A novel multiomics machine learning signature identifies rapid progression in clinically low risk prostate cancer

Risk stratification in primary prostate cancer remains heavily reliant on clinicopathological criteria that frequently miss the heterogeneity underlying early aggressive disease. We present a novel machine learning non-linear prognostic framework encoding somatic copy-number alterations and biological information associated with gene products, along with an integrative multi-omics approach including epigenomics and transcriptomics into a patient-specific biological network. Applied to the TCGA-PRAD (n = 498), our weighted graph-based feature selection and LASSO-Cox model identified ZNF268 as a master regulator gene, in which the hypermethylation of its promoter region is linked to a distinct oncogenic transition exclusive to Low/Intermediate-risk disease. Post-hoc analysis of Low-ZNF268 tumors showed a distinct somatic landscape enriched for driver mutations and predicted sensitivity to MAPK, ATR, and PI3K/mTOR inhibitors, providing potential therapeutic vulnerabilities alongside the prognostic signal. Topological network analysis further revealed that ZNF268 loss impacts a co-expression rewiring gene network, quantified as a Rewiring Score: associated with Progression-Free Survival in the TCGA-PRAD (HR: 2.79, 95% CI: 1.36-5.71, p = 0.0049) and Biochemical Recurrence in two external cohorts. By capturing tumors at an active molecular transition state preceding systemic progression, this framework offers a prognostic tool to identify biologically aggressive prostate cancer disease within patients currently undertreated by standard risk criteria.