Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: Robust edge-based biomarker discovery improves prediction of breast cancer metastasis

Fig. 1

AUC evaluation of edge-based RF model compared to gene-based RF model. The highlighted entry as “Bold” and “Underlined” indicates that the edge-based model outperformed gene-based model with statistical significance. Significance of the p-value of the paired t-test between the edge- and gene-based model AUCs is provided in the “P _Value” row under that edge-based feature type row. ***, ** and * indicate that the p-value is lower than 0.0005, 0.005 and 0.05 respectively. “ns” indicates that the p-value is not statistically significant. “Red” entry indicates that gene-based model outperformed edge-based model with statistical significance. Colors are provided for better visualization of the results

Back to article page
\