Fig. 4: The single-cell 3D genome distinguishes and encodes cancer progression states.

a, Cartoon illustration of scA/B score calculation (top-left). t-SNE (top-right), UMAP (bottom-left) and PaCMAP (bottom-right) plots of single-cell 3D genome conformations. n = 3,410, 157, 689, 878 and 8,834 for WT AT2, AdenomaR, AdenomaG, AdenomaY and LUAD cells, respectively. Cell numbers of each cell state are identical in a–c, g and h. b, Confusion matrix of supervised machine learning in mouse lung cells. The number in each matrix element represents the precision in each predicted state. c, ROC curves of the machine learning model in mouse lung cells. The AUC values are shown. d, PCA plot of single-cell 3D genome conformations. n = 1,103, 191 and 268 for normal duct, PanIN and PDAC cells, respectively. Cell numbers of each cell state are identical in d–f. e, Confusion matrix of supervised machine learning in mouse pancreas cells. The number in each matrix element represents the precision in each predicted state. f, ROC curves of the machine learning model in mouse pancreas cells. The AUC values are shown. g, PCA plot of single-cell 3D genome conformations of adenoma and LUAD cells (left). Leiden clustering separates Adenoma-like and LUAD-like clusters (right). h, Percentages of cells with adenoma-like or LUAD-like 3D genome conformations in g, in each of the AdenomaR/AdenomaY, AdenomaG and LUAD states. The adenoma-like or LUAD-like conformation state for each cell is assigned based on a Leiden clustering approach. P values from two-sided Fisher’s exact test are shown. t-SNE, t-distributed stochastic neighbor embedding; UMAP, uniform manifold approximation and projection; PaCMAP, pairwise controlled manifold approximation; ROC, receiver operating characteristic; AUC, area under the curve.

Source data