272 breast cancer patients (as rows), 1570 columns. Network built using only gene expression. Meta data includes patient info, treatment, and survival.
Each node is a group of patients similar to each other. Flares (left) represent sub-populations that are distinct from the larger population. (One differentiating factor between the two flares is estrogen expression (low = top flare, high = bottom flare)). Bottom flare is a group of patients with 100% survival. Top flare shows a range of survival – very poor towards the tip (red), and very good near the base (circled).
The circled group of good survivors have genetic indicators of poor survivors (i.e. low ESR1 levels, which is typically the prognostic indicator of poor outcomes in breast cancer) – understanding this group could be critical for helping improve mortality rates for this disease. Why this group survived was quickly analysed by using the Outcome Column (here Event Death - which is binary - 0,1) as a Data Lens (which we term Supervised vs Unsupervised analyses).
Published in 2 papers - Nature and PNAS: