Using the below script I was able to create a labeled and coloured boxplot and calculate p-value for 2 classes, eg LB/B and LP/P which were established by VKGL.
Now I want to create an ROC curve for both classes thereby determining the optimal cut-off (youden index) and in addtion determine the PPV. Is possible to integrate this in the below script?
Does anybody have an idea how to do this?
Note, I have already installed following packagess
- filter(classification %in% c("LB/B", "LP/P") & Source %in% c("VKGL"))%>%
- ggplot(mapping=aes(x=classification, y=
Backbone Hbond, color="red", fill = "orange", alpha=0.2))+
- labs(title = "Backbone Hbond for LB/B and LP/P classes (VKGL)",
x = "Classification",
y = "Backbone Hbond")+
- stat_compare_means(label.x = 1.3, size = 4)