Fig. 2

Predicting favorable and adverse risk with k-mers (A1), average k-mer (B1), and genes selected by list (C1), genes selected by DEseq2 (D1) counts using Decision Tree (DT), K-nearest neighbors (KNN), and Logistic Regression (LR), Neural Network (NN), Random Forest (RF), and eXtreme Gradient Boosting (XGB) models. Metrics Area under the curve (AUC), accuracy (ACC), sensitivity (SENS), specificity (SPEC), and Matthew’s correlation coefficient (MCC) for evaluating models in younger and older patients. UMAP projection with k-mer (A2), average k-mer (B2), gene selected by list (C2), and genes selected by DEseq2 (D2) counts.