Research Article
Motif-Based Text Mining of Microbial Metagenome Redundancy Profiling Data for Disease Classification
Figure 3
ROC curves of motif finding step of PMF algorithm for pneumonia samples (CAP + HAP) in 2-class problem (a, b), normal samples (c, d), CAP samples in 3-class problem (e, f), and HAP samples in 3-class problem (g, h), with NNA or SVM.
(a) auc = 0.7943 |
(b) auc = 0.9652 |
(c) auc = 0.6347 |
(d) auc = 0.8810 |
(e) auc = 0.6139 |
(f) auc = 0.7648 |
(g) auc = 0.7219 |
(h) auc = 0.7520 |