Work

Survival-informed mutational network clustering reveals prognostic glioma architectures

Year: 2026
Type: preprint
Abstract: Cancer heterogeneity remains a major challenge for predicting patient outcomes. To address this challenge, we introduce SNOWS (Survival-iNfOrmed netWork cluStering), a probabilistic framework that integrates somatic mutations, clinical covariates and survival information to discover patient groups with distinct mutation patterns and survival profiles, using Bayesian networks to capture dependencies involving mutations and clinical variables. Applied to 950 adult-type diffuse gliomas from TCGA, SNOWS identified three clusters that transferred successfully to classify an independent CGGA cohort of 181 patients using mutation and clinical data, without requiring their survival outcomes. The transferred clusters showed distinct survival, mutation profiles and dependency structures, and provided prognostic information beyond WHO 2021 tumour subtype, age and sex, significantly increasing the C-index from 0.691 to 0.712. Cluster assignments were driven by specific mutation frequencies, with network dependencies improving the assignments of patients with less typical molecular profiles. Beyond glioma, SNOWS also improved prognostic discrimination in pan-kidney and pan-myeloid cohorts. These results support survival-informed network clustering as a general framework for resolving clinically relevant cancer heterogeneity.
Language: English
Subfield: Oncology
Field: Medicine
Open Access status: green
OpenAlex ID: W7233725315
Cites: 35
Cited by:
Related to: 10