To establish whether non-muscle-invasive (NMI) and muscle-invasive (MI) tumours arise from a distinct or common progenitor cell, Dancik et al. developed a novel statistical framework that predicts cell-of-origin (COO) score as a function of known genetic alterations (TP53, HRAS, KDM6A, and FGFR3) that drive either MI or NMI bladder cancer, and compared this to the observed COO score of the tumour. Analysis of data from 874 patients established the distinct progenitor cell model as the best fit to the available data.