Architecting the metabolic reprogramming survival risk framework in LUAD through single-cell landscape analysis: three-stage ensemble learning with genetic algorithm optimization

Sun, Xinti; Nong, Minyu; Meng, Fei; Sun, Xiaojuan; Jiang, Lihe; Li, Zihao; Zhang, Peng

doi:10.1186/s12967-024-05138-2

Fig. 1

From: Architecting the metabolic reprogramming survival risk framework in LUAD through single-cell landscape analysis: three-stage ensemble learning with genetic algorithm optimization

Cellular dynamics changing across early, advanced, and metastatic LUAD. (A) The cell distribution of the samples showed no significant batch effect. (B) The t-SNE map of cells from all scRNA-seq samples, colored by cell-type annotation. (C) Dot plot showing representative marker genes for each cell type. (D) The proportion of each cell type from tissues of each origin, as indicated. (E) Line chart showing tissue prevalence for each cell type estimate by Ro/e score. (F) Graded heatmap showing CNVs of epithelial cells from tissues of each origin. Normal lung origin epithelial cells are used as a control reference. Red: gains; blue: losses. (G) K-means clustering of inferred CNVs to obtain cancer cells. (H) Violin plot showing the difference in CNV score of the five K-means clusters

Back to article page

Fig. 1

Journal of Translational Medicine

Contact us