic datasets are available (both compressed), where 50 timepoints were inferred: trajectories_1_to_2_test.csv.tar.gz simulates the progression of RNASeq data between patients at stages 1 and 2, while trajectories_2_to_3_test.csv.tar.gz contains the same sort of progression from stage 2 to 3. Finally, nodes_metadata.csv contains the clinical information of the patients (with columns: sample name, histological_type (lobular or ductal) ,gender, race, stage, and subtype). Trained models used for the synthetic data generation are available in Hugging Face.