Skip to main content
. Author manuscript; available in PMC: 2012 Dec 17.
Published in final edited form as: IEEE/ACM Trans Comput Biol Bioinform. 2008 Apr-Jun;5(2):291–300. doi: 10.1109/TCBB.2007.1074

Fig. 4.

Fig. 4

Results of leave-one-out cross validation on R5 versus X4 strains prediction. (a) Ability of the best neural networks to discriminate between R5 samples (0) and non-X4 samples (1). (b) The best probability of detection (P(D)) of 0.81 is achieved with a probability of false alarm (P(FA)) of 0.05 (area under the ROC curve A(z) = 0.927).