Published December 31, 2024 | Version v1
Dataset Open

Exploring the Boundaries of Medulloblastoma Subgroups with Synthetic Data Generation

Authors/Creators

  • 1. ROR icon Barcelona Supercomputing Center
  • 2. ROR icon Institució Catalana de Recerca i Estudis Avançats

Description

These datasets contain the synthetic data generated with a VAE in the Exploring the Boundaries of Medulloblastoma Subgroups with Synthetic Data Generation publication (https://doi.org/10.1101/2024.12.30.630738). First, `augmented_data.csv` contains both the real and synthetic patients as rows, and the corresponding genes as columns. Second, `augmented_metadata.csv` contains the subgroup to which each patient, synthetic and real, belong to: WNT, SHH, Group 3, Group 4, G3-G4, synthetic_Group 3, synthetic_Group 4, synthetic_G3-G4.

Files

augmented_data.csv

Files (285.6 MB)

Name Size Download all
md5:6a90304b23a24c8f112c7a167c56d2bb
285.5 MB Preview Download
md5:a1e5e38c4ae96b6da058b95e9a571b15
33.8 kB Preview Download

Additional details

Related works

Is published in
Preprint: 10.1101/2024.12.30.630738 (DOI)

Funding

European Commission
EVENFLOW - Robust Learning and Reasoning for Complex Event Forecasting 101070430

Software

Repository URL
https://github.com/gprolcastelo/scratchmedulloblastoma
Programming language
Python , R
Development Status
Active