Decoding the Architecture of Tumour States: Integrating Transcriptomic Program Modules with Radiomic Phenotypes for Survival Risk Prediction in Lung Adenocarcinoma

Abstract

Lung adenocarcinoma (LUAD) exhibits substantial molecular heterogeneity, which complicates tumour stratification and limits the ability of mutation-centric models to capture tumour behaviour and predict patient outcomes. This thesis investigates whether coordinated transcriptomic programs can provide a systems-level representation of tumour states and whether these states manifest as imaging-derived phenotypes detectable in clinical computed tomography (CT) scans. Bulk RNA-sequencing data from the TCGA-LUAD cohort were analysed to reconstruct pathway-level transcriptomic organisation using a stability-optimised network framework (SPARK). This analysis identified eight transcriptomic modules representing coordinated biological processes active across tumours. Module activity scores were subsequently used to derive a composite Transcriptomic Risk Score through elastic-net Cox proportional hazards modelling. The resulting risk score showed a significant association with overall survival in the discovery cohort (multivariable hazard ratio = 2.82, 95% CI 1.84–4.33, p < 0.001) and improved prognostic discrimination beyond clinical variables (C-index = 0.711 compared with 0.688 for the clinical baseline). An independent evaluation in the CPTAC-LUAD cohort confirmed the prognostic signal and preserved risk stratification across patient groups. Unsupervised clustering of module activity further revealed three transcriptomic patient states characterised by distinct biological programs, genomic alteration patterns, and survival outcomes. Radiogenomic analysis demonstrated that CTderived radiomic features capture a measurable component of this transcriptomic risk landscape, with elastic-net modelling identifying texture-based radiomic predictors associated with transcriptomic risk. Together, these findings suggest that LUAD heterogeneity can be organised into coordinated transcriptomic programs with measurable clinical relevance and partial imaging correlates, providing a systems-level framework for integrating tumour molecular states with radiomic phenotypes.