Fig. 5: Discovery and validation of atypical subpopulations in triple-negative breast cancer (TNBC) and luminal A patients. | Communications Medicine

Fig. 5: Discovery and validation of atypical subpopulations in triple-negative breast cancer (TNBC) and luminal A patients.

From: Deep learning and transfer learning identify breast cancer survival subtypes from single-cell imaging data

Fig. 5

a Sankey plot showing the distribution of patients in the seven subpopulations vs. clinical subtypes. b Kaplan-Meier (KM) survival plot for the two TNBC subpopulations in the single-cell dataset and the differentially expressed protein biomarkers for the two subpopulations. c Validation of the two TNBC subpopulations in TCGA breast cancer data corresponding to those in (b) by KM plot and differentially expressed genes. d Validation of the two TNBC subpopulations in METABRIC breast cancer data corresponding to those in (b) by KM plot and differentially expressed genes. e KM survival plot for the two luminal A subpopulations in the single-cell dataset and the differentially expressed protein biomarkers for the two subpopulations. f Validation of the two luminal A subpopulations in TCGA breast cancer data corresponding to those in (e) by KM plot and differentially expressed genes. g Validation of the two luminal A subpopulations in METABRIC breast cancer data corresponding to those in (e) by KM plot and differentially expressed genes. (For each subplot, the blue curve represents the subpopulation in context).

Back to article page