Extended Data Fig. 8: Logistical regression model data.

(a) Table summarizing results of regression models using different features and their associated AUCROC and accuracy for following comparisons- IDC recurrence (n = 17) vs IDC non-recurrence (n = 20) samples, ILC recurrence (n = 21) vs non-recurrence (n = 30) samples, all ER+ recurrence (n = 38) and non-recurrence (n = 50) samples and IDC (n = 50) and ILC (n = 65) samples. Significant features with predictive value are highlighted in bold in blue color. (b) AUC-ROC curves across 5-folds of cross validation (colors represent folds of cross-validation) for ER+ IDC (n = 50 samples) vs ILC (n = 65 samples) subtype classification using neighborhood type (NT) frequencies as a feature and table of model weights associated with features of importance for classification model using neighborhood type frequencies (c) AUC-ROC curves across 5-folds of cross validation (colors represent folds of cross-validation) for ER+ IDC (n = 50 samples) vs ILC (n = 65 samples) subtype classification using cell type (CT) frequencies as a feature and associated table of model weights associated with features of importance (d) AUC-ROC curves across 5-folds of cross validation (colors represent folds of cross-validation) for ER+ IDC (n = 50 samples) vs ILC (n = 65 samples) subtype classification using neighborhood type (NT) and cell type (CT) frequencies together (NT+CT) as a feature and associated table of model weights associated with features of importance.