Patient-specific gene networks reveal novel subtypes and predictive biomarkers in lung cancer

Lung adenocarcinoma (LUAD) is an aggressive form of non-small cell lung cancer. Genome-wide gene co-expression networks (GCNs) has been paramount to describe changes in the transcriptional regulatory programs found between diseased and healthy states of LUAD. Multiple cancerous phenotypes share a distinct GCN architecture, suggesting that network topology holds promise for understanding disease pathology. However, conventional GCN inference methods struggle to capture specificity within a patient population, thus flattening its heterogeneity. To address this issue, the use of single-sample networks (SSN) has emerged as a promising solution. Here, we reconstructed patient-specific GCNs (n=334) using the LIONESS equation. Unsupervised analysis revealed six novel LUAD subtypes based on inter-patient network similarity, reflecting unique biological programs. Supervised analysis, employing regularized Cox regression, identified 12 genes (CHRDL2, SPP2, VAC14, IRF5, GUCY1B1, NCS1, RRM2B, EIF5A2, CCDC62, CTCFL, XG, and TP53INP2) whose weighted degree in SSNs is predictive of patient survival in LUAD. These findings suggest that topological features of SSNs offer insights into the context-specific nature of LUAD, highlighting the potential of SSN-based approaches for further research.