Skip to main content
. 2018 Apr 3;13:5. doi: 10.1186/s13062-018-0207-8

Fig. 2.

Fig. 2

Classification performance on all endpoints considered in the study: by classifier for the 498 (panels a and b) and the 145 (panels c and d) sample subsets, as well as by platform (panels e and f) for both sample subsets