Zapisane w:
Opis bibliograficzny
Główni autorzy: Lütge, Mechthild, Nassiri, Sina
Format: Recurso digital
Język:angielski
Wydane: Zenodo 2026
Hasła przedmiotowe:
Dostęp online:https://doi.org/10.5281/zenodo.18933914
Etykiety: Dodaj etykietę
Nie ma etykietki, Dołącz pierwszą etykiete!
Spis treści:
  • <p>This package provides a complete workflow to discover robust tumor archetypes. It automates the following key steps:</p> <ul> <li>Scoring: Computes enrichment scores for gene signatures using ssGSEA or loads pre-calculated scores.</li> <li>Normalization: Optionally normalizes scores by tumor purity and scales signatures to ensure equal contribution.</li> <li>Dimensionality Reduction: Performs PCA on the enrichment scores.</li> <li>Clustering: Applies Louvain clustering across a user-defined grid of parameters (e.g., different variance cutoffs and k-neighbors).</li> <li>Characterization: Evaluates each clustering result using internal metrics, cluster stability, and association with clinical variables.</li> </ul> <p>Finally, the package helps you select an optimal clustering result and train a robust single-sample classifier that can be used to apply the derived subtypes to new datasets.</p>