The abstract is read at the publisher; the summary is JClub's.
SNOWS identifies three survival-informed mutational clusters in 950 adult-type diffuse gliomas from TCGA, and their transferred cluster assignments raise C-index from 0.691 to 0.712.
- Why it matters: Patient-to-patient heterogeneity limits outcome prediction, and existing molecular subtypes may not capture survival-linked mutation dependencies.
- What they did: SNOWS (Survival-iNfOrmed netWork cluStering) uses Bayesian networks to integrate somatic mutations, clinical covariates, and survival information to cluster TCGA patients, then transfers the clusters to classify 181 CGGA patients without using survival outcomes.
- The result: The transferred clusters show distinct survival, mutation profiles, and dependency structures, with prognostic information beyond WHO 2021 tumour subtype, age, and sex, and network dependencies particularly improve assignments for patients with less typical molecular profiles.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.