Skip to main content
. Author manuscript; available in PMC: 2024 Apr 10.
Published in final edited form as: Cancer Cell. 2023 Apr 10;41(4):791–806.e4. doi: 10.1016/j.ccell.2023.03.010

Figure 6. Statistical models are improved by including prior anti-CTLA-4 experience to predict response to anti-PD-1 in cutaneous melanoma.

Figure 6.

(A) Feature selection using cross-validated lasso-regularized logistic regression for 90 paired WES and RNAseq baseline cutaneous melanoma tumors treated with anti-PD-1, with or without prior anti-CTLA-4, comparing CR/PR to PD. (B) Heatmap of selected features for 3 fitted models. Color indicates magnitude and direction of the standardized coefficient for that feature. Gray indicates that the feature was not selected. (C) Predicted probabilities from leave-one-out cross-validation (LOOCV) logistic regression comparing CR/PR vs PD using all selected features from (B) in each respective model. The y-axis indicates probability of response. The top and bottom facets indicate the clinically annotated true response to anti-PD-1. LOOCV accuracy is at the bottom. See Figure S7.